[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-qupath--qupath":3,"tool-qupath--qupath":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",144730,2,"2026-04-07T23:26:32",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107888,"2026-04-06T11:32:50",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":64,"owner_name":72,"owner_avatar_url":73,"owner_bio":74,"owner_company":75,"owner_location":75,"owner_email":75,"owner_twitter":64,"owner_website":76,"owner_url":77,"languages":78,"stars":101,"forks":102,"last_commit_at":103,"license":104,"difficulty_score":32,"env_os":105,"env_gpu":105,"env_ram":105,"env_deps":106,"category_tags":110,"github_topics":111,"view_count":32,"oss_zip_url":75,"oss_zip_packed_at":75,"status":17,"created_at":128,"updated_at":129,"faqs":130,"releases":160},5473,"qupath\u002Fqupath","qupath","QuPath - Open-source bioimage analysis for research","QuPath 是一款专为生物医学研究打造的开源图像分析软件，旨在帮助科研人员高效处理显微镜图像和全玻片扫描数据。它主要解决了生物图像数据量大、分析流程复杂以及传统方法难以实现精准量化等痛点，让细胞计数、组织分类等繁琐工作变得自动化且可重复。\n\n这款软件特别适合生物学家、病理学家及生命领域研究人员使用，同时也为需要定制分析流程的开发者提供了强大的脚本扩展能力。QuPath 的核心亮点在于其交互式的机器学习功能，用户无需深厚的编程背景，即可通过简单标注训练模型，轻松完成细胞分割、像素分类及组织微阵列解阵等高级任务。此外，它还支持批量处理和与 ImageJ 等主流工具的无缝集成，确保了分析方法的开放性与透明度。作为一款由学术界主导开发的工具，QuPath 致力于让复杂的图像分析变得直观、透明且易于获取，是探索微观世界得力的科研助手。","[![Image.sc forum](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdynamic\u002Fjson.svg?label=forum&url=https%3A%2F%2Fforum.image.sc%2Ftags%2Fqupath.json&query=%24.topic_list.tags.0.topic_count&colorB=brightgreen&suffix=%20topics&logo=data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAA4AAAAOCAYAAAAfSC3RAAABPklEQVR42m3SyyqFURTA8Y2BER0TDyExZ+aSPIKUlPIITFzKeQWXwhBlQrmFgUzMMFLKZeguBu5y+\u002F\u002F17dP3nc5vuPdee6299gohUYYaDGOyyACq4JmQVoFujOMR77hNfOAGM+hBOQqB9TjHD36xhAa04RCuuXeKOvwHVWIKL9jCK2bRiV284QgL8MwEjAneeo9VNOEaBhzALGtoRy02cIcWhE34jj5YxgW+E5Z4iTPkMYpPLCNY3hdOYEfNbKYdmNngZ1jyEzw7h7AIb3fRTQ95OAZ6yQpGYHMMtOTgouktYwxuXsHgWLLl+4x++Kx1FJrjLTagA77bTPvYgw1rRqY56e+w7GNYsqX6JfPwi7aR+Y5SA+BXtKIRfkfJAYgj14tpOF6+I46c4\u002FcAM3UhM3JxyKsxiOIhH0IO6SH\u002FA1Kb1WBeUjbkAAAAAElFTkSuQmCC)](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)\n[![Total downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fqupath\u002Fqupath\u002Ftotal?style=flat)](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases)\n[![Latest release downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fqupath\u002Fqupath\u002Flatest\u002Ftotal?style=flat)](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Flatest)\n[![Paper](https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.1038\u002Fs41598-017-17204-5.svg)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-017-17204-5)\n[![Twitter](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Fqupath?style=flat)](http:\u002F\u002Ftwitter.com\u002Fqupath)\n\n# QuPath\n\n**QuPath is open source software for bioimage analysis**.\n\nFeatures include:\n\n* Lots of tools to annotate and view images, including whole slide & microscopy images\n* Workflows for brightfield & fluorescence image analysis\n* New algorithms for common tasks, including cell segmentation, tissue microarray dearraying\n* Interactive machine learning for object & pixel classification\n* Customization, batch-processing & data interrogation by scripting\n* Easy integration with other tools, including ImageJ\n\nTo **download QuPath**, go to the [Latest Releases](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Flatest) page.\n\nFor **documentation**, see [https:\u002F\u002Fqupath.readthedocs.io](https:\u002F\u002Fqupath.readthedocs.io)\n\nFor **help & support**, try [image.sc](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) or the [links here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fstarting\u002Fhelp.html)\n\nTo **build QuPath from source** see [here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Freference\u002Fbuilding.html).\n\n**If you find QuPath useful in work that you publish, please [_cite the publication_](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\n\n*QuPath is an academic project intended for research use only.*\n*The software has been made freely available under the terms of the [GPLv3](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FLICENSE) in the hope it is useful for this purpose, and to make analysis methods open and transparent.*\n\n\n## Development & support\n\nQuPath is being actively developed at the University of Edinburgh by:\n\n* [Pete Bankhead](https:\u002F\u002Fgithub.com\u002Fpetebankhead) (creator)\n* [Fiona Inglis](https:\u002F\u002Fgithub.com\u002Ffinglis)\n* [Alan O'Callaghan](https:\u002F\u002Fgithub.com\u002Falanocallaghan)\n* [Léo Leplat](https:\u002F\u002Fgithub.com\u002FRylern)\n* [Laura Nicolás-Sáenz](https:\u002F\u002Fgithub.com\u002Flauranicolass)\n\nPast QuPath dev team members:\n\n* Melvin Gelbard\n* Mahdi Lamb\n\nFor all contributors, see [here](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fgraphs\u002Fcontributors).\n\nThis work is made possible in part thanks to funding from:\n\n* [Wellcome Trust Technology Development Grant](https:\u002F\u002Fwellcome.org\u002Fgrant-funding\u002Fpeople-and-projects\u002Fgrants-awarded\u002Fqupath-advanced-open-platform-next-generation) (2022-Present)\n* [CZI Essential Open Source Software for Science, Cycle 4](https:\u002F\u002Fchanzuckerberg.com\u002Feoss\u002Fproposals\u002Fqupath-boosting-bioimage-analysis-for-users-developers\u002F) (2022-2025)\n* [CZI Essential Open Source Software for Science, Cycle 1](https:\u002F\u002Fchanzuckerberg.com\u002Feoss\u002Fproposals\u002Fqupath-open-source-bioimage-analysis-and-quantitative-pathology\u002F) (2020-2022)\n* Wellcome Trust \u002F University of Edinburgh Institutional Strategic Support Fund (ISSF3) (2019-2020)\n\n\n----\n\n## Background\n\nQuPath was first designed, implemented and documented by Pete Bankhead while at Queen's University Belfast, with additional code and testing by Jose Fernandez.\n\nVersions up to v0.1.2 are copyright 2014-2016 The Queen's University of Belfast, Northern Ireland.\nThese were written as part of projects that received funding from:\n\n* Invest Northern Ireland (RDO0712612)\n* Cancer Research UK Accelerator (C11512\u002FA20256)\n\n\n![Image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fqupath_qupath_readme_f96aca4a168d.jpg)\n","[![Image.sc 论坛](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdynamic\u002Fjson.svg?label=forum&url=https%3A%2F%2Fforum.image.sc%2Ftags%2Fqupath.json&query=%24.topic_list.tags.0.topic_count&colorB=brightgreen&suffix=%20topics&logo=data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAA4AAAAOCAYAAAAfSC3RAAABPklEQVR42m3SyyqFUR0TDyExZ+aSPIKUlPIITFzKeQWXwhBlQrmFgUzMMFLKZeguBu5y+\u002F\u002F17dP3nc5vuPdee6299gohUYYaDGOyyACq4JmQVoFujOMR77hNfOAGM+hBOQqB9TjHD36xhAa04RCuuXeKOvwHVWIKL9jCK28xhAneeo9VNOEaBhzALGtoRy02cIcWhE34jj5hYwxuXsHgWLLl+4x++Kx1FJrjLTagA77bTPvYgw1rRqY56e+w7GNYsqX6JfPwi7aR+Y5SA+BXtKIRfkecgAjziPpOG4+U44sg5\u002FgZgpmZmZnJxyKsxiOIhH0IO6SH\u002FA1Kb1WBeUjbkAAAAAElFTkSuQmCC)](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)\n[![总下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fqupath\u002Fqupath\u002Ftotal?style=flat)](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases)\n[![最新版本下载量](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fqupath\u002Fqupath\u002Flatest\u002Ftotal?style=flat)](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Flatest)\n[![论文](https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.1038\u002Fs41598-017-17204-5.svg)](https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-017-17204-5)\n[![Twitter](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Fqupath?style=flat)](http:\u002F\u002Ftwitter.com\u002Fqupath)\n\n# QuPath\n\n**QuPath 是一款用于生物图像分析的开源软件**。\n\n其功能包括：\n\n* 丰富的工具用于标注和查看图像，涵盖全切片图像及显微镜图像；\n* 针对明场与荧光图像分析的工作流程；\n* 面向常见任务的新算法，如细胞分割、组织微阵列去排布等；\n* 用于对象和像素分类的交互式机器学习；\n* 通过脚本实现的自定义功能、批处理以及数据查询；\n* 易于与其他工具（如 ImageJ）集成。\n\n要 **下载 QuPath**，请访问 [最新版本页面](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Flatest)。\n\n有关 **文档**，请参阅 [https:\u002F\u002Fqupath.readthedocs.io](https:\u002F\u002Fqupath.readthedocs.io)。\n\n如需 **帮助和支持**，可尝试访问 [image.sc](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 或查阅 [此处链接](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fstarting\u002Fhelp.html)。\n\n若想 **从源代码构建 QuPath**，请参考 [此处](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Freference\u002Fbuilding.html)。\n\n**如果您在已发表的研究工作中使用了 QuPath，请务必 [_引用相关文献_](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)**！\n\n*QuPath 是一项仅面向科研用途的学术项目。*\n*该软件根据 [GPLv3](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FLICENSE) 协议免费提供，旨在促进开放透明的分析方法，并为科研工作提供实用工具。*\n\n\n## 开发与支持\n\nQuPath 目前由爱丁堡大学的以下团队成员积极开发：\n\n* [Pete Bankhead](https:\u002F\u002Fgithub.com\u002Fpetebankhead)（创始人）\n* [Fiona Inglis](https:\u002F\u002Fgithub.com\u002Ffinglis)\n* [Alan O'Callaghan](https:\u002F\u002Fgithub.com\u002Falanocallaghan)\n* [Léo Leplat](https:\u002F\u002Fgithub.com\u002FRylern)\n* [Laura Nicolás-Sáenz](https:\u002F\u002Fgithub.com\u002Flauranicolass)\n\n过往的 QuPath 开发团队成员包括：\n\n* Melvin Gelbard\n* Mahdi Lamb\n\n所有贡献者名单请见 [此处](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fgraphs\u002Fcontributors)。\n\n本项目得以顺利推进，部分归功于以下机构的资助：\n\n* [Wellcome Trust 技术开发基金](https:\u002F\u002Fwellcome.org\u002Fgrant-funding\u002Fpeople-and-projects\u002Fgrants-awarded\u002Fqupath-advanced-open-platform-next-generation)（2022年至今）\n* [CZI 科学领域关键开源软件计划第四轮](https:\u002F\u002Fchanzuckerberg.com\u002Feoss\u002Fproposals\u002Fqupath-boosting-bioimage-analysis-for-users-developers\u002F)（2022—2025年）\n* [CZI 科学领域关键开源软件计划第一轮](https:\u002F\u002Fchanzuckerberg.com\u002Feoss\u002Fproposals\u002Fqupath-open-source-bioimage-analysis-and-quantitative-pathology\u002F)（2020—2022年）\n* Wellcome Trust \u002F 爱丁堡大学机构战略支持基金 (ISSF3)（2019—2020年）\n\n\n----\n\n## 背景\n\nQuPath 最初由 Pete Bankhead 在贝尔法斯特女王大学任职期间设计、实现并编写文档，Jose Fernandez 提供了额外的代码和测试支持。\n\n截至 v0.1.2 版本的代码版权归北爱尔兰贝尔法斯特女王大学所有，创作时间为 2014—2016 年。这些版本是在以下项目的资助下完成的：\n\n* Invest Northern Ireland（RDO0712612）\n* 英国癌症研究基金会加速器项目（C11512\u002FA20256）\n\n\n![图片](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fqupath_qupath_readme_f96aca4a168d.jpg)","# QuPath 快速上手指南\n\nQuPath 是一款开源的生物图像分析软件，专为全切片成像（WSI）和显微镜图像设计。它提供细胞分割、组织微阵列解阵、交互式机器学习分类以及强大的脚本批处理功能，并支持与 ImageJ 无缝集成。\n\n## 环境准备\n\n*   **操作系统**：支持 Windows、macOS 和 Linux。\n*   **Java 环境**：\n    *   QuPath 自带运行时环境，通常无需单独安装 Java。\n    *   若需进行二次开发或从源码构建，请确保安装 **Java 17** 或更高版本。\n*   **硬件建议**：\n    *   内存：建议至少 8GB RAM，处理大型全切片图像时推荐 16GB 或以上。\n    *   存储：预留足够空间存放大型图像数据及临时缓存文件。\n\n## 安装步骤\n\nQuPath 提供预编译的二进制包，推荐直接下载解压使用，无需复杂安装命令。\n\n1.  **下载安装包**\n    访问官方发布页面下载最新版本：\n    ```text\n    https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Flatest\n    ```\n    *   **Windows 用户**：下载 `QuPath-x.x.x-win.zip`\n    *   **macOS 用户**：下载 `QuPath-x.x.x-mac.zip` (Intel\u002FApple Silicon 通用)\n    *   **Linux 用户**：下载 `QuPath-x.x.x-linux.tar.gz`\n\n2.  **解压与运行**\n    *   **Windows**: 解压 ZIP 文件，双击运行 `QuPath.exe`。\n    *   **macOS**: 解压后，将 `QuPath.app` 拖入“应用程序”文件夹，或直接双击运行。\n        *   *注意*：若首次运行提示“无法打开”，请在“系统设置”>“隐私与安全性”中允许运行，或在终端执行：\n        ```bash\n        xattr -cr \u002FApplications\u002FQuPath.app\n        ```\n    *   **Linux**: 解压 tar.gz 文件，进入目录并赋予执行权限后运行：\n        ```bash\n        tar -xzf QuPath-*-linux.tar.gz\n        cd QuPath-*\n        chmod +x QuPath\n        .\u002FQuPath\n        ```\n\n## 基本使用\n\n以下是最简单的操作流程，用于打开图像并进行基础的细胞检测：\n\n1.  **启动项目**\n    打开 QuPath，点击 `File` > `New Project` 创建一个新项目文件夹（可选，但推荐用于管理数据）。\n\n2.  **导入图像**\n    将生物图像文件（如 `.svs`, `.ndpi`, `.tif`, `.ome.tif` 等）直接拖入 QuPath 主窗口，或通过 `File` > `Open...` 加载。\n\n3.  **运行细胞检测（示例）**\n    在菜单栏选择 `Analyze` > `Cell detection` > `Run cell detection`。\n    *   在弹出的对话框中，根据图像类型（明场\u002FBrightfield 或 荧光\u002FFluorescence）调整参数。\n    *   点击 `Run`，软件将自动分割细胞并在图像上叠加标注。\n\n4.  **脚本批处理（进阶）**\n    按 `Ctrl+Shift+B` (Windows\u002FLinux) 或 `Cmd+Shift+B` (macOS) 打开脚本编辑器。输入以下 Groovy 脚本示例以打印当前图像中的细胞数量：\n\n    ```groovy\n    \u002F\u002F 获取当前图像中的所有检测对象\n    def detections = getDetectionObjects()\n    \n    \u002F\u002F 输出数量\n    print \"检测到的细胞数量：\" + detections.size()\n    \n    \u002F\u002F 遍历并打印每个细胞的面积\n    detections.each { cell ->\n        println \"细胞 ID: ${cell.getID()}, 面积：${cell.getMeasurementList().getMeasurementValue('Area µm^2')}\"\n    }\n    ```\n    点击编辑器上方的绿色运行按钮即可执行。\n\n5.  **导出结果**\n    选择 `File` > `Export measurements` 可将分析结果导出为 CSV 格式，以便在 Excel 或 Python\u002FR 中进一步分析。","某癌症研究中心的病理学家正试图从数百张全切片扫描图像中，量化肿瘤微环境内特定免疫细胞的密度与分布，以评估新药疗效。\n\n### 没有 QuPath 时\n- **人工计数效率极低**：研究人员需在显微镜下目视估算或手动点击计数成千上万个细胞，处理一张切片耗时数小时，且极易疲劳出错。\n- **多通道分析困难**：面对荧光标记的多重免疫组化图像，缺乏统一工具同时查看明场与荧光通道，难以精准区分重叠表达的蛋白信号。\n- **结果不可复现**：不同研究员对“阳性细胞”的判断标准主观不一，导致数据波动大，无法满足发表级研究对可重复性的严格要求。\n- **批量处理缺失**：无法自动化运行分析流程，每新增一批实验样本都需重新进行繁琐的手工操作，严重拖慢项目进度。\n\n### 使用 QuPath 后\n- **自动化细胞分割**：利用内置的先进算法一键完成全切片细胞检测与分割，将单张图像分析时间从数小时缩短至几分钟，精度显著提升。\n- **多模态交互分析**：在同一界面无缝切换明场与荧光视图，通过交互式机器学习快速训练分类器，精准识别复杂背景下的特定免疫细胞亚群。\n- **标准化工作流**：将分析步骤固化为可共享的脚本或项目文件，确保团队所有成员基于完全一致的参数运行，消除人为偏差，数据可信度大幅提高。\n- **高效批量执行**：编写简单脚本即可对数百张切片进行无人值守的批量处理与数据导出，让研究人员能将精力集中于生物学结论的挖掘而非重复劳动。\n\nQuPath 通过将繁琐的主观目测转化为标准化、自动化的定量分析流程，极大地释放了生物医学影像数据的科研价值。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fqupath_qupath_f96aca4a.jpg","QuPath","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fqupath_8fd8a83f.png","Open source software for bioimage analysis",null,"https:\u002F\u002Fqupath.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fqupath",[79,83,87,90,94,97],{"name":80,"color":81,"percentage":82},"Java","#b07219",99.5,{"name":84,"color":85,"percentage":86},"CSS","#663399",0.2,{"name":88,"color":89,"percentage":86},"Assembly","#6E4C13",{"name":91,"color":92,"percentage":93},"ImageJ Macro","#99AAFF",0.1,{"name":95,"color":96,"percentage":93},"Groovy","#4298b8",{"name":98,"color":99,"percentage":100},"Shell","#89e051",0,1332,338,"2026-04-07T09:41:51","GPL-3.0","未说明",{"notes":107,"python":105,"dependencies":108},"README 中未提供具体的运行环境需求（如操作系统、GPU、内存、Python 版本等）。QuPath 是一款基于 Java 的生物图像分析软件，通常通过预编译的安装包运行，支持脚本扩展。详细构建和运行指南需参考其官方文档链接。",[109],"ImageJ (可选集成)",[14,15],[112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"bioimage-informatics","image-processing","digital-pathology","pathology","machine-learning","cell-segmentation","whole-slide-imaging","bioimage-analysis","cell-analysis","imagej","opencv","groovy","histology","javafx","tissue-microarray-analysis","computational-pathology","2026-03-27T02:49:30.150509","2026-04-08T17:04:50.726670",[131,136,141,146,151,156],{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},24856,"移动了 .qpdata 文件或图像后，如何修复丢失的文件路径？","在 QuPath v0.2.0-m4 及更高版本中，项目结构已更新。如果移动了文件或图像导致路径丢失，可以通过内置功能修复：\n1. 打开项目时若提示\"Set path to missing file\"，尝试使用\"Repair projects by finding missing\u002Fmoved images\"功能。\n2. 具体操作指南可参考官方文档：https:\u002F\u002Fpetebankhead.github.io\u002Fqupath\u002F2019\u002F08\u002F20\u002Ffourth-milestone.html#repair-projects-by-finding-missingmoved-images\n3. 避免手动编辑 .qpdata 文件中的路径，这通常无效且可能导致额外文件（如 data.qpdata）被错误创建。","https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F266",{"id":137,"question_zh":138,"answer_zh":139,"source_url":140},24857,"为什么将注释（Annotations）转换为检测对象（Detections）后，左侧面板显示的计数少了一个？","这是预期行为。QuPath 的注释标签页（Annotation TAB）仅统计直接子对象（direct children），即位于注释下一层级的对象。\n1. 当你在一个注释内部创建检测对象时，该检测对象成为其子对象并被正确计数。\n2. 如果你看到计数\"少一\"，通常是因为统计逻辑排除了某些嵌套层级或子细胞检测，以防止重复计数导致数据混乱。\n3. 如果不需要细胞边界测量，可以在检测时将\"cell expansion\"参数设为 0，仅创建细胞核检测器以避免混淆。","https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F259",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},24858,"在 Linux (Arch\u002FUbuntu) 上构建 QuPath 时遇到测试失败或无法运行，如何解决？","这个问题通常是因为使用了 OpenJ9 JVM 而不是 Hotspot JVM。QuPath 主要针对 Hotspot 进行测试。\n解决方案：\n1. 卸载当前的 OpenJ9 JDK，安装 AdoptOpenJDK 的 Hotspot 版本。\n2. 在 Ubuntu 上的安装命令如下：\n   wget -qO - https:\u002F\u002Fadoptopenjdk.jfrog.io\u002Fadoptopenjdk\u002Fapi\u002Fgpg\u002Fkey\u002Fpublic | sudo apt-key add -\n   sudo add-apt-repository --yes https:\u002F\u002Fadoptopenjdk.jfrog.io\u002Fadoptopenjdk\u002Fdeb\u002F\n   sudo apt install adoptopenjdk-14-hotspot\n3. 设置环境变量：export JAVA_HOME=\u002Fusr\u002Flib\u002Fjvm\u002Fadoptopenjdk-14-hotspot-amd64\u002F (建议添加到 ~\u002F.bashrc)\n4. 验证 Java 版本，确保显示为\"Hotspot\"而非\"OpenJ9\"。","https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F484",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},24859,"如何在触摸屏上使用触控笔进行标记而不触发意外的缩放操作？","默认情况下，触摸屏的上下滑动会被识别为缩放操作，这会干扰使用触控笔进行标记。\n1. 该问题已在后续版本中得到修复或改善。\n2. 临时解决方法：在使用移动工具时，可能会遇到轻微的不规则移动，建议在使用其他工具时按住空格键进行平移，而不是直接使用移动工具拖动。\n3. 确保升级到最新的里程碑版本（milestone version），开发者已确认此问题可通过更新解决。","https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F188",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},24860,"在 M1 Mac 上训练像素分类器时出现\"Physical memory usage is too high\"错误，但实际内存并未用完，怎么办？","这是一个已知问题，特别是在 M1 MacBook Pro 上，与 javacpp 库对物理内存的检测机制有关，并非真实内存不足。\n1. 错误信息通常显示：`java.lang.OutOfMemoryError: Physical memory usage is too high`。\n2. 这是由于底层库（javacpp）在 Apple Silicon 架构上报告内存使用情况不准确导致的。\n3. 建议尝试增加 QuPath 的最大堆内存设置（例如在启动脚本中调整 -Xmx 参数）。\n4. 关注官方后续更新，该问题涉及到底层依赖库的修复（参考 javacpp issue #468 和 #516）。","https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F856",{"id":157,"question_zh":158,"answer_zh":159,"source_url":140},24861,"如何将手动绘制的注释区域批量转换为特定类别的检测对象？","可以使用 Groovy 脚本将选定的注释转换为检测对象。以下是一个示例脚本：\n1. 选择符合条件的注释对象（例如面积小于 4000 且未分类的）。\n2. 运行以下代码：\n   import qupath.lib.objects.PathTileObject\n   import qupath.lib.roi.RectangleROI\n   import qupath.lib.scripting.QP\n\n   selectObjects { p -> p.getPathClass() == null && p.isAnnotation() && p.getROI().getArea() \u003C 4000 }\n   annotations = getSelectedObjects()\n   def classification = getPathClass('NAME') \u002F\u002F 替换为你想要的类别名称\n   def detections = annotations.collect {\n       new qupath.lib.objects.PathDetectionObject(it.getROI(), classification)\n   }\n   removeObjects(annotations, true)\n   addObjects(detections)\n   fireHierarchyUpdate()\n3. 注意：转换后，原注释将被删除，新生成的检测对象将继承其 ROI 形状和指定类别。",[161,166,171,176,181,186,191,196,201,206,211,216,221,226,231,236,241,246,251,256],{"id":162,"version":163,"summary_zh":164,"released_at":165},154345,"v0.5.0-rc1","## QuPath v0.5.0-rc1 is now available!\r\n\r\nThis is a **release candidate**, available for testing before the final v0.5.0 release.\r\n\r\nThis is a **major update** compared to v0.4.4. It is recommended not to mix projects between v0.4 and v0.5.\r\n\r\nTo see what it includes, check out the **[changelog here](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)**.\r\n\r\n> #### Important - v0.5.0-rc1 is not a final version!\r\n>  It's available for early feedback and the [QuPath workshop in San Diego, October 2023](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fupcoming-qupath-training-course-october-9-11-san-diego\u002F83751).\r\n> The full v0.5.0 release is expected to follow within a few weeks.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-v0.5.0-rc1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc1\u002FQuPath-v0.5.0-rc1-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-v0.5.0-rc1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc1\u002FQuPath-v0.5.0-rc1-Windows.zip) - unzip it and double-click QuPath-v0.5.0-rc1.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-v0.5.0-rc1-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc1\u002FQuPath-v0.5.0-rc1-Mac-x64.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-v0.5.0-rc1-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc1\u002FQuPath-v0.5.0-rc1-Mac-arm64.pkg) - for Macs using Apple Silicon. This runs faster, but lacks support for some file formats through Bio-Formats (particularly .czi with jpeg-xr compression).\r\n     * To install: right-click and choose *Open* to install.\r\n* For **Linux**\r\n  * [`QuPath-v0.5.0-rc1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc1\u002FQuPath-v0.5.0-rc1-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable.","2023-10-06T15:51:02",{"id":167,"version":168,"summary_zh":169,"released_at":170},154334,"v0.7.0","## 我们很高兴地宣布 QuPath v0.7.0 发布！\n\n* 更多详情，请查看 [变更日志](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)，或下方自动生成的更详细的变更列表。\n* 如有任何问题或讨论，请使用 [Scientific Community Image Forum](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)。\n* 如需提交 bug 报告，请按照 [GitHub issues](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 上的模板进行。\n\n\u003Cdetails>\n\u003Csummary>自动生成的变更日志\u003C\u002Fsummary>\n\n* 从 v0.7.0-SNAPSHOT 开始，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1949 中提出\n* 添加地图图钉到图标工厂，由 @alanocallaghan 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1939 中完成\n* 确保工具栏按钮高度标准化，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1950 中实现\n* 当 OpenCV 本地库不可用时进行恢复，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1951 中完成\n* 避免网格视图中的空工具提示，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1952 中修复\n* 不再打开服务器后立即关闭，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1959 中实现\n* 依赖项和变更日志更新，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1962 中完成\n* 修复没有主选区的变换标注，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1965 中修复\n* 修复 RGB 通道查看器的默认设置，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1966 中完成\n* 将扩展管理器更新至 1.0.2，由 @Rylern 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1968 中完成\n* 将 moveToTrash 方法设为公共方法并改进文档，由 @Rylern 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1969 中完成\n* 修复 n 可能为 NULL 的测试，由 @zindy 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1967 中完成\n* 从 TIFF 写入器的公共函数中移除 FormatException 异常，由 @Rylern 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1971 中完成\n* 以多种方式同步迷你\u002F通道查看器与主查看器，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1970 中实现\n* 改进点工具和多点工具之间的切换，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1972 中完成\n* 记录导入对象错误，由 @Rylern 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1977 中完成\n* 更新至 pom-scijava 42，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1979 中完成\n* 修复 GeometryTools.union 对于非多边形几何体的问题，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1980 中完成\n* 修复 SubtractOffsetAndScaleNormalizer，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1981 中完成\n* 改进直方图级别选择的显示，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1982 中完成\n* 更新至 DJL 0.34.0，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1975 中完成\n* 修复论坛链接，由 @petebankhead 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1984 中完成\n* 添加 Gradle 更新操作，由 @alanocallaghan 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1944 中完成\n* 为 Gradle 更新操作添加写权限，由 @alanocallaghan 在 https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1985 中完成\n* 为 up 添加 PR 权限","2026-03-02T15:07:30",{"id":172,"version":173,"summary_zh":174,"released_at":175},154335,"v0.7.0-rc1","**我们很高兴地宣布 QuPath v0.7.0 的首个（希望也是唯一一个）候选版本！**\n\n这是一个用于测试的预览版本。如果未发现重大问题，v0.7.0 将很快发布。\n\n更多详细信息请参阅 [CHANGELOG](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)。\n\n如果您试用后发现问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.7.0-rc1 用于重要工作，并确保备份您使用它打开的所有项目。\n > 不建议在同一项目中切换使用 v0.6.x 和 v0.7.0-rc1。\n\n## 应下载的内容\n**请参阅[安装说明](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html)——其中解释了当安全设置阻止 QuPath 安装时应如何操作！**\n\n* 对于 **Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.7.0-rc1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.7.0-rc1\u002FQuPath-v0.7.0-rc1-Windows.msi) —— 如果您希望使用标准的 Windows（本地）安装程序；\n  * [`QuPath-v0.7.0-rc1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.7.0-rc1\u002FQuPath-v0.7.0-rc1-Windows.zip) —— 解压后双击 QuPath-v0.7.0-rc1.exe 即可运行，无需进一步安装。\n* 对于 **Mac**（两种选项，取决于处理器）：\n  * [`QuPath-v0.7.0-rc1-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.7.0-rc1\u002FQuPath-v0.7.0-rc1-Mac-arm64.pkg) —— 适用于搭载 Apple Silicon 芯片的 Mac。此版本运行速度更快，推荐大多数用户使用，但对少数文件格式的支持有所欠缺，尤其是采用 jpeg-xr 压缩的 .czi 文件和 .ndpis 文件。\n  * [`QuPath-v0.7.0-rc1-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.7.0-rc1\u002FQuPath-v0.7.0-rc1-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac。\n* 对于 **Linux**：\n  * [`QuPath-v0.7.0-rc1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.7.0-rc1\u002FQuPath-v0.7.0-rc1-Linux.tar.xz) —— 使用 `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` 命令使启动脚本可执行。","2026-02-17T15:45:15",{"id":177,"version":178,"summary_zh":179,"released_at":180},154336,"v0.6.0","**我们很高兴地宣布，QuPath v0.6.0 现已发布！**\n\n* 更多详情，请参阅 [image.sc 上的发行说明](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fqupath-v0-6-0-now-available\u002F114104)。\n* 如有任何问题或讨论，请使用 [Scientific Community Image 论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)。\n* 如需提交 bug 报告，请按照 [GitHub issues](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 中的模板进行。\n\n## 应下载的内容\n更多详细信息请参阅 [安装说明](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html)。\n\n* **Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.6.0-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0\u002FQuPath-v0.6.0-Windows.msi) —— 如果您希望使用标准的 Windows 本地安装程序。\n  * [`QuPath-v0.6.0-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0\u002FQuPath-v0.6.0-Windows.zip) —— 解压后双击 `QuPath-v0.6.0.exe` 即可运行，无需进一步安装。\n* **Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.6.0-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0\u002FQuPath-v0.6.0-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon 芯片（如 M1\u002FM2\u002FM3\u002FM4 等）的 Mac。\n  * [`QuPath-v0.6.0-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0\u002FQuPath-v0.6.0-Mac-arm64.pkg) —— 仅适用于使用 Apple Silicon 芯片的 Mac。\n    * arm64 版本运行速度更快，推荐大多数 Mac 用户使用，但通过 Bio-Formats 支持的文件格式较少（尤其是采用 jpeg-xr 压缩的 .czi 文件）。\n* **Linux**：\n  * [`QuPath-v0.6.0-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0\u002FQuPath-v0.6.0-Linux.tar.xz)","2025-06-27T11:26:08",{"id":182,"version":183,"summary_zh":184,"released_at":185},154337,"v0.6.0-rc5","**我们很高兴地宣布 QuPath v0.6.0 的第五个候选版本！**\n\n这是一个用于测试的预览版本。\n\n我们认为这很可能是 v0.6.0 正式发布前的最后一个预览版本……当然，我们也曾判断失误过。\n\n如果您试用后发现任何问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.6.0-rc5 用于重要工作，并确保对使用该版本打开的项目进行备份。\n> 不建议在同一项目中频繁切换 v0.5.x 和 v0.6.0-rcx 版本。\n\n## 亮点\n有关之前各候选版本的信息，请参阅 [v0.6.0-rc1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc1)、[v0.6.0-rc2](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc2)、[v0.6.0-rc3](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc3) 和 [v0.6.0-rc4](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc4)。\n\nv0.6.0-rc5 的主要改进包括：\n* 修复了一个可能导致 QuPath 占用过多内存的 bug（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1864）\n* 更新工具栏，使重要按钮在较小屏幕上也能显示（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1841）\n* 在通过命令行运行时，使用 `-s` 参数保存项目（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1859）\n* 添加停靠按钮，以保持项目描述窗口始终打开（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1856）\n* 在 `RenderedImageServer` 中使用查看器伽玛校正（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1849）\n* 添加对 OME-XML 形状的支持（https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1848）\n\n> **注意：针对 macOS Sequoia 用户**\n> macOS Sequoia 的最新安全更新可能会阻止 QuPath 安装程序运行。\n> 您可以通过 *苹果菜单 > 系统设置 > 隐私与安全性* 来解决此问题——详情请参阅 [apple.com 上的相关页面](https:\u002F\u002Fsupport.apple.com\u002Fen-gb\u002Fguide\u002Fmac-help\u002Fmchleab3a043\u002F15.0\u002Fmac\u002F15.0)。\n> （我们理解这可能有些麻烦，但目前我们尚无办法将 QuPath 打包为“已签名”应用以规避这一限制）\n\n## 下载内容\n更多详细信息请参阅 [安装说明](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html)。\n\n* 对于 **Windows**（两种方式，功能相同）：\n  * [`QuPath-v0.6.0-rc5-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc5\u002FQuPath-v0.6.0-rc5-Windows.msi) —— 如果您希望使用标准的 Windows 本地安装程序\n  * [`QuPath-v0.6.0-rc5-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc5\u002FQuPath-v0.6.0-rc5-Windows.zip) —— 解压后双击 `QuPath-v0.6.0-rc5.exe` 即可运行，无需进一步安装\n* 对于 **Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.6.0-rc5-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc5\u002FQuPath-v0.6.0-rc5-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac\n  * [`QuPath-v0.6.0-rc5-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fr","2025-05-11T12:44:56",{"id":187,"version":188,"summary_zh":189,"released_at":190},154338,"v0.6.0-rc4","**我们很高兴地宣布 QuPath v0.6.0 的第四版候选发布！**\n\n这是一个用于测试的预览版本……虽然有些延迟，但基于反馈和测试，相比 rc3 有了*大量*改进。\n\n如果您试用后发现任何问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.6.0-rc4 用于重要工作，并确保备份您使用它打开的任何项目。\n> 不建议在同一项目中切换使用 v0.5.x 和 v0.6.0-rcx 版本。  \n\n## 亮点\n有关之前各候选版本的信息，请参阅 [v0.6.0-rc1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc1)、[v0.6.0-rc2](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc2) 和 [v0.6.0-rc3](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc3)。\n\nv0.6.0-rc4 的主要变化包括：\n* 全新的**扩展管理器**\n  * 可通过 *Extensions > Manage extensions* 访问\n  * 使用此工具可**安装 InstanSeg、P4J 及训练扩展**（这些不再像之前的候选版本那样捆绑在一起）\n  * 这将使我们能够更快速地修复扩展中的 bug 并添加新功能，同时更好地管理兼容性\n  * 扩展开发者可以管理自己的[扩展目录](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fextension-catalog-model)\n* 更多选项可用于[管理分类并显示\u002F隐藏对象](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1752)\n* 新增用于[导航多维图像](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1802)的控件，以及计算[Z 投影叠加层](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1810)的功能\n* 现在可以将**QuPath 与 Fiji 一起构建**（[pull 请求 #1728](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1728)）\n* 复杂 ROI 的**创建与渲染速度大幅提升**（[pull 请求 #1777](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fpull\u002F1777)）\n* 诸多其他 bug 修复及性能优化\n\n> **注意：适用于 macOS Sequoia 用户**\n> macOS Sequoia 中最近的安全更改可能会阻止 QuPath 安装程序运行。\n> 您可以通过 *Apple 菜单 > 系统设置 > 隐私与安全性* 来解决此问题——详情请参阅 [apple.com 上的此页面](https:\u002F\u002Fsupport.apple.com\u002Fen-gb\u002Fguide\u002Fmac-help\u002Fmchleab3a043\u002F15.0\u002Fmac\u002F15.0)。\n> （我们知道这很麻烦，但我们目前尚无办法将 QuPath 打造成“已签名”应用以避免此类问题）\n\n## 下载内容\n* 对于 **Windows**（两种选择，功能相同）：\n  * [`QuPath-v0.6.0-rc4-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc4\u002FQuPath-v0.6.0-rc4-Windows.msi) —— 如果您希望使用标准的 Windows 本地安装程序\n  * [`QuPath-v0.6.0-rc4-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc4\u002FQuPath-v0.6.0-rc4-Windows.zip) —— 解压后双击 QuPath-v0.6.0-rc4.exe 即可，无需进一步安装\n* 对于 **Mac**（两种选择，取决于处理器）：\n  * [`QuPath-v0.6.0-rc4-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc4\u002FQuPath-v","2025-04-11T16:27:49",{"id":192,"version":193,"summary_zh":194,"released_at":195},154339,"v0.6.0-rc3","**我们很高兴地宣布 QuPath v0.6.0 的第三个候选版本！**\n\n这是一个用于测试的预览版本，发布于 [I2K 研讨会](https:\u002F\u002Fwww.i2kconference.org) 期间，以及 [虚拟 I2K 活动（10月28日至30日）](https:\u002F\u002Fwww.i2kconference.org\u002Fvirtual) 之前。\n\n我们计划在 2024 年 10 月至 11 月左右发布最终版本。\n\n如果您试用后发现任何问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.6.0-rc3 用于重要工作，并确保备份您使用它打开的任何项目。\n> 不建议在同一项目中切换使用 v0.5.x 和 v0.6.0-rcx 版本。\n\n## 亮点\n有关前两个候选版本的信息，请参阅 [v0.6.0-rc1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc1) 和 [v0.6.0-rc2](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc2)。\n\nv0.6.0-rc3 的主要更改包括：\n* 全新的 *ImageJ 脚本运行器*（取代旧的宏运行器）\n* 新增扩展，添加了 *帮助 → QuPath 导览* 命令，以帮助用户熟悉用户界面\n* 新增扩展，支持 [Py4J](https:\u002F\u002Fwww.py4j.org)\n\n> **注意：文档及其他扩展（例如 StarDist 扩展）尚未更新以兼容此候选版本。**\n> 我们计划在最终版本中进行更新。\n\n> **注2：针对 macOS Sequoia 用户**\n> macOS Sequoia 中最近的安全性更改可能会阻止 QuPath 的安装程序运行。\n> 这可以通过 *苹果菜单 > 系统设置 > 隐私与安全性* 来解决——详情请参阅 [apple.com 上的此页面](https:\u002F\u002Fsupport.apple.com\u002Fen-gb\u002Fguide\u002Fmac-help\u002Fmchleab3a043\u002F15.0\u002Fmac\u002F15.0)。\n> （我们知道这很麻烦，但目前我们尚无办法将 QuPath 打造成“已签名”应用以避免此问题）\n\n## 下载内容\n* 对于 **Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.6.0-rc3-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc3\u002FQuPath-v0.6.0-rc3-Windows.msi) —— 如果您希望使用标准的 Windows 本地安装程序\n  * [`QuPath-v0.6.0-rc3-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc3\u002FQuPath-v0.6.0-rc3-Windows.zip) —— 解压后双击 QuPath-v0.6.0-rc3.exe 即可使用，无需进一步安装\n* 对于 **Mac**（两种选项，取决于处理器）：\n  * [`QuPath-v0.6.0-rc3-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc3\u002FQuPath-v0.6.0-rc3-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac\n  * [`QuPath-v0.6.0-rc3-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc3\u002FQuPath-v0.6.0-rc3-Mac-arm64.pkg) —— 仅适用于使用 Apple Silicon 的 Mac。此版本运行速度更快，推荐大多数用户使用，但其通过 Bio-Formats 支持的文件格式较少（尤其是采用 jpeg-xr 压缩的 .czi 文件）。\n     * 安装方法：右键单击并选择 *打开* 即可安装。\n* 对于 **Linux**\n  * [`QuP","2024-10-23T09:51:34",{"id":197,"version":198,"summary_zh":199,"released_at":200},154340,"v0.6.0-rc2","**我们很高兴地宣布 QuPath v0.6.0 的第二个候选版本！**\n\n这是一个用于测试的预览版本。我们计划在 2024 年 10 月发布最终正式版。\n\n如果您试用后发现任何问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.6.0-rc2 用于重要工作，并确保备份您使用它打开的所有项目。\n> 不建议在同一项目中频繁切换 v0.5.x 和 v0.6.0-rcx 版本。\n\n## 亮点\n有关第一个候选版本的信息，请参阅 [v0.6.0-rc1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.6.0-rc1)。\n\nv0.6.0-rc2 的主要改进包括：\n* OME-Zarr 支持大幅增强\n  * 新增 *文件 → 导出图像... → OME-Zarr* 命令\n  * 可通过命令行工具 `convert-ome` 将图像转换为 ome.zarr 格式\n  * 支持读取和写入元数据，例如像素尺寸和通道颜色\n  * 支持读取远程 OME-Zarr 图像\n* [**QuPath InstanSeg 扩展**](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-instanseg) 在检测大型且复杂的感兴趣区域中的细胞时速度更快\n* QuPath 现已采用 DeepJavaLibrary v0.30.0，该版本默认支持 PyTorch 2.4.0\n  * 如果您希望在 Windows 或 Linux 上启用 [CUDA 加速](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fdeep\u002Fgpu.html)，这一点尤为重要——您需要 CUDA 12.4；或者使用 CUDA 12.1 并配合启动脚本来请求 PyTorch 2.3.1 版本\n\n> **注意：文档及其他扩展（例如 StarDist）尚未更新以兼容此候选版本。**\n> 我们计划在最终正式版发布时进行相应更新。\n\n> **补充说明：针对 macOS Sequoia 用户**\n> macOS Sequoia 的最新安全设置可能会阻止 QuPath 安装程序运行。\n> 您可以通过 *苹果菜单 > 系统设置 > 隐私与安全性* 来解决此问题——详情请参阅 [apple.com 官方支持页面](https:\u002F\u002Fsupport.apple.com\u002Fen-gb\u002Fguide\u002Fmac-help\u002Fmchleab3a043\u002F15.0\u002Fmac\u002F15.0)。\n> （我们理解这可能有些麻烦，但目前我们尚无能力将 QuPath 打造成“已签名”应用以避免此类限制）\n\n## 下载内容\n* 对于 **Windows**（两种方式功能相同）：\n  * [`QuPath-v0.6.0-rc2-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc2\u002FQuPath-v0.6.0-rc2-Windows.msi) —— 如果您希望使用标准的本地 Windows 安装程序\n  * [`QuPath-v0.6.0-rc2-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc2\u002FQuPath-v0.6.0-rc2-Windows.zip) —— 解压后双击 `QuPath-v0.6.0-rc2.exe` 即可运行，无需额外安装\n* 对于 **Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.6.0-rc2-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc2\u002FQuPath-v0.6.0-rc2-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac\n  *  [`QuPath-v0.6.0-rc2-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002F","2024-09-20T16:04:50",{"id":202,"version":203,"summary_zh":204,"released_at":205},154341,"v0.6.0-rc1","**我们很高兴地宣布 QuPath v0.6.0 的首个候选版本！**\n\n这是一个用于测试的预览版本。我们计划在 2024 年 10 月发布最终正式版。\n\n如果您试用后发现任何问题，请通过 [GitHub](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues) 或 [用户论坛](https:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) 告知我们。\n\n> **可能存在 bug！**\n > 请勿将 v0.6.0-rc1 用于重要工作，并确保备份您使用它打开的所有项目。\n> 不建议在同一项目中切换使用 v0.5.x 和 v0.6.0-rc1。\n\n## 亮点\n[变更日志](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) 中列出了许多大小不一的更改。\n\n但也许最大的亮点是，该候选版本首次向社区推出了 [**QuPath InstanSeg 扩展**](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-instanseg)。\n\n[InstanSeg](https:\u002F\u002Fgithub.com\u002Finstanseg\u002Finstanseg) 是一种基于深度学习的新方法，用于细胞核和细胞分割，旨在快速、准确且易于使用。\n\n我们正在编写更多文档，但目前您可以访问 [扩展仓库以获取更多信息](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-instanseg)，并查看两篇介绍该方法的预印本——分别针对 [明场图像](https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2408.15954) 和 [多通道图像](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2024.09.04.611150)。\n\n> **注意：其他扩展（例如 StarDist）尚未更新以兼容此候选版本。**\n> 我们计划在最终正式版中对其进行更新。\n\n## 下载内容\n* 对于 **Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.6.0-rc1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc1\u002FQuPath-v0.6.0-rc1-Windows.msi) —— 如果您希望使用标准的 Windows 本地安装程序。\n  * [`QuPath-v0.6.0-rc1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc1\u002FQuPath-v0.6.0-rc1-Windows.zip) —— 解压后双击 QuPath-v0.6.0-rc1.exe 即可运行（无需进一步安装）。\n* 对于 **Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.6.0-rc1-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc1\u002FQuPath-v0.6.0-rc1-Mac-x64.pkg) —— 适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac。\n  * [`QuPath-v0.6.0-rc1-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc1\u002FQuPath-v0.6.0-rc1-Mac-arm64.pkg) —— 仅适用于使用 Apple Silicon 的 Mac。此版本运行速度更快，推荐大多数用户使用，但对少数通过 Bio-Formats 支持的文件格式（尤其是采用 jpeg-xr 压缩的 .czi 文件）支持有限。\n     * 安装方法：右键单击并选择“打开”即可安装。\n* 对于 **Linux**：\n  * [`QuPath-v0.6.0-rc1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.6.0-rc1\u002FQuPath-v0.6.0-rc1-Linux.tar.xz) —— 使用 `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` 命令使启动脚本可执行。","2024-09-11T18:24:51",{"id":207,"version":208,"summary_zh":209,"released_at":210},154342,"v0.5.1","## QuPath v0.5.1现已发布！\n\n这是一个**次要更新**，旨在与[v0.5.0](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.5.0)完全兼容，同时修复了一些错误。\n\n要了解具体内容，请查看**[此处的变更日志](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)**。\n\n## 如何提供帮助\n\n**请务必在使用该软件的任何出版物中引用QuPath论文**！  \n\n**有关QuPath的问题与讨论，请使用[科学社区图像论坛](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)！**\n\n## 可下载内容\n* 对于**Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.5.1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.1\u002FQuPath-v0.5.1-Windows.msi) - 如果您希望使用标准的Windows本地安装程序；\n  * [`QuPath-v0.5.1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.1\u002FQuPath-v0.5.1-Windows.zip) - 解压后双击QuPath-v0.5.1.exe即可运行（无需进一步安装）。\n* 对于**Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.5.1-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.1\u002FQuPath-v0.5.1-Mac-x64.pkg) - 适用于配备Intel处理器或Apple Silicon（M1\u002FM2）的Mac；\n  * [`QuPath-v0.5.1-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.1\u002FQuPath-v0.5.1-Mac-arm64.pkg) - 仅适用于使用Apple Silicon的Mac。此版本运行速度更快，但通过Bio-Formats对少数文件格式的支持有所欠缺（尤其是采用jpeg-xr压缩的.czi文件）。\n     * 安装方法：右键单击并选择“打开”以进行安装。\n* 对于**Linux**：\n  * [`QuPath-v0.5.1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.1\u002FQuPath-v0.5.1-Linux.tar.xz) - 使用`chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath`命令将启动脚本设置为可执行文件。","2024-03-04T14:49:45",{"id":212,"version":213,"summary_zh":214,"released_at":215},154343,"v0.5.0","## QuPath v0.5.0现已发布！\n\n这是一次**重大更新**，包含多项改进、新功能和错误修复。建议您**不要**在 v0.5.0 与旧版本之间混合使用项目。\n\n如需了解具体内容，请查看[此处的变更日志](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)。\n\n## 如何提供帮助\n\n**请务必在使用该软件的任何出版物中引用 QuPath 论文**！[引用指南](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)\n\n**有关 QuPath 的问题与讨论，请使用[科学社区图像论坛](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath)！**\n\n## 下载内容\n* **Windows**（两种选项，功能相同）：\n  * [`QuPath-v0.5.0-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0\u002FQuPath-v0.5.0-Windows.msi)：如果您希望使用标准的 Windows 本地安装程序。\n  * [`QuPath-v0.5.0-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0\u002FQuPath-v0.5.0-Windows.zip)：解压后双击 `QuPath-v0.5.0.exe` 即可运行，无需进一步安装。\n* **Mac**（两种选项，取决于处理器类型）：\n  * [`QuPath-v0.5.0-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0\u002FQuPath-v0.5.0-Mac-x64.pkg)：适用于配备 Intel 处理器或 Apple Silicon（M1\u002FM2）的 Mac。\n  * [`QuPath-v0.5.0-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0\u002FQuPath-v0.5.0-Mac-arm64.pkg)：仅适用于使用 Apple Silicon 的 Mac。此版本运行速度更快，但通过 Bio-Formats 对少数文件格式的支持有所欠缺（尤其是采用 jpeg-xr 压缩的 .czi 文件）。\n    * 安装方法：右键单击并选择“打开”即可安装。\n* **Linux**：\n  * [`QuPath-v0.5.0-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0\u002FQuPath-v0.5.0-Linux.tar.xz)：请使用 `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` 命令将启动脚本设置为可执行。","2023-12-01T16:35:54",{"id":217,"version":218,"summary_zh":219,"released_at":220},154344,"v0.5.0-rc2","## QuPath v0.5.0-rc2 is now available!\r\n\r\nThis is a **release candidate**, available for testing before the final v0.5.0 release.\r\n\r\nThis is a **major update** compared to v0.4.4. It is recommended that you do **not** mix projects between v0.4 and v0.5.\r\n\r\nTo see what it includes, check out the **[changelog here](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md)**.\r\n\r\n> #### Important - v0.5.0-rc2 is not a final version!\r\n>  It's available for early feedback, to help us find & fix any bugs before the final release.\r\n> Release candidates are **not** intended for final analysis.\r\n> The full v0.5.0 release is expected to follow within a few weeks.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-v0.5.0-rc2-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc2\u002FQuPath-v0.5.0-rc2-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-v0.5.0-rc2-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc2\u002FQuPath-v0.5.0-rc2-Windows.zip) - unzip it and double-click QuPath-v0.5.0-rc2.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-v0.5.0-rc2-Mac-x64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc2\u002FQuPath-v0.5.0-rc2-Mac-x64.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-v0.5.0-rc2-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc2\u002FQuPath-v0.5.0-rc2-Mac-arm64.pkg) - for Macs using Apple Silicon. This runs faster, but lacks support for a small number of file formats through Bio-Formats (particularly .czi with jpeg-xr compression).\r\n     * To install: right-click and choose *Open* to install.\r\n* For **Linux**\r\n  * [`QuPath-v0.5.0-rc2-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.5.0-rc2\u002FQuPath-v0.5.0-rc2-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable.","2023-10-26T18:56:02",{"id":222,"version":223,"summary_zh":224,"released_at":225},154346,"v0.4.4","## QuPath v0.4.4 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with earlier v0.4.x versions while fixing one bug.\r\n\r\nTo date, the bug has only been reported to affect a small number of people using the [*QuPath ABBA extension*](https:\u002F\u002Fgithub.com\u002FBIOP\u002Fqupath-extension-abba). But because it *could* impact analysis results in rare circumstances, it is recommended that users of QuPath v0.4.0 - v0.4.3 update to v0.4.4.\r\n\r\nThere is a full description at https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F1306\r\n\r\n## QuPath Course in San Diego - and v0.5.0\r\n\r\nWe're happy to announced there will be a **[QuPath Training Course in San Diego from October 9-11, 2023](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fupcoming-qupath-training-course-october-9-11-san-diego\u002F83751).**\r\n\r\nThis will be followed by the **[Quantitative Bioimaging Society's workshop on Muliplex Image Analysis](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fupcoming-qbi-workshop-of-multiplex-image-analysis-october-12-13-san-diego\u002F83753).**\r\n\r\nWe are planning to release **QuPath v0.5.0** shortly before these events, as the next major release of the software.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.4.4-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.4\u002FQuPath-0.4.4-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.4.4-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.4\u002FQuPath-0.4.4-Windows.zip) - unzip it and double-click QuPath-0.4.4.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-0.4.4-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.4\u002FQuPath-0.4.4-Mac.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-0.4.4-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.4\u002FQuPath-0.4.4-Mac-arm64.pkg) - for Macs using Apple Silicon only (experimental). This runs much faster, but you'll need to [install OpenSlide separately](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002F0.4\u002Fdocs\u002Fintro\u002Finstallation.html#apple-silicon).\r\n     * To install: right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.4.4-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.4\u002FQuPath-0.4.4-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.","2023-09-01T16:23:07",{"id":227,"version":228,"summary_zh":229,"released_at":230},154347,"v0.4.3","## QuPath v0.4.3 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with earlier v0.4.x versions while fixing bugs.\r\n\r\nIt also updates to [Bio-Formats 6.12.0](https:\u002F\u002Fforum.image.sc\u002Ft\u002Frelease-of-bio-formats-6-12-0\u002F77261). This adds some additional fixes related to reading\u002Fwriting images, and makes it possible for QuPath to support memoization again.\r\n\r\nFor more details about how memoization can speed up reading some images, and how to turn on the feature, see https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F1236\r\n\r\n* See the [v0.4.0 announcement](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fqupath-v0-4-0-now-available\u002F74887) for more details of the latest features and improvements\r\n* See [the changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for a record of what extra fixes are in v0.4.3\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.4.3-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.3\u002FQuPath-0.4.3-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.4.3-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.3\u002FQuPath-0.4.3-Windows.zip) - unzip it and double-click QuPath-0.4.3.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-0.4.3-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.3\u002FQuPath-0.4.3-Mac.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-0.4.3-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.3\u002FQuPath-0.4.3-Mac-arm64.pkg) - for Macs using Apple Silicon only (experimental). This runs much faster, but you'll need to [install OpenSlide separately](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002F0.4\u002Fdocs\u002Fintro\u002Finstallation.html#apple-silicon).\r\n     * To install: right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.4.3-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.3\u002FQuPath-0.4.3-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.","2023-02-23T10:47:05",{"id":232,"version":233,"summary_zh":234,"released_at":235},154348,"v0.4.2","## QuPath v0.4.2 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with [v0.4.0](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.4.0) and [v0.4.1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.4.1) while fixing bugs.\r\n\r\n* See the [v0.4.0 announcement](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fqupath-v0-4-0-now-available\u002F74887) for more details of the latest features and improvements\r\n* See [the changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for a record of what extra fixes are in v0.4.2\r\n\r\nThe main fix is in v0.4.2 to to point annotations, which couldn't have classifications assigned in v0.4.1 without throwing an error.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.4.2-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.2\u002FQuPath-0.4.2-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.4.2-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.2\u002FQuPath-0.4.2-Windows.zip) - unzip it and double-click QuPath-0.4.2.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-0.4.2-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.2\u002FQuPath-0.4.2-Mac.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-0.4.2-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.2\u002FQuPath-0.4.2-Mac-arm64.pkg) - for Macs using Apple Silicon only (experimental). This runs much faster, but you'll need to [install OpenSlide separately](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002F0.4\u002Fdocs\u002Fintro\u002Finstallation.html#apple-silicon).\r\n     * To install: right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.4.2-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.2\u002FQuPath-0.4.2-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.","2023-01-19T18:18:03",{"id":237,"version":238,"summary_zh":239,"released_at":240},154349,"v0.4.1","## QuPath v0.4.1 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with [v0.4.0](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.4.0) while fixing bugs.\r\n\r\n* See the [v0.4.0 announcement](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fqupath-v0-4-0-now-available\u002F74887) for more details of the latest features and improvements.\r\n* See [the changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for a record of what extra fixes are in v0.4.1\r\n\r\nThe most annoying bug by far is the one that broke the update message - so QuPath v0.4.0 sadly can't tell anyone that v0.4.1 is available. So ideally everyone on v0.4.0 would switch to v0.4.1 and we can put that little issue behind us.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.4.1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.1\u002FQuPath-0.4.1-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.4.1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.1\u002FQuPath-0.4.1-Windows.zip) - unzip it and double-click QuPath-0.4.1.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-0.4.1-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.1\u002FQuPath-0.4.1-Mac.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-0.4.1-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.1\u002FQuPath-0.4.1-Mac-arm64.pkg) - for Macs using Apple Silicon only (experimental). This runs much faster, but you'll need to [install OpenSlide separately](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002F0.4\u002Fdocs\u002Fintro\u002Finstallation.html#apple-silicon).\r\n     * To install: right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.4.1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.1\u002FQuPath-0.4.1-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.","2022-12-20T19:14:28",{"id":242,"version":243,"summary_zh":244,"released_at":245},154350,"v0.4.0","## QuPath v0.4.0 is now available!\r\n\r\nThis is a **major update**, that introduces several new features and includes many other improvements.\r\n\r\nNo time to describe it all yet - I'll post more info in a day or two to describe what's new, along with releasing some new extensions.\r\n\r\nIn the meantime, [here's a tweet](https:\u002F\u002Ftwitter.com\u002Fpetebankhead\u002Fstatus\u002F1599131758284271618?s=20&t=AMVdh_9w1KBoBvg_scdppg) to get started - or check out the [Changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for more details.\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.4.0-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.0\u002FQuPath-0.4.0-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.4.0-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.0\u002FQuPath-0.4.0-Windows.zip) - unzip it and double-click QuPath-0.4.0.exe (no further installation needed)\r\n* For **Mac** (two options, depending upon processor)\r\n  * [`QuPath-0.4.0-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.0\u002FQuPath-0.4.0-Mac.pkg) - for Macs with Intel Processors *or* Apple Silicon (M1\u002FM2)\r\n  *  [`QuPath-0.4.0-Mac-arm64.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.0\u002FQuPath-0.4.0-Mac-arm64.pkg) - for Macs using Apple Silicon only (experimental). This runs much faster, but you'll need to [install OpenSlide separately](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002F0.4\u002Fdocs\u002Fintro\u002Finstallation.html#apple-silicon).\r\n     * To install: right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.4.0-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.4.0\u002FQuPath-0.4.0-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.\r\n\r\n## Known issues\r\n\r\n* Security settings might want to thwart installing\u002Frunning QuPath. See [here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html) for information how to run it anyway.\r\n* On macOS, the installer may choose the generic name 'QuPath' for the installation. You may want to rename it to support different installations more easily (otherwise installations with the same name may be overwritten).","2022-12-02T18:48:09",{"id":247,"version":248,"summary_zh":249,"released_at":250},154351,"v0.3.2","## QuPath v0.3.2 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with [v0.3.0](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.3.0) and [v0.3.1](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.3.1) while fixing bugs and improving performance.\r\n\r\nThe biggest change since v0.3.1 is to revert back to Bio-Formats 6.7.0, to resolve problems that were reported with some SVS files [here](https:\u002F\u002Fforum.image.sc\u002Ft\u002Fproblem-about-opening-some-svs-slides-in-qupath-v0-3-1-bio-formats-6-8-0\u002F61404).\r\n\r\nSeveral smaller fixes are enhancements are included and the update is **recommended for all users of v0.3.0 and v0.3.1**.\r\nSee the [Changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for more details.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.3.2-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.2\u002FQuPath-0.3.2-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.3.2-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.2\u002FQuPath-0.3.2-Windows.zip) - unzip it and double-click QuPath-0.3.2.exe (no further installation needed)\r\n* For **Mac**\r\n  * [`QuPath-0.3.2-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.2\u002FQuPath-0.3.2-Mac.pkg) - right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.3.2-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.2\u002FQuPath-0.3.2-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.\r\n\r\n## Known issues\r\n\r\n* Security settings might want to thwart installing\u002Frunning QuPath. See [here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html) for information how to run it anyway.\r\n* On macOS, the installer may choose the generic name 'QuPath' for the installation. You may want to rename it to support different installations more easily (otherwise installations with the same name may be overwritten).","2022-01-17T11:30:59",{"id":252,"version":253,"summary_zh":254,"released_at":255},154352,"v0.3.1","## QuPath v0.3.1 is now available!\r\n\r\nThis is a *minor* update, that aims to be compatible with [v0.3.0](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Ftag\u002Fv0.3.0) while fixing bugs and improving performance.\r\n\r\nThis includes an important fix for https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F836 which could cause problems when running commands on images with different channel names within the same QuPath session. It also includes significant improvements to the memory use and performance when reading large images with ImageJ or Bio-Formats under some circumstances, along with many smaller fixes.\r\n\r\nSee the [Changelog](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for more details.\r\n\r\n## How to help\r\n\r\n**Please remember to [cite the QuPath paper in any publications that use the software](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Fstable\u002Fdocs\u002Fintro\u002Fciting.html)!**\r\n\r\n**Please use the [Scientific Community Image Forum](http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath) for QuPath questions & discussions!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.3.1-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.1\u002FQuPath-0.3.1-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.3.1-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.1\u002FQuPath-0.3.1-Windows.zip) - unzip it and double-click QuPath-0.3.1.exe (no further installation needed)\r\n* For **Mac**\r\n  * [`QuPath-0.3.1-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.1\u002FQuPath-0.3.1-Mac.pkg) - right-click and choose *Open* to install. Note that this will try to install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.3.1-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.1\u002FQuPath-0.3.1-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make the launcher executable. If you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355), you might find the alternative bash script `\u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath.sh` better for launching the software.\r\n\r\n## Known issues\r\n\r\n* Security settings might want to thwart installing\u002Frunning QuPath. See [here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html) for information how to run it anyway.\r\n* On macOS, the installer may choose the generic name 'QuPath' for the installation. You may want to rename it to support different installations more easily (otherwise installations with the same name may be overwritten).","2021-12-23T20:37:26",{"id":257,"version":258,"summary_zh":259,"released_at":260},154353,"v0.3.0","## QuPath v0.3.0 is now available!\r\n\r\nThis is a major update, that introduces several new features along with many bug fixes and performance improvements.\r\n\r\n> **Important!** It is *not* recommended to switch between using QuPath v0.2.x and v0.3.x in the same project.\r\n> Please back up any older projects if you want to try them with v0.3.0.\r\n\r\n## Release highlights\r\n* **New 'Create density map' command** to visualize hotspots & generate annotations based on object densities\r\n* **_Many_ code fixes** & **major performance improvements** - especially for pixel classification\r\n* **Revised code structure**, with non-core features now separated out as optional **extensions**, including:\r\n  * **OMERO**\r\n    * https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-omero\r\n    * **Major update!** New support for browsing multiple OMERO servers, importing images & exchanging annotations\r\n  * **StarDist**\r\n    * https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-stardist\r\n    * **Major update!** No longer any need to build QuPath from source\r\n  * **TensorFlow**\r\n    * https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-tensorflow\r\n    * No longer needed to run StarDist (but gives an alternative option)\r\n  * **Interactive image alignment**\r\n    * https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-align\r\n    * Calculate a rigid transform between two images\r\n  * **JPen**\r\n    * https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath-extension-jpen\r\n    * Adds support for (some) graphics tablets\r\n* **Rotate images** in the viewer 360°\r\n* **Easier OpenCV scripting** with many new methods in `OpenCVTools`\r\n* **New build scripts**, now with **continuous integration** via GitHub Actions\r\n* **Groundwork for new features** coming soon...\r\n\r\nThe major revision of the code structure and creation of extensions is designed to make QuPath more developer-friendly, maintainable and adaptable in the future.\r\n\r\nCheck out [the CHANGELOG](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fblob\u002Fmain\u002FCHANGELOG.md) for a longer list.\r\n\r\nThe **latest documentation** is at https:\u002F\u002Fqupath.readthedocs.io\u002F\r\n\r\nThe **new javadoc (API documentation)** is at https:\u002F\u002Fqupath.github.io\u002Fjavadoc\u002Fdocs\u002F\r\n\r\nPlease **report any problems** at http:\u002F\u002Fforum.image.sc\u002Ftag\u002Fqupath - thanks!\r\n\r\n## How to help\r\n\r\n**Please let us know what you think (and want) by completing the [QuPath User Survey](https:\u002F\u002Fedinburgh.onlinesurveys.ac.uk\u002Fqupath-user-survey-2021) - it closes on 16 September!**\r\n\r\n## What to download\r\n* For **Windows** (two options, functionally the same)\r\n  * [`QuPath-0.3.0-Windows.msi`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.0\u002FQuPath-0.3.0-Windows.msi) - if you want a standard Windows (local) installer\r\n  * [`QuPath-0.3.0-Windows.zip`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.0\u002FQuPath-0.3.0-Windows.zip) - unzip it and double-click QuPath-0.3.0.exe (no further installation needed)\r\n* For **Mac**\r\n  * [`QuPath-0.3.0-Mac.pkg`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.0\u002FQuPath-0.3.0-Mac.pkg) - right-click and choose *Open* to install. Note that this will install to *\u002FApplications\u002FQuPath.app* - if you have an older version at that location that you want to keep, you should rename it before installation.\r\n* For **Linux**\r\n  * [`QuPath-0.3.0-Linux.tar.xz`](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Freleases\u002Fdownload\u002Fv0.3.0\u002FQuPath-0.3.0-Linux.tar.xz) - use `chmod u+x \u002Fpath\u002Fto\u002FQuPath\u002Fbin\u002FQuPath` to make executable - and the same for `QuPath.sh` if you suffer [pixman problems](https:\u002F\u002Fgithub.com\u002Fqupath\u002Fqupath\u002Fissues\u002F355) - then launching from a command line with `QuPath.sh` may help.\r\n\r\n## Known issues\r\n\r\n* Security settings might want to thwart installing\u002Frunning QuPath. See [here](https:\u002F\u002Fqupath.readthedocs.io\u002Fen\u002Flatest\u002Fdocs\u002Fintro\u002Finstallation.html) for information how to run it anyway.\r\n* On macOS, the installer may choose the generic name 'QuPath' for the installation. You may want to rename it to support different installations more easily (otherwise installations with the same name may be overwritten).","2021-09-02T19:00:18"]