OrthoRay – 一款由外科医生使用Rust/wgpu编写的原生轻量级DICOM查看器
嗨,HN,
我是一名骨科医生,同时也是一名自学的开发者。我创建了 OrthoRay,因为我对现有医疗影像软件的滞后感到沮丧。大多数现有解决方案要么是臃肿的 Electron 应用,要么是昂贵的云订阅。
我想要一种即时、以本地为优先、注重隐私的解决方案。因此,我花了很多晚上的时间学习 Rust,并大量利用 AI 编码助手来应对陡峭的学习曲线和借用检查器。这个项目证明了领域专家如何在 AI 支持下构建高性能的本地软件。
我使用 Tauri 和 wgpu 进行渲染构建了这个查看器。
主要特点:
- 原生性能:能够瞬间打开超过 500MB 的 MRI 系列(不使用 Electron,也没有网页包装)。
- GPU 加速:为 3D 体积渲染和 MPR 定制的 wgpu 管道。
- BoneFidelity:我专门开发的一种高保真骨骼可视化算法。
- 隐私:以本地为优先,离线运行,无需云上传。
目前该软件作为一个免费的业余项目在 Microsoft Store 上提供。
免责声明:该软件仅供学术/研究使用,并未获得 FDA/CE 认证用于临床诊断。
我正在评估开源许可选项,以使其成为一个社区工具。非常希望能听到您对渲染性能的反馈。
链接:https://orthoarchives.com/en/orthoray
查看原文
Hi HN,<p>I am an orthopedic surgeon and a self-taught developer. I built OrthoRay because I was frustrated with the lag in standard medical imaging software. Most existing solutions were either bloated Electron apps or expensive cloud subscriptions.<p>I wanted something instant, local-first, and privacy-focused. So, I spent my nights learning Rust, heavily utilizing AI coding assistants to navigate the steep learning curve and the borrow checker. This project is a testament to how domain experts can build performant native software with AI support.<p>I built this viewer using Tauri and wgpu for rendering.<p>Key Features:<p>Native Performance: Opens 500MB+ MRI series instantly (No Electron, no web wrappers).<p>GPU-Accelerated: Custom wgpu pipeline for 3D Volume Rendering and MPR.<p>BoneFidelity: A custom algorithm I developed specifically for high-fidelity bone visualization.<p>Privacy: Local-first, runs offline, no cloud uploads.<p>It is currently available on the Microsoft Store as a free hobby project.<p>Disclaimer: This is intended for academic/research use and is NOT FDA/CE certified for clinical diagnosis.<p>I am evaluating open-source licensing options to make this a community tool. I’d love your feedback on the rendering performance.<p>Link: https://orthoarchives.com/en/orthoray