📄 中文摘要
在医疗保健中，隐私不仅仅是一项功能，而是一项基本权利。处理敏感的医疗数据如皮肤图像时，用户常常不愿意将照片上传到云端。Derm-Scan 是一款完全在设备上进行皮肤病变分类和分割的移动应用程序。通过利用隐私保护的人工智能、Flutter 和专业的 Med-SAM（医学分割任意模型），可以在不将任何生物识别数据传出用户智能手机的情况下实现高精度筛查。本教程将探讨如何使用 PyTorch Mobile 将高性能计算机视觉模型与跨平台移动开发相结合。
Derm-Scan：构建一个保护隐私的皮肤病变分类器，使用 Med-SAM 和 Flutter
📄 English Summary
Derm-Scan: Building a Privacy-Preserving Skin Lesion Classifier with Med-SAM and Flutter
Privacy in healthcare is a fundamental right, especially when handling sensitive medical data such as skin images. Users are often reluctant to upload photos to the cloud. Derm-Scan is a mobile application that performs skin lesion classification and segmentation entirely on-device. By leveraging privacy-preserving AI, Flutter, and the specialized Medical Segment Anything Model (Med-SAM), high-accuracy screening can be achieved without any biometric data leaving the user's smartphone. This tutorial explores how to bridge high-performance computer vision models with cross-platform mobile development using PyTorch Mobile.