Giter Site home page Giter Site logo

szupzp / clinical-grade-computational-pathology-using-weakly-supervised-deep-learning-on-whole-slide-images Goto Github PK

View Code? Open in Web Editor NEW

This project forked from tankzhoufirst/clinical-grade-computational-pathology-using-weakly-supervised-deep-learning-on-whole-slide-images

0.0 0.0 0.0 989 KB

首个临床级别的 AI 系统可用源码

Python 100.00%

clinical-grade-computational-pathology-using-weakly-supervised-deep-learning-on-whole-slide-images's Introduction

全球首个临床级病理 AI 系统源码及复现。


个人新增部分

  1. 数据集下载。自己申请的,可直接使用,50G 左右。下载地址,密码:yetk
  2. 数据集准备。官方接口需要指定格式,参考 code/README.md。这里我自己写了一个脚本,见 code/dataPrepare_for_CNN.pycode/dataPrepare_for_Rnn.py,改一下相关路径就好。
  3. 训练及测试。将官方代码改成单机数据并行训练,加速训练,单 GPU 也无需更改代码。具体运行命令,参考 code/README.md
  4. 具体代码运行流程
    1. 运行:code/dataPrepare_for_CNN.py,生成 MIL 所需的数据
    2. 运行 code/MIL_train.pycode/MIL_test.py(很慢)
    3. 运行:code/dataPrepare_for_Rnn.py,生成 RNN 所需的数据(较慢)
    4. 运行 code/RNN_train.pycode/RNN_test.py

原理图贴一张

结果

MIL

Pred \ target 1 0
1 11 1
0 2 31

ACC = 42 / 45 = 93.3% FNR = 2 / 13 = 15.4% FPR = 1 / 32 = 3.1%

RNN

Pred \ target 1 0
1 12 1
0 1 31

ACC = 43 / 45 = 95.6% FNR = 1 / 13 = 7.7% FPR = 1 / 32 = 3.1%

clinical-grade-computational-pathology-using-weakly-supervised-deep-learning-on-whole-slide-images's People

Contributors

tankzhoufirst avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.