Home

Welcome to the wiki

State of The Art

1. Read papers, understand, take notes
2. Go to the code - play a bit
3. re-read papers
4. Implement some code - train and predict
5. Compare results - conclusions
6. Deliver

Papers and other info sources:

-Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection. And their impressive github repository torch framed

-Learning to Recognize Chest-Xray Images Fasterand More Efficiently Based on Multi-KernelDepthwise Convolution

-Chexpert

-Chester

-classification of chest x-ray images using convolutional neuralnetworks pre-trained for ImageNet and data augmentation

-Detecting Pneumonia in Chest X-Rays with Custom Vision and PyTorch

-End-to-End Deep Diagnosis of X-ray Images

• Detecting and Localizing Pneumonia from Chest X-Ray Scans with PyTorch

Code and Repositories in Pytorch:

• CheXNet-with-localization - Pytorch

• CheXNet - Pytorch

• Chest-XRay-Vision with TRansfer Learning - Pytorch

• pneumonia-pytorch-localization

• Chest xrays with Transfer Learning - Keras

• Pneumonia-Detection-from-Chest-X-Ray-Images-with-Deep-Learning - KERAS

• Xvision - TF

• X-ray-classification - TF

• Torchio: Tools for medical image processing in deep learning and PyTorch

• X-ray images analysis on pneumonia with deep learning using PyTorch

• Detecting and Localizing Pneumonia from Chest X-Ray Scans with PyTorch

  • CheXpert - paper: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison - 2019
  • CheXpert webpage
  • Pytorch Pneumonia localization
  • Chest X-ray Disease Diagnosis with Deep Convolutional Neural Networks

• COVID-19 Detection in X-ray Images with Pytorch

• Covid19-detection - pytorch

Other Datasets:

• Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE
• Dati COVID-19 Italia