RSNA Intracranial Hemorrhage Detection with python

Last update: Nov 30, 2022

Overview

RSNA Intracranial Hemorrhage Detection

This is the source code for the first place solution to the RSNA2019 Intracranial Hemorrhage Detection Challenge.

Solution write up: Link.

Solutuoin Overview

Dependencies

opencv-python==3.4.2
scikit-image==0.14.0
scikit-learn==0.19.1
scipy==1.1.0
torch==1.1.0
torchvision==0.2.1

CODE

2DNet
3DNet
SequenceModel

2D CNN Classifier

Pretrained models

seresnext101_256*256 [seresnext101]
densenet169_256*256 [densenet169]
densenet121_512*512 [densenet121]

Preprocessing

Prepare csv file:

download data.zip: https://drive.google.com/open?id=1buISR_b3HQDU4KeNc_DmvKTYJ1gvj5-3

convert dcm to png

python3 prepare_data.py -dcm_path stage_1_train_images -png_path train_png
python3 prepare_data.py -dcm_path stage_1_test_images -png_path train_png
python3 prepare_data.py -dcm_path stage_2_test_images -png_path test_png

train

python3 train_model.py -backbone DenseNet121_change_avg -img_size 256 -tbs 256 -vbs 128 -save_path DenseNet121_change_avg_256
python3 train_model.py -backbone DenseNet169_change_avg -img_size 256 -tbs 256 -vbs 128 -save_path DenseNet169_change_avg_256
python3 train_model.py -backbone se_resnext101_32x4d -img_size 256 -tbs 80 -vbs 40 -save_path se_resnext101_32x4d_256

predict

python3 predict.py -backbone DenseNet121_change_avg -img_size 256 -tbs 4 -vbs 4 -spth DenseNet121_change_avg_256
python3 predict.py -backbone DenseNet169_change_avg -img_size 256 -tbs 4 -vbs 4 -spth DenseNet169_change_avg_256
python3 predict.py -backbone se_resnext101_32x4d -img_size 256 -tbs 4 -vbs 4 -spth se_resnext101_32x4d_256

After single models training, the oof files will be saved in ./SingleModelOutput(three folders for three pipelines).

After training the sequence model, the final submission will be ./FinalSubmission/final_version/submission_tta.csv

Sequence Models

Sequence Model 1

Sequence Model 2

Path Setup

Set data path in ./setting.py

download

download [csv.zip]

download [feature samples]

Sequence Model Training

CUDA_VISIBLE_DEVICES=0 python main.py

The final submissions are in the folder ../FinalSubmission/version2/submission_tta.csv

Final Submission

Private Leaderboard:

0.04383

Reference

If you find our work useful in your research or if you use parts of this code please consider citing our paper:

  title={A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans},
  author={Wang, Xiyue and Shen, Tao and Yang, Sen and Lan, Jun and Xu, Yanming and Wang, Minghui and Zhang, Jing and Han, Xiao},
  journal={NeuroImage: Clinical},
  volume={32},
  pages={102785},
  year={2021},
  publisher={Elsevier}
}

TODO

Pre-trained models
2DCNN + SeqModel end-to-end training
3DCNN training

RSNA Intracranial Hemorrhage Detection with python

Related tags

Overview

RSNA Intracranial Hemorrhage Detection

Solutuoin Overview

Dependencies

CODE

2D CNN Classifier

Pretrained models

Preprocessing

Sequence Models

Sequence Model 1

Sequence Model 2

Path Setup

download

Sequence Model Training

Final Submission

Private Leaderboard:

Reference

TODO

Owner

Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, arXiv 2021

Pytorch Lightning Distributed Accelerators using Ray

SwinIR: Image Restoration Using Swin Transformer

YOLOX + ROS(1, 2) object detection package

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"

Official code for: A Probabilistic Hard Attention Model For Sequentially Observed Scenes

Training PSPNet in Tensorflow. Reproduce the performance from the paper.

Code for "OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021)"

Canonical Capsules: Unsupervised Capsules in Canonical Pose (NeurIPS 2021)

Unofficial implementation (replicates paper results!) of MINER: Multiscale Implicit Neural Representations in pytorch-lightning

AI pipelines for Nvidia Jetson Platform

Brax is a differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators

Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

Dark Finix: All in one hacking framework with almost 100 tools

Unofficial & improved implementation of NeRF--: Neural Radiance Fields Without Known Camera Parameters

[WACV21] Code for our paper: Samuel, Atzmon and Chechik, "From Generalized zero-shot learning to long-tail with class descriptors"

The toolkit to generate auto labeled datasets

🔥 Cannlytics-powered artificial intelligence 🤖

Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer.