Codes and pretrained weights for winning submission of 2021 Brain Tumor Segmentation (BraTS) Challenge

Last update: Dec 28, 2022

Related tags

Overview

Winning submission to the 2021 Brain Tumor Segmentation Challenge

This repo contains the codes and pretrained weights for the winning submission to the 2021 Brain Tumor Segmentation Challenge by KAIST MRI Lab Team. The code was developed on top of the excellent nnUNet library. Please refer to the original repo for the installation, usages, and common Q&A

Inference with docker image

You can run the inference with the docker image that we submitted to the competition by following these instructions:

Install docker-ce and nvidia-container-toolkit (instruction)
Pull the docker image from here
Gather the data you want to infer on in one folder. The naming of the file should follow the convention: BraTS2021_ID_<contrast>.nii.gz with contrast being flair, t1, t1ce, t2
Run the command: docker run -it --rm --gpus device=0 --name nnunet -v "/your/input/folder/":"/input" -v "/your/output/folder/":"/output" rixez/brats21nnunet , replacing /your/input/folder and /your/output/folder with the absolute paths to your input and output folder.
You can find the prediction results in the specified output folder.

The docker container was built and verified with Pytorch 1.9.1, Cuda 11.4 and a RTX3090. It takes about 4GB of GPU memory for inference with the docker container. The provided docker image might not work with different hardwares or cuda version. In that case, you can try running the models from the command line.

Inference with command line

If you want to run the model without docker, first, download the models from here. Extract the files and put the models in the RESULTS_FOLDER that you set up with nnUNet. Then run the following commands:

nnUNet_predict -i <input_folder> -o <output_folder1> -t <TASK_ID> -m 3d_fullres -tr nnUNetTrainerV2BraTSRegions_DA4_BN_BD --save_npz
nnUNet_predict -i <input_folder> -o <output_folder2> -t <TASK_ID> -m 3d_fullres -tr nnUNetTrainerV2BraTSRegions_DA4_BN_BD_largeUnet_Groupnorm --save_npz
nnUNet_ensemble -f <output_folder1> <output_folder2> -o <final_output_folder>

You need to specify the options in <>. TASK_ID is 500 for the pretrained weights but you can change it depending on the task ID that you set with your installation of nnUNet. To get the results that we submitted, you need to additionally apply post-processing threshold for of 200 and convert the label back to BraTS convention. You can check this file as an example.

Training with the model

You can train the models that we used for the competition using the command:

nnUNet_train 3d_fullres nnUNetTrainerV2BraTSRegions_DA4_BN_BD <TASK_ID> <FOLD> --npz # BL config
nnUNet_train 3d_fullres nnUNetTrainerV2BraTSRegions_DA4_BN_BD_largeUnet_Groupnorm <TASK_ID> <FOLD> --npz # BL + L + GN config

Comments

axial_attention RuntimeError

Hello, your work is so great!! When using nnUNetTrainerV2BraTSRegions_DA4_BN_BD_normalUnet_axialattention to train on my dataset, I met the problem :

  File "/home3/anaconda3/envs/nnunet_modify/lib/python3.8/site-packages/axial_attention/axial_attention.py", line 119, in forward
    x = x + getattr(self, f'param_{i}')
RuntimeError: The size of tensor a (10) must match the size of tensor b (4) at non-singleton dimension 3

I check the part of axial_attention.py, and check the x and getattr(self, f'param_{i}') size,

    def forward(self, x):
        for i in range(self.num_axials):
            print(f"size error: x: {x.size()},add: {getattr(self, f'param_{i}').size()}")
            x = x + getattr(self, f'param_{i}')
        
        return x

print size:

>> size error::x: torch.Size([2, 320, 4, 10, 10]),add: torch.Size([1, 320, 4, 1, 1])
>> size error::x: torch.Size([2, 320, 4, 10, 10]),add: torch.Size([1, 320, 1, 4, 1])

but I don.t know why this problem happend, could you please help me ? Thx

opened by Jy-stdio 14

CUDA out of memory.

Hi : Thank you for sharing, your work is amazing. I am running nnUNet_train 3d_fullres nnUNetTrainerV2BraTSRegions_DA4_BN_BD_largeUnet_Groupnorm Task500_Colon 0 --npz There was a problem RuntimeError: CUDA out of memory. Tried to allocate 1.17 GiB (GPU 0; 11.91 GiB total capacity; 10.92 GiB already allocated; 18.88 MiB free; 11.04 GiB reserved in total by PyTorch)

I want to know how much GPU is needed for training. I only have 12G. If 12G is not enough, can I train in other ways? ?

Best wishes

opened by wxr521314 9
How to calculate a single sample segmentation metrics?

Hi, I can use your docker image to generate the segmentation result for a single sample. May I ask that how can I calculate the segmentation metrics like Dice score and HD95 score of ET, TC and WT regions for this sample suppose the ground-truth segmentation mask exist? Thanks!

opened by panovr 3
The number of patch

Hi friends， Here I go again. I have some questions for you, My data is in 3D. I want to know how many patches my data is divided into. My patch_size is 24x320x320. Can I understand that 24 represents the number of data layers? However, some of my data is less than 24 layers. How did he input it to the network? Best wish!

opened by wxr521314 3
Training my own dataset with axial attention network

I would like to know which parameters in the axial attention network are to be modified if for custom datasets? Since your dataset is (128, 128, 128) and my own dataset is (24, 64, 80), I don't know which parts of the network need to be modified in order to satisfy this condition. Thanks!

opened by ysl2 2
Providing Dockerfile

@rixez Do you have the Dockerfile that you used to create the container on Dockerhub? I would like to recreate it to use a different CUDA version to work on some of our older cards.

opened by blakedewey 2
[ENH] Paper Implementation using Tensorflow/Keras

Hi @rixez

I would like to implement this paper using tensorflow and keras library. I have a problem with axial attention section and i can not understand it in details. Could you please give me some hints and/or resources to find out how to implement the axial attention?

Regards

opened by EverLookNeverSee 2
About dataset_conversion

When I run the task500_brats_2021.py file, I get an error at line 799：”TypeError: my_evaluate_folder() missing 1 required positional argument: 'gt_folder'” What parameters should be written here?

opened by Zhuofei-Wang 1
Stop training to test

hi When I was training, I found that after 300 epoch, my dice was basically unchanged, and loss also converged. I wanted to stop training for testing, how should I modify it? Except for setting the training epoch to 300.Is there another way? For example, can I use the results in the middle of training to predict? How do I change the code?

opened by wxr521314 1
output channel

hi ， Why is the output of a network two-channel? What do two channels represent? Is the first channel the background and the second channel the foreground ?

opened by wxr521314 1
Bump joblib from 1.0.1 to 1.2.0
Bumps joblib from 1.0.1 to 1.2.0.

Changelog

Sourced from joblib's changelog.

Release 1.2.0

Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported. joblib/joblib#1327

Make sure that joblib works even when multiprocessing is not available, for instance with Pyodide joblib/joblib#1256

Avoid unnecessary warnings when workers and main process delete the temporary memmap folder contents concurrently. joblib/joblib#1263

Fix memory alignment bug for pickles containing numpy arrays. This is especially important when loading the pickle with mmap_mode != None as the resulting numpy.memmap object would not be able to correct the misalignment without performing a memory copy. This bug would cause invalid computation and segmentation faults with native code that would directly access the underlying data buffer of a numpy array, for instance C/C++/Cython code compiled with older GCC versions or some old OpenBLAS written in platform specific assembly. joblib/joblib#1254

Vendor cloudpickle 2.2.0 which adds support for PyPy 3.8+.

Vendor loky 3.3.0 which fixes several bugs including:

robustly forcibly terminating worker processes in case of a crash (joblib/joblib#1269);

avoiding leaking worker processes in case of nested loky parallel calls;

reliability spawn the correct number of reusable workers.

Release 1.1.0

Fix byte order inconsistency issue during deserialization using joblib.load in cross-endian environment: the numpy arrays are now always loaded to use the system byte order, independently of the byte order of the system that serialized the pickle. joblib/joblib#1181

Fix joblib.Memory bug with the ignore parameter when the cached function is a decorated function.

... (truncated)

Commits

5991350 Release 1.2.0

3fa2188 MAINT cleanup numpy warnings related to np.matrix in tests (#1340)

cea26ff CI test the future loky-3.3.0 branch (#1338)

8aca6f4 MAINT: remove pytest.warns(None) warnings in pytest 7 (#1264)

067ed4f XFAIL test_child_raises_parent_exits_cleanly with multiprocessing (#1339)

ac4ebd5 MAINT add back pytest warnings plugin (#1337)

a23427d Test child raises parent exits cleanly more reliable on macos (#1335)

ac09691 [MAINT] various test updates (#1334)

4a314b1 Vendor loky 3.2.0 (#1333)

bdf47e9 Make test_parallel_with_interactively_defined_functions_default_backend timeo...

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

dependencies
opened by dependabot[bot] 0

Owner

GitHub

Cancer-and-Tumor-Detection-Using-Inception-model - In this repo i am gonna show you how i did cancer/tumor detection in lungs using deep neural networks, specifically here the Inception model by google.

Cancer-and-Tumor-Detection-Using-Inception-model In this repo i am gonna show you how i did cancer/tumor detection in lungs using deep neural networks

1 Jan 1, 2022

This repo provides the official code for TransBTS: Multimodal Brain Tumor Segmentation Using Transformer (https://arxiv.org/pdf/2103.04430.pdf).

TransBTS: Multimodal Brain Tumor Segmentation Using Transformer This repo is the official implementation for TransBTS: Multimodal Brain Tumor Segmenta

247 Dec 28, 2022

Self-supervised Multi-modal Hybrid Fusion Network for Brain Tumor Segmentation

JBHI-Pytorch This repository contains a reference implementation of the algorithms described in our paper "Self-supervised Multi-modal Hybrid Fusion N

5 Dec 13, 2021

TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

A Brain Tumor Detection and Classification Model built using RESNET50 architecture. The model is also deployed as a web application using Flask framework.

0 Aug 17, 2021

VGG16 model-based classification project about brain tumor detection.

Brain-Tumor-Classification-with-MRI VGG16 model-based classification project about brain tumor detection. First, you can check what people are doing o

2 Mar 21, 2022

The sixth place winning solution (6/220) in 2021 Gaofen Challenge.

SwinTransformer + OBBDet The sixth place winning solution (6/220) in the track of Fine-grained Object Recognition in High-Resolution Optical Images, 2

46 Dec 2, 2022

An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

Bottom-Up and Top-Down Attention for Visual Question Answering An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge. The

731 Jan 3, 2023

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Use this instead: https://github.com/facebookresearch/maskrcnn-benchmark A Pytorch Implementation of Detectron Example output of e2e_mask_rcnn-R-101-F

2.8k Dec 29, 2022

🔪 Elimination based Lightweight Neural Net with Pretrained Weights

ELimNet ELimNet: Eliminating Layers in a Neural Network Pretrained with Large Dataset for Downstream Task Removed top layers from pretrained Efficient

4 Jul 12, 2022

Submission to Twitter's algorithmic bias bounty challenge

Twitter Ethics Challenge: Pixel Perfect Submission to Twitter's algorithmic bias bounty challenge, by Travis Hoppe (@metasemantic). Abstract We build

4 Aug 19, 2022

Code for A Volumetric Transformer for Accurate 3D Tumor Segmentation

VT-UNet This repo contains the supported pytorch code and configuration files to reproduce 3D medical image segmentaion results of VT-UNet. Environmen

7 Dec 3, 2021

Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.

Music Source Separation with Channel-wise Subband Phase Aware ResUnet (CWS-PResUNet) Introduction This repo contains the pretrained Music Source Separ

100 Dec 25, 2022

This is the winning solution of the Endocv-2021 grand challange.

Endocv2021-winner [Paper] This is the winning solution of the Endocv-2021 grand challange. Dependencies pytorch # tested with 1.7 and 1.8 torchvision

14 Dec 3, 2022

PyTorch Implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedding (ORAL, MICCAIW 2021)

Small Lesion Segmentation in Brain MRIs with Subpixel Embedding PyTorch implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedd

22 Oct 21, 2022

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

wsss-analysis The code of: A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains, arXiv pre-print 2019 paper.

48 Dec 18, 2022

Winning solution of the Indoor Location & Navigation Kaggle competition

This repository contains the code to generate the winning solution of the Kaggle competition on indoor location and navigation organized by Microsoft

62 Dec 28, 2022

U-Net implementation in PyTorch for FLAIR abnormality segmentation in brain MRI

U-Net for brain segmentation U-Net implementation in PyTorch for FLAIR abnormality segmentation in brain MRI based on a deep learning segmentation alg

562 Jan 2, 2023

ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

48 Dec 30, 2022

Source code for Zalo AI 2021 submission

zalo_ltr_2021 Source code for Zalo AI 2021 submission Solution: Pipeline We use the pipepline in the picture below: Our pipeline is combination of BM2

128 Dec 27, 2022