Semi-supervised-learning-for-medical-image-segmentation.

Recently, semi-supervised image segmentation has become a hot topic in medical image computing, unfortunately, there are only a few open-source codes and datasets, since the privacy policy and others. For easy evaluation and fair comparison, we are trying to build a semi-supervised medical image segmentation benchmark to boost the semi-supervised learning research in the medical image computing community. If you are interested, you can push your implementations or ideas to this repository at any time.

This project was originally developed for our previous works (DTC and URPC), if you find it's useful for your research, please cite the followings:

  @InProceedings{luo2021urpc,
  author={Luo, Xiangde and Liao, Wenjun and Chen, Jieneng and Song, Tao and Chen, Yinan and Zhang, Shichuan and Chen, Nianyong and Wang, Guotai and Zhang, Shaoting},
  title={Efficient Semi-supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency},
  booktitle={Medical Image Computing and Computer Assisted Intervention -- MICCAI 2021},
  year={2021},
  pages={318--329}
  }

  @article{luo2021semi,
    title={Semi-supervised Medical Image Segmentation through Dual-task Consistency},
    author={Luo, Xiangde and Chen, Jieneng and Song, Tao and  Wang, Guotai},
    journal={AAAI Conference on Artificial Intelligence},
    year={2021},
    pages={8801-8809}
  }
  @misc{ssl4mis2020,
    title={{SSL4MIS}},
    author={Luo, Xiangde and Chen, Jieneng and Song, Tao and  Wang, Guotai},
    howpublished={\url{https://github.com/HiLab-git/SSL4MIS}},
    year={2020}
  }

Literature reviews of semi-supervised learning approach for medical image segmentation (SSL4MIS).

Date	The First and Last Authors	Title	Code	Reference
2021-09	K. Wang and Y. Wang	Tripled-Uncertainty Guided Mean Teacher Model for Semi-supervised Medical Image Segmentation	Code	MICCAI2021
2021-09	H. Huang and R. Tong	3D Graph-S2Net: Shape-Aware Self-ensembling Network for Semi-supervised Segmentation with Bilateral Graph Convolution	None	MICCAI2021
2021-09	L. Zhu and B. Ooi	Semi-Supervised Unpaired Multi-Modal Learning for Label-Efficient Medical Image Segmentation	Code	MICCAI2021
2021-09	R. Zhang and G. Li	Self-supervised Correction Learning for Semi-supervised Biomedical Image Segmentation	Code	MICCAI2021
2021-09	D. Kiyasseh and A. Chen	Segmentation of Left Atrial MR Images via Self-supervised Semi-supervised Meta-learning	None	MICCAI2021
2021-09	Y. Wu and J. Cai	Enforcing Mutual Consistency of Hard Regions for Semi-supervised Medical Image Segmentation	None	Arxiv
2021-09	X. Zeng and Y. Wang	Reciprocal Learning for Semi-supervised Segmentation	Code	MICCAI2021
2021-09	G. Zhang and S. Jiang	Automatic segmentation of organs at risk and tumors in CT images of lung cancer from partially labelled datasets with a semi-supervised conditional nnU-Net	None	CMPB2021
2021-09	J. Chen and G. Yang	Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data	Code	TMI2021
2021-09	X. Hu and Y. Shi	Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation	Code	MICCAI2021
2021-09	G. Chen and J. Shi	MTANS: Multi-Scale Mean Teacher Combined Adversarial Network with Shape-Aware Embedding for Semi-Supervised Brain Lesion Segmentation	Code	NeuroImage2021
2021-08	H. Peiris and M. Harandi	Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation	Code	MICCAI2021
2021-08	J. Sun and Y. Kong	Semi-Supervised Medical Image Semantic Segmentation with Multi-scale Graph Cut Loss	None	ICIP2021
2021-08	X. Shen and J. Lu	PoissonSeg: Semi-Supervised Few-Shot Medical Image Segmentation via Poisson Learning	None	ArXiv
2021-08	C. You and J. Duncan	SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation	None	Arxiv
2021-08	C. Li and P. Heng	Self-Ensembling Co-Training Framework for Semi-supervised COVID-19 CT Segmentation	None	JBHI2021
2021-08	H. Yang and P. H. N. With	Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning	None	JBHI2021
2021-07	W. Ding and H. Hawash	RCTE: A Reliable and Consistent Temporal-ensembling Framework for Semi-supervised Segmentation of COVID-19 Lesions	None	Information Fusion2021
2021-06	X. Liu and S. A. Tsaftaris	Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation	Code	MICCAI2021
2021-06	P. Pandey and Mausam	Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation	None	MICCAI2021
2021-06	C. Li and Y. Yu	Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation	None	Arxiv
2021-05	J. Xiang and S. Zhang	Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation	None	Arxiv
2021-05	S. Li and C. Guan	Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentation	None	Arxiv
2021-05	C. You and J. Duncan	Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentation	None	Arxiv
2021-05	Z. Xie and J. Yang	Semi-Supervised Skin Lesion Segmentation with Learning Model Confidence	None	ICASSP2021
2021-04	S. Reiß and R. Stiefelhagen	Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation	None	CVPR2021
2021-04	S. Chatterjee and A. Nurnberger	DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data	Code	MIDL
2021-04	A. Meyer and M. Rak	Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of Prostate Zones and Beyond	Code	Arxiv
2021-04	Y. Li and P. Heng	Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images	None	MICCAI2021
2021-03	Y. Zhang and C. Zhang	Dual-Task Mutual Learning for Semi-Supervised Medical Image Segmentation	Code	PRCV2021
2021-03	J. Peng and C. Desrosiers	Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization	Code	MELBA
2021-03	Y. Wu and L. Zhang	Semi-supervised Left Atrium Segmentation with Mutual Consistency Training	None	MICCAI2021
2021-02	J. Peng and Y. Wang	Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models	None	Arxiv
2021-02	J. Dolz and I. B. Ayed	Teach me to segment with mixed supervision: Confident students become masters	Code	IPMI2021
2021-02	C. Cabrera and K. McGuinness	Semi-supervised Segmentation of Cardiac MRI using Image Registration	None	Under review for MIDL2021
2021-02	Y. Wang and A. Yuille	Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction	None	TMI2021
2021-02	R. Alizadehsaniand U R. Acharya	Uncertainty-Aware Semi-supervised Method using Large Unlabelled and Limited Labeled COVID-19 Data	None	Arxiv
2021-02	D. Yang and D. Xu	Federated Semi-Supervised Learning for COVID Region Segmentation in Chest CT using Multi-National Data from China, Italy, Japan	None	MedIA2021
2020-01	E. Takaya and S. Kurihara	Sequential Semi-supervised Segmentation for Serial Electron Microscopy Image with Small Number of Labels	Code	Journal of Neuroscience Methods
2021-01	Y. Zhang and Z. He	Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer	None	Arxiv
2020-12	H. Wang and D. Chen	Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation	None	Arxiv
2020-12	X. Luo and S. Zhang	Efficient Semi-supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency	Code	MICCAI2021
2020-12	M. Abdel‐Basset and M. Ryan	FSS-2019-nCov: A Deep Learning Architecture for Semi-supervised Few-Shot Segmentation of COVID-19 Infection	None	Knowledge-Based Systems2020
2020-11	N. Horlava and N. Scherf	A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data	None	Arxiv
2020-11	P. Wang and C. Desrosiers	Self-paced and self-consistent co-training for semi-supervised image segmentation	None	MedIA2021
2020-10	Y. Sun and L. Wang	Semi-supervised Transfer Learning for Infant Cerebellum Tissue Segmentation	None	MLMI2020
2020-10	L. Chen and D. Merhof	Semi-supervised Instance Segmentation with a Learned Shape Prior	Code	LABELS2020
2020-10	S. Shailja and B.S. Manjunath	Semi supervised segmentation and graph-based tracking of 3D nuclei in time-lapse microscopy	Code	Arxiv
2020-10	L. Sun and Y. Yu	A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision	None	Arxiv
2020-10	J. Ma and X. Yang	Active Contour Regularized Semi-supervised Learning for COVID-19 CT Infection Segmentation with Limited Annotations	Code	Physics in Medicine & Biology2020
2020-10	W. Hang and J. Qin	Local and Global Structure-Aware Entropy Regularized Mean Teacher Model for 3D Left Atrium Segmentation	Code	MICCAI2020
2020-10	K. Tan and J. Duncan	A Semi-supervised Joint Network for Simultaneous Left Ventricular Motion Tracking and Segmentation in 4D Echocardiography	None	MICCAI2020
2020-10	Y. Wang and Z. He	Double-Uncertainty Weighted Method for Semi-supervised Learning	None	MICCAI2020
2020-10	K. Fang and W. Li	DMNet: Difference Minimization Network for Semi-supervised Segmentation in Medical Images	None	MICCAI2020
2020-10	X. Cao and L. Cheng	Uncertainty Aware Temporal-Ensembling Model for Semi-supervised ABUS Mass Segmentation	None	TMI2020
2020-09	Z. Zhang and W. Zhang	Semi-supervised Semantic Segmentation of Organs at Risk on 3D Pelvic CT Images	None	Arxiv
2020-09	J. Wang and G. Xie	Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions	None	BMVC2020
2020-09	X. Luo and S. Zhang	Semi-supervised Medical Image Segmentation through Dual-task Consistency	Code	AAAI2021
2020-08	X. Huo and Q. Tian	ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Medical Image Segmentation	None	Arxiv
2020-08	Y. Xie and Y. Xia	Pairwise Relation Learning for Semi-supervised Gland Segmentation	None	MICCAI2020
2020-07	K. Chaitanya and E. Konukoglu	Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation	Code	Arxiv
2020-07	S. Li and X. He	Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images	Code	MICCAI2020
2020-07	Y. Li and Y. Zheng	Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation	None	MICCAI2020
2020-07	Z. Zhao and P. Heng	Learning Motion Flows for Semi-supervised Instrument Segmentation from Robotic Surgical Video	Code	MICCAI2020
2020-07	Y. Zhou and P. Heng	Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation	Code	MICCAI2020
2020-07	A. Tehrani and H. Rivaz	Semi-Supervised Training of Optical Flow Convolutional Neural Networks in Ultrasound Elastography	None	MICCAI2020
2020-07	Y. He and S. Li	Dense biased networks with deep priori anatomy and hard region adaptation: Semi-supervised learning for fine renal artery segmentation	None	MedIA2020
2020-07	J. Peng and C. Desrosiers	Mutual information deep regularization for semi-supervised segmentation	Code	MIDL2020
2020-07	Y. Xia and H. Roth	Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation	None	WACV2020,MedIA2020
2020-07	X. Li and P. Heng	Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation	Code	TNNLS2020
2020-06	F. Garcıa and S. Ourselin	Simulation of Brain Resection for Cavity Segmentation Using Self-Supervised and Semi-Supervised Learning	None	MICCAI2020
2020-06	H. Yang and P. With	Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet	None	MICCAI2020
2020-05	G. Fotedar and X. Ding	Extreme Consistency: Overcoming Annotation Scarcity and Domain Shifts	None	MICCAI2020
2020-04	C. Liu and C. Ye	Semi-Supervised Brain Lesion Segmentation Using Training Images with and Without Lesions	None	ISBI2020
2020-04	R. Li and D. Auer	A Generic Ensemble Based Deep Convolutional Neural Network for Semi-Supervised Medical Image Segmentation	Code	ISBI2020
2020-04	K. Ta and J. Duncan	A Semi-Supervised Joint Learning Approach to Left Ventricular Segmentation and Motion Tracking in Echocardiography	None	ISBI2020
2020-04	Q. Chang and D. Metaxas	Soft-Label Guided Semi-Supervised Learning for Bi-Ventricle Segmentation in Cardiac Cine MRI	None	ISBI2020
2020-04	D. Fan and L. Shao	Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images	Code	TMI2020
2019-10	L. Yu and P. Heng	Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation	Code	MICCAI2019
2019-10	G. Bortsova and M. Bruijne	Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations	None	MICCAI2019
2019-10	Y. He and S. Li	DPA-DenseBiasNet: Semi-supervised 3D Fine Renal Artery Segmentation with Dense Biased Network and Deep Priori Anatomy	None	MICCAI2019
2019-10	H. Zheng and X. Han	Semi-supervised Segmentation of Liver Using Adversarial Learning with Deep Atlas Prior	None	MICCAI2019
2019-10	P. Ganayea and H. Cattin	Removing Segmentation Inconsistencies with Semi-Supervised Non-Adjacency Constraint	Code	MedIA2019
2019-10	Y. Zhao and C. Liu	Multi-view Semi-supervised 3D Whole Brain Segmentation with a Self-ensemble Network	None	MICCAI2019
2019-10	H. Kervade and I. Ayed	Curriculum semi-supervised segmentation	None	MICCAI2019
2019-10	S. Chen and M. Bruijne	Multi-task Attention-based Semi-supervised Learning for Medical Image Segmentation	None	MICCAI2019
2019-10	Z. Xu and M. Niethammer	DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation	None	MICCAI2019
2019-10	S. Sedai and R. Garnavi	Uncertainty Guided Semi-supervised Segmentation of Retinal Layers in OCT Images	None	MICCAI2019
2019-10	G. Pombo and P. Nachev	Bayesian Volumetric Autoregressive Generative Models for Better Semisupervised Learning	Code	MICCAI2019
2019-06	W. Cui and C. Ye	Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model	None	IPMI2019
2019-06	K. Chaitanya and E. Konukoglu	Semi-supervised and Task-Driven Data Augmentation	Code	IPMI2019
2019-04	M. Jafari and P. Abolmaesumi	Semi-Supervised Learning For Cardiac Left Ventricle Segmentation Using Conditional Deep Generative Models as Prior	None	ISBI2019
2019-03	Z. Zhao and Z. Zeng	Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation	None	BHI
2019-03	J. Peng and C. Desrosiers	Deep co-training for semi-supervised image segmentation	Code	PR2020
2019-01	Y. Zhou and A. Yuille	Semi-Supervised 3D Abdominal Multi-Organ Segmentation via Deep Multi-Planar Co-Training	None	WACV2019
2018-10	P. Ganaye and H. Cattin	Semi-supervised Learning for Segmentation Under Semantic Constraint	Code	MICCAI2018
2018-10	A. Chartsias and S. Tsaftari	Factorised spatial representation learning: application in semi-supervised myocardial segmentation	None	MICCAI2018
2018-09	X. Li and P. Heng	Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model	Code	BMVC2018
2018-04	Z. Feng and D. Shen	Semi-supervised learning for pelvic MR image segmentation based on multi-task residual fully convolutional networks	None	ISBI2018
2017-09	L. Gu and S. Aiso	Semi-supervised Learning for Biomedical Image Segmentation via Forest Oriented Super Pixels(Voxels)	None	MICCAI2017
2017-09	S. Sedai and R. Garnavi	Semi-supervised Segmentation of Optic Cup in Retinal Fundus Images Using Variational Autoencoder	None	MICCAI2017
2017-09	W. Bai and D. Rueckert	Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation	None	MICCAI2017

Code for semi-supervised medical image segmentation.

Some implementations of semi-supervised learning methods can be found in this Link.

Conclusion

This repository provides daily-update literature reviews, algorithms' implementation, and some examples of using PyTorch for semi-supervised medical image segmentation. The project is under development. Currently, it supports 2D and 3D semi-supervised image segmentation and includes five widely-used algorithms' implementations.
In the next two or three months, we will provide more algorithms' implementations, examples, and pre-trained models.

Questions and Suggestions

If you have any questions or suggestions about this project, please contact me through email: [email protected] or QQ Group (Chinese):906808850.

Hello,

First of all congratulations for this amazing work. I want to ask how you handle the creation of dataloaders for labeled and unlabaled data. To the best of my understanding from reading the dataloaders in each iteration you forward pass the same amount of labaled and unlabaled data. Actually in each epoch you pass the whole labeled data and random sample equal amount of unlabaled data. I have read a couple of approaches for this. The first is to define an epoch as the passing of all unlabeled data from the network, but with this the labeled data will be passed from the network multiple times in an epoch. The second approach, as you have done, is to use a sampler to sample at each epoch equal amount of unlabeled data to match the size of the labeled data. Which of these 2 techniques would force the model to perform better? Generally , I'm a bit confused on how to construct the dataloaders of labeled and unlabeled data in a semi supervised setting. Any hints will be appreciated!

Thanks in advance.

Question about MSE used here.

您好~我最近刚开始接触半监督的东西。很感谢您提供的论文及代码资源，但是在尝试的时候发现我跑train_efficient_unet_2D_mean_teacher.py这个代码的时候在有MSE那一项consistency loss的时候反而使得结果变差了，我对比了在有和没有MSE这一项（其他保持一样）的情况下，用各自最后一次迭代的模型使用test_efficient_unet_2D_acdc.py进行测试，发现在使用MSE的时候测试结果感觉已经崩溃了（使用您提供的ACDC数据）。最差的一类dice只有0.5左右。同时也发现，这个存下来的best模型通常都在迭代次数的靠前位置，而这时通常mse这一项本身就比较小，是不是mse这一项引入反而造成训练不对了。不知道您那边跑代码的过程中是否有类似的情况？或者是我运行的时候有什么需要额外注意的地方。现在都是使用默认参数直接跑了一次。

opened by JohnMiao1 19
BRaTS2019 settings

Hi,

Thanks for your fantastic work. One question is why we preprocess the BRaST2019 into a binary problem. According to your paper (https://arxiv.org/pdf/2105.09511v3.pdf), the dataset has four classes (including b.g.). Did anyone do it before? Please share the reference.

Cheers,

opened by ghost 5
The first supplied array does not contain any binary object

Hi, thank you so much for your efforts in implementing all these methods.

After training on ACDC with labeled_num=3, the testing code on ACDC gives me this error "The first supplied array does not contain any binary object", which is raised near:

The problem is that the trained model does not predict labeled 2 and label 3, which can be seen here:

The visualized dice on validation set shows that there is a performance peak at 600th step

The test performance on the validation set (at 600th step) looks normal

It's confusing that on a test set image the same model does not prediction label 2 and 3 at all. Have you met this issue and could you give me some advice?

Many thanks.

opened by Huiimin5 4
models

I installed all the moudels, but the model still has the problem that models are not defined. I have tried many methods. When I input from torchvision import models, the problem is solved, but this problem occurs again? How to solve it?

opened by heixinbaicaishang 4
No module named 'val_unet_2D_dv'

Hi, I found some problem in 2ed step as following: Traceback (most recent call last): File "train_unet_2D_dv_fully_supervised.py", line 23, in <module> from val_unet_2D_dv import test_single_volume ModuleNotFoundError: No module named 'val_unet_2D_dv' I cant find the module "val_unet_2D_dv" in your repository or pypi, How can I get it?

opened by hannhu 4
About URPC Training On Brats2019

Hi, Good work and thanks for the scripts, it's good to use. I've trained a URPC model on brats2019 dataset by using this script in train_brats2019_semi_seg.sh : python -u train_uncertainty_rectified_pyramid_consistency_3D.py --labeled_num 25 --total_num 250 --root_path ../data/BraTS2019 --max_iterations 30000 --base_lr 0.1 --exp BraTS2019/Uncertainty_Rectified_Pyramid_Consistency but the result is poor: The dice_score is 0.41 not like what the paper says (about 0.8). While it's OK on ACDC dataset (the dice_score is high enough and hd95 is low enough). Is anything wrong?

opened by QUIvannn 3
Great project, I have a question about About the cross teaching between CNN and Transformer paper....
Table 2: Mean 3D DSC and HD95 (mm) on the ACDC dataset. All results are based on the same backbone (UNet) with a fixed seed. Mean and standard variance (in parentheses) are presented in this table. Red numbers denote the p-value < 0.05 based on paired t-test when comparing with the others

How to get the Mean and standard variance (in parentheses) are presented in this table? And how to generate the Red numbers denote the p-value < 0.05 based on paired t-test when comparing with the others? Could your please share the code? Thank you. @Luoxd1996 Looking forward to your reply.
opened by Byronnar 3
test_urpc.py

Hi, Is there provide a 2D "test_urpc.py". I try to use your work:"train_uncertainty_rectified_pyramid_consistency_2D.py", but I don't know how to test it. Thanks!

opened by 18677064404 3
Baidu link not working

Hello, thanks for your nice repository, however, I tried to download the two datasets from Baidu repository but the links are not working. Can you please look into this?

opened by hritam-98 3
your results

Thank you so much for releasing the code and dataset. Is it possible to show the performance comparison of these methods in your environment? or at least the best performance of your proposal on acdc and Brats?

opened by Huiimin5 3
How can we download the datasets?

Hi, I tried to download the datasets but it requires a bidu account. However, I can't register account with foreign mobile number ,and don't know much Chinese. Can you provide Google Drive, Dropbox or other download link? Thanks!

opened by PotatoThanh 2
Differences between the URCP paper and code

https://github.com/HiLab-git/SSL4MIS/blob/ad16872abd672cdcbe1ce387614797baa0a4dc6a/code/train_uncertainty_rectified_pyramid_consistency_2D.py#L165

I noticed a log operation employed before calculating KL divergence. I was confused about it, and it is different from Eq. (4) in either the MIA paper or the MICCAI paper.

Besides, I'm not sure whether the subscripts of Eq. (4) in both paper are wrong, because $P_C$ is not mentioned again, and $P_{avg}$ is not appear in the formulas.

opened by nicetomeetu21 0
unsupervised loss weight

In this project, the consistency_weight is set to 0.1,while in Cross-Consistency Training https://github.com/yassouali/CCT/blob/master/configs/config.json,it was set to 30. Maybe it is different. I'm NOT sure whether it influence the result or not.

opened by FrankWuuu 0
RGB input

Maybe the test_single_volume function in val_2D.py also needs to be modified,where the input channel of the net is set to 1 while the model is trained with 3 channel

opened by FrankWuuu 0
About the way you create dataloaders for labeled and unlabeled data

Hello,

First of all congratulations for this amazing work. I want to ask how you handle the creation of dataloaders for labeled and unlabaled data. To the best of my understanding from reading the dataloaders in each iteration you forward pass the same amount of labaled and unlabaled data. Actually in each epoch you pass the whole labeled data and random sample equal amount of unlabaled data. I have read a couple of approaches for this. The first is to define an epoch as the passing of all unlabeled data from the network, but with this the labeled data will be passed from the network multiple times in an epoch. The second approach, as you have done, is to use a sampler to sample at each epoch equal amount of unlabeled data to match the size of the labeled data. Which of these 2 techniques would force the model to perform better? Generally , I'm a bit confused on how to construct the dataloaders of labeled and unlabeled data in a semi supervised setting. Any hints will be appreciated!

Thanks in advance.

opened by nysp78 0
worker_init_fn in train_cross_teaching_between_cnn_transformer_2D.py

Hello , In the below line i do no not see the initialisation of worker_init_fn in the code available in the file train_cross_teaching_between_cnn_transformer_2D.py. Please can you help me with this.

trainloader = DataLoader(db_train, batch_sampler=batch_sampler, num_workers=4, pin_memory=True, worker_init_fn=worker_init_fn)

opened by Padmini588 0

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

Related tags

Overview

Semi-supervised-learning-for-medical-image-segmentation.

Literature reviews of semi-supervised learning approach for medical image segmentation (SSL4MIS).

Code for semi-supervised medical image segmentation.

Conclusion

Questions and Suggestions

Comments

Owner

Healthcare Intelligence Laboratory

Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"

ISBI 2022: Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image.

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

A collection of loss functions for medical image segmentation

Project looking into use of autoencoder for semi-supervised learning and comparing data requirements compared to supervised learning.

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation

DRIFT is a tool for Diachronic Analysis of Scientific Literature.

2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

Copy Paste positive polyp using poisson image blending for medical image segmentation

Build a medical knowledge graph based on Unified Language Medical System (UMLS)

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Code base for "On-the-Fly Test-time Adaptation for Medical Image Segmentation"

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation (CVPR 2021)

[cvpr22] Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.