MICCAI 2022 Paper with Codes

This repository is still under construction. Please help yourself to join 😊.

Contents

• 1. Backbone
• 2. Multi Task Learning
• 3. Self Supervised Learning
• 4. Weakly Supervised Learning
• 5. Semi Supervised Learning
• 6. Imbalanced Data
• 7. Multi Modal
• 8. Data Augmentation
• 9. Knowledge Distillation

1. Backbone

UNeXt: MLP-based Rapid Medical Image Segmentation Network

• Paper: https://arxiv.org/abs/2203.04967
• Code: https://github.com/jeya-maria-jose/UNeXt-pytorch
• Project Website: https://jeya-maria-jose.github.io/UNext-web/
• Data Modality: Camera-acquired dermatologic images, Ultrasound images.
• Task: Segmentation.

Spatial-Hierarchical Graph Neural Network with Dynamic Structure Learning for Histological Image Classification

• Paper: https://link.springer.com/chapter/10.1007/978-3-031-16434-7_18
• Code: https://github.com/HeLongHuang/SHGNN
• Data Modality: Histology.
• Task:

2. Multi Task Learning

TGANet: Text-guided Attention for Improved Polyp Segmentation

• Paper: https://arxiv.org/abs/2205.04280
• Code: https://github.com/nikhilroxtomar/TGANet
• Data Modality: Colonoscopy.
• Task: Polyp segmentation.

3. Self Supervised Learning

mulEEG: A Multi-View Representation Learning on EEG Signals

• Paper: https://arxiv.org/abs/2204.03272
• Code: https://github.com/likith012/mulEEG
• Data Modality: Electroencephalogram (EEG) signals.
• Task: Classification.

Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Ray

• Paper: https://arxiv.org/pdf/2206.03935.pdf
• Code: https://github.com/caiyu6666/DDAD
• Data Modality: X-Rays.
• Task: Anomaly detection.

Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions

• Paper: https://arxiv.org/abs/2205.09292
• Code: https://github.com/xmed-lab/DistillingSelf
• Data Modality: Surgical video.

Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image

• Paper: https://arxiv.org/abs/2206.01856
• Code: https://github.com/tacalvin/Poisson2Sparse
• Data Modality: Fluorescence microscopy, MRI.
• Task: Denosing.

4. Weakly Supervised Learning

Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images

• Paper: https://arxiv.org/abs/2206.06665
• Code: https://github.com/xmed-lab/OEEM
• Data Modality:
• Task:

Transformer Based Multiple Instance Learning for Weakly Supervised Histopathology Image Segmentation

• Paper: https://arxiv.org/pdf/2205.08878
• Code: https://github.com/Nexuslkl/Swin_MIL
• Data Modality: Histology.
• Task: Segmentation.

Uncertainty Aware Sampling Framework of Weak-Label Learning for Histology Image Classification

• Paper: https://link.springer.com/chapter/10.1007/978-3-031-16434-7_36
• Code: https://github.com/machiraju-lab/UA-CNN
• Data Modality: Histology.
• Task: Classification.

SETMIL: Spatial Encoding Transformer-Based Multiple Instance Learning for Pathological Image Analysis

• Paper: https://link.springer.com/chapter/10.1007/978-3-031-16434-7_7
• Code: https://github.com/TencentAILabHealthcare/SETMIL.git
• Data Modality: Histology.
• Task: Classification.

5. Semi Supervised Learning

Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation

• Paper: https://arxiv.org/pdf/2203.01324.pdf
• Code: https://github.com/ycwu1997/SS-Net
• Data Modality:
• Task:

6. Imbalanced Data

Calibrating Label Distribution for Class-Imbalanced Barely-Supervised Knee Segmentation

• Paper: https://arxiv.org/abs/2205.03644
• Code: https://github.com/xmed-lab/CLD-Semi
• Data Modality:
• Task:

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

• Paper: https://arxiv.org/abs/2103.04053
• Code: https://github.com/FBLADL/NVUM
• Data Modality:
• Task:

7. Multi Modal

mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation

• Paper: https://arxiv.org/abs/2206.02425
• Code: https://github.com/YaoZhang93/mmFormer
• Data Modality:
• Task:

Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency

• Paper: https://arxiv.org/abs/2206.11826
• Code: https://github.com/WeijieMax/CPC-Trans
• Data Modality:
• Task:

8. Data Augmentation

SapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation

• Paper: https://arxiv.org/abs/2206.02118
• Code: https://github.com/BWGZK/ShapePU
• Data Modality:
• Task:

RandStainNA: Learning Stain-Agnostic Features from Histology Slides by Bridging Stain Augmentation and Normalization

• Paper: https://arxiv.org/abs/2206.12694
• Code: https://github.com/yiqings/RandStainNA
• Data Modality: MRI
• Task: Classification, Segmentation.

SUPER-IVIM-DC: Intra-voxel Incoherent Motion Based Fetal Lung Maturity Assessment from Limited DWI Data Using Supervised Learning Coupled with Data-Consistency

• Paper: https://arxiv.org/pdf/2206.03820
• Code: https://github.com/TechnionComputationalMRILab/SUPER-IVIM-DC
• Data Modality: DWI MRI.
• Task:

9. Knowledge-Distillation

Distilling Knowledge from Topological Representations for Pathological Complete Response Prediction

• Paper: https://link.springer.com/chapter/10.1007/978-3-031-16434-7_6
• Code: https://github.com/zoedsy/DK_Topology_PCR
• Data Modality: MRI
• Task:

Inclusion Critertion

In this initial stage where MICCAI papers are not official published, we use the key world MICCAI 2022 on github to search the associated respoitory. Afterwards, we primary check if there is a pre-print version on arXiv.