Home

Awesome

Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty

1. Requirements

Some important required packages include:    
- Python == 3.6  
- pytorch 1.6.0
- torchvision 0.7.0
Some basic python packages such as Numpy...

2. Overview

2.1 Introduction

Medical image segmentation (MIS) is essential for supporting disease diagnosis and treatment effect assessment. Despite considerable advances in artificial intelligence (AI) for MIS, clinicians remain skeptical of its utility, maintaining low confidence in such black box systems, with this problem being exacerbated by low generalization for out-of-distribution (OOD) data. To move towards effective clinical utilization, we propose a foundation model named EvidenceCap, which makes the box transparent in a quantifiable way by uncertainty estimation. EvidenceCap not only makes AI visible in regions of uncertainty and OOD data, but also enhances the reliability, robustness, and computational efficiency of MIS. Uncertainty is modeled explicitly through subjective logic theory to gather strong evidence from features. We show the effectiveness of EvidenceCap in three segmentation datasets and apply it to the clinic. Our work sheds light on clinical safe applications and explainable AI, and can contribute towards trustworthiness in the medical domain.

<div align=center><img width="900" height="300" alt="Our TBraTS framework" src="https://github.com/Cocofeat/UMIS/blob/main/image/Moti-TMIS.png"/></div>

2.2 Framework Overview

EvidenceCap is a trustworthy medical image segmentation framework based on evidential deep learning, which provides robust segmentation performance and reliable uncertainty quantification for diagnostic support. A pipeline of EvidenceCap and its results in undertaking trustworthy medical image segmentation tasks are shown in Fig. 1 b and c. In the training phase (Fig. 1 b), EvidenceCap can be applied to any task in numerous medical domains. Its trained model visually generates auxiliary diagnostic results, including robust target segmentation results and reliable uncertainty estimation. In the testing phase, in order to verify the effectiveness of the method, EvidenceCap was tested for confidence, robustness, and computational efficiency on different segmentation tasks.

<div align=center><img width="900" height="400" alt="Our EvidenceCap framework" src="https://github.com/Cocofeat/UMIS/blob/main/image/NC_F1.png"/></div>

2.3 Qualitative Results

<div align=center><img width="900" height="400" alt="Qualitative Results on BraTS2019 dataset" src="https://github.com/Cocofeat/UMIS/blob/main/image/brats_fA2.png"/></div>

3. Proposed Baseline

3.1 Original Data Acquisition

3.2 Data Preprocess or download Abnormal data directly

Abnormal data: Gaussian noise, Gaussian blur and random pixel mask

3.3 Abnormal Data Acquisition

<!-- -->

3.4 Training & Testing

3.5 Evaluating & Output uncertainty map

:fire: NEWS :fire:

If you find our work is helpful for your research, please consider to cite:

@misc{Coco2022EvidenceCap,
  author    = {Zou, Ke and Yuan, Xuedong and Shen, Xiaojing and Wang, Meng and Rick, Siow Mong, Goh and Liu, Yong and Fu, Huazhu},
  title     = {EvidenceCap: Towards trustworthy medical image segmentation via evidential identity cap},
  year      = {2023},
  publisher = {arXiv},
  url = {https://arxiv.org/abs/2301.00349},
}

@InProceedings{Coco2022TBraTS,
  author    = {Zou, Ke and Yuan, Xuedong and Shen, Xiaojing and Wang, Meng and Fu, Huazhu},
  booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2022},
  title     = {TBraTS: Trusted Brain Tumor Segmentation},
  year      = {2022},
  address   = {Cham},
  pages     = {503--513},
  publisher = {Springer Nature Switzerland},
}

Acknowledgement

Part of the code is revised from CA-Net, H-DenseU, TransBTS, TMC

Contact