CVMay 30, 2023

Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions

arXiv:2305.18830v126 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the labor-intensive annotation challenge in medical imaging for cancer diagnosis, presenting an incremental improvement in semi-supervised segmentation methods.

The paper tackles the problem of reducing annotation costs for pathological image segmentation in cancer diagnosis by proposing a semi-supervised learning method called Cross Distillation of Multiple Attentions (CDMA), which outperforms eight state-of-the-art SSL methods on the DigestPath dataset under different annotation ratios.

Segmentation of pathological images is a crucial step for accurate cancer diagnosis. However, acquiring dense annotations of such images for training is labor-intensive and time-consuming. To address this issue, Semi-Supervised Learning (SSL) has the potential for reducing the annotation cost, but it is challenged by a large number of unlabeled training images. In this paper, we propose a novel SSL method based on Cross Distillation of Multiple Attentions (CDMA) to effectively leverage unlabeled images. Firstly, we propose a Multi-attention Tri-branch Network (MTNet) that consists of an encoder and a three-branch decoder, with each branch using a different attention mechanism that calibrates features in different aspects to generate diverse outputs. Secondly, we introduce Cross Decoder Knowledge Distillation (CDKD) between the three decoder branches, allowing them to learn from each other's soft labels to mitigate the negative impact of incorrect pseudo labels in training. Additionally, uncertainty minimization is applied to the average prediction of the three branches, which further regularizes predictions on unlabeled images and encourages inter-branch consistency. Our proposed CDMA was compared with eight state-of-the-art SSL methods on the public DigestPath dataset, and the experimental results showed that our method outperforms the other approaches under different annotation ratios. The code is available at \href{https://github.com/HiLab-git/CDMA}{https://github.com/HiLab-git/CDMA.}

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes