Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation

Model Overview

Abstract

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation, often producing noisy predictions around object boundaries. To address this, we adopt a superpixel representation and develop a robust iterative learning strategy that combines noise-aware training of segmentation network and noisy label refinement, both guided by the superpixels. This design enables us to exploit the structural constraints in segmentation labels and effectively mitigate the impact of label noise in learning. Experiments on two benchmarks show that our method outperforms recent state-of-the-art approaches, and achieves superior robustness in a wide range of label noises. Code is available at https://github.com/gaozhitong/SP_guided_Noisy_Label_Seg.

Publication
In Medical Image Computing and Computer Assisted Intervention Society 2021
Shuailin Li
Shuailin Li
Master Student

My research interests include image segmentation, medical image analysis and weak-supervised learning.

Zhitong Gao
Zhitong Gao
Master Student

My research interests include learning from noisy labels, uncertainty estimation and medical image segmentation.

Xuming He
Xuming He
Associate Professor

My research interests include few/low-shot learning, graph neural networks and video understanding.