Refining Pseudo Labels With a Teacher-Student Paradigm for Accurate Brain Lesion Segmentation

In medical image segmentation, obtaining large volume of high quality labeled data is a persistent challenge, especially for intricate tasks like brain lesion segmentation, where annotations are time-consuming, costly, and require expert knowledge. This work introduces a novel learning framework whe...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Pubali Chatterjee, Kaushik Das Sharma, Amlan Chakrabarti
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Mean-teacher model supervised learning superpixel segmentation pseudo label image segmentation
Online Access:	https://ieeexplore.ieee.org/document/10982225/