Segmentation only uses sparse annotations: Unified weakly and semi-supervised learning in medical images

Download PDF
Open Webpage

Feng Gao, Minhao Hu, Min-Er Zhong, Shixiang Feng, Xuwei Tian, Xiaochun Meng, Ma-yi-di-li Ni-jia-ti, Zeping Huang, Minyi Lv, Tao Song, Xiaofan Zhang, Xiaoguang Zou, Xiaojian Wu

Published: 2022, Last Modified: 06 Jan 2026Medical Image Anal. 2022EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We designed a image segmentation framework with weakly- semi- supervision setting.•We proposed a consistency loss, which amplifies the error of boundary and outliers.•We achieved a comparable performance with fully supervised models on two datasets.