Journal Article

Annotation-efficient deep learning for automatic medical image segmentation

Wang, Shanshan, Zheng, Hairong, Tan, Hongna, Wang, Meiyun, Chen, Jie, Wu, Yaping, Wang, Rongpin, Liu, Zaiyi, Li, Cheng, Sun, Hui, Ben Ayed, Ismail, Yang, Rui, Liu, Xinfeng, Liu, Xin, Zhou, Huihui

2021

Overview

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, the authors introduce an open-source framework to handle imperfect training datasets.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 59 / 59/57 / 631/114/1305 / 631/114/1564 / 639/166/985 / Annotations / Biomedical materials / Breast cancer / Breast Neoplasms - diagnostic imaging / Breast Neoplasms - pathology / Datasets / Datasets as Topic / Deep Learning / Empirical analysis / Female / Health care facilities / Health services / Humanities and Social Sciences / Humans / Image processing / Image Processing, Computer-Assisted - methods / Image segmentation / Magnetic Resonance Imaging - statistics & numerical data / Medical imaging / Medical research / multidisciplinary / Retrospective Studies / Science / Science (multidisciplinary) / Teaching methods / Therapeutic applications / Training