Annotation-efficient deep learning for automatic medical image segmentation
This work significantly reduces the annotation burden for medical image segmentation, benefiting clinicians and researchers in biomedical applications where expert labels are scarce or expensive.
This paper addresses the challenge of medical image segmentation with limited or noisy annotations, proposing AIDE, an open-source framework. AIDE achieves segmentation quality comparable to fully-supervised models using only 10% of the training annotations on a breast tumor segmentation task across 11,852 images from three medical centers.
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.