Annotation-efficient deep learning for automatic medical image segmentation
Description
<jats:title>Abstract</jats:title><jats:p>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.</jats:p>
Journal
-
- Nature Communications
-
Nature Communications 12 (1), 5915-, 2021-10-08
Springer Science and Business Media LLC
- Tweet
Details 詳細情報について
-
- CRID
- 1360299770348843904
-
- ISSN
- 20411723
-
- Data Source
-
- Crossref