Annotation-efficient deep learning for automatic medical image segmentation

By Shanshan Wang, Cheng Li, Rongpin Wang, Zaiyi Liu, Meiyun Wang, H. Tan, Yaping Wu, Xinfeng Liu, Hui Sun, Rui Yang and 5 more. Nature Communications, 2020

300 citations recorded by the source corpus.

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.

View Paper: https://www.semanticscholar.org/paper/a0e856430bc91597bf0e8ce30b6babc84462efa0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jieneng Chen
2. Yucheng Tang
3. Jie Liu
4. Zongwei Zhou
5. Yongyi Lu
6. Yixuan Yuan
7. Junfei Xiao
8. Alan L. Yuille

Citations in the corpus

• CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection (2023, background): “Although a total of around 5,000 annotated abdominal CT scans are publicly available, an ingrained impression remains: medical imaging datasets are too small to develop robust AI models [13,45,55,61,78,79].”
• Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining (2024, unknown): “This is particularly important in the field of medicine, where medical image datasets are often limited in size and diversity [28].”