Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.
Peng Cheng Laboratory, Shenzhen, Guangdong, China.
Nat Commun. 2021 Oct 8;12(1):5915. doi: 10.1038/s41467-021-26216-9.
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.
自动医学图像分割在科学研究和医疗保健中起着至关重要的作用。现有的高性能深度学习方法通常依赖于具有高质量手动注释的大型训练数据集，而在许多临床应用中，这些数据集很难获得。在这里，我们介绍了 Annotation-efficient Deep lEarning（AIDE），这是一个开源框架，用于处理不完美的训练数据集。我们进行了方法分析和实证评估，并证明了 AIDE 在具有稀缺或嘈杂注释的开放数据集上表现出更好的性能，超越了传统的完全监督模型。我们进一步在乳腺癌分割的实际案例研究中测试了 AIDE。我们使用了来自三个医学中心的包含 11852 个乳房图像的三个数据集，AIDE 利用 10%的训练注释，始终生成与完全监督模型或独立放射科医生提供的分割图相当的分割图。利用专家标签的 10 倍增强效率有可能促进广泛的生物医学应用。
