Annotation-efficient deep learning for automatic medical image segmentation
arXiv:2012.04885 · doi:10.1038/s41467-021-26216-9
Abstract
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.
References in corpus (17)
- A Survey on Deep Learning in Medical Image Analysis
- Distilling the Knowledge in a Neural Network
- CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
- A Closer Look at Memorization in Deep Networks
- Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
- Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
- Iterative annotation to ease neural network training: Specialized machine learning in medical image analysis
- How does Disagreement Help Generalization against Label Corruption?
- X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
- Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
- CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke
- Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis
- Data Distillation: Towards Omni-Supervised Learning
- Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation
- Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation