DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation
This addresses the labor-intensive challenge of obtaining 3D segmentations for medical imaging, offering a semi-supervised solution that enhances model performance with very limited training data, though it is incremental as it builds on classical joint approaches and deep unsupervised methods.
The paper tackles the problem of limited labeled data for 3D medical image segmentation by proposing a joint learning framework for image registration and segmentation, achieving improvements in Dice scores by 2.7% and 1.8% on knee and brain images in a one-shot scenario.
Deep convolutional neural networks (CNNs) are state-of-the-art for semantic image segmentation, but typically require many labeled training samples. Obtaining 3D segmentations of medical images for supervised training is difficult and labor intensive. Motivated by classical approaches for joint segmentation and registration we therefore propose a deep learning framework that jointly learns networks for image registration and image segmentation. In contrast to previous work on deep unsupervised image registration, which showed the benefit of weak supervision via image segmentations, our approach can use existing segmentations when available and computes them via the segmentation network otherwise, thereby providing the same registration benefit. Conversely, segmentation network training benefits from the registration, which essentially provides a realistic form of data augmentation. Experiments on knee and brain 3D magnetic resonance (MR) images show that our approach achieves large simultaneous improvements of segmentation and registration accuracy (over independently trained networks) and allows training high-quality models with very limited training data. Specifically, in a one-shot-scenario (with only one manually labeled image) our approach increases Dice scores (%) over an unsupervised registration network by 2.7 and 1.8 on the knee and brain images respectively.