Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
This work addresses the need for context-sensitive self-supervised learning in medical imaging, particularly for detecting tissue abnormalities, but it appears incremental as it builds on existing self-supervised and graph neural network techniques.
The paper tackles the problem of self-supervised learning for medical images by introducing a context-aware method using graph neural networks to incorporate anatomical relationships, achieving favorable results compared to baseline methods on large-scale CT lung datasets and applying it to COVID-19 abnormality staging.
Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method should be sensitive enough to detect deviation from normal-appearing tissue of each anatomical region; here, anatomy is the context. We introduce a novel approach with two levels of self-supervised representation learning objectives: one on the regional anatomical level and another on the patient-level. We use graph neural networks to incorporate the relationship between different anatomical regions. The structure of the graph is informed by anatomical correspondences between each patient and an anatomical atlas. In addition, the graph representation has the advantage of handling any arbitrarily sized image in full resolution. Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context. We use the learned embedding for staging lung tissue abnormalities related to COVID-19.