Self-Supervised Learning for Segmentation
This work addresses kidney segmentation for medical imaging, but it is incremental as it applies existing self-supervised methods to a specific domain.
The paper tackled kidney segmentation from CT scans by using self-supervised learning with a siamese CNN to classify kidney sides as a proxy task, resulting in improved performance and faster convergence compared to training from scratch without extra data or annotations.
Self-supervised learning is emerging as an effective substitute for transfer learning from large datasets. In this work, we use kidney segmentation to explore this idea. The anatomical asymmetry of kidneys is leveraged to define an effective proxy task for kidney segmentation via self-supervised learning. A siamese convolutional neural network (CNN) is used to classify a given pair of kidney sections from CT volumes as being kidneys of the same or different sides. This knowledge is then transferred for the segmentation of kidneys using another deep CNN using one branch of the siamese CNN as the encoder for the segmentation network. Evaluation results on a publicly available dataset containing computed tomography (CT) scans of the abdominal region shows that a boost in performance and fast convergence can be had relative to a network trained conventionally from scratch. This is notable given that no additional data/expensive annotations or augmentation were used in training.