Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation
This work addresses the problem of segmenting unfamiliar organs with limited data for medical image analysis, representing an incremental advance in one-shot learning for healthcare applications.
The paper tackles the challenge of one-shot organ segmentation in medical CT images by proposing OrganNet, which learns a generalized organ concept from annotated classes and transfers it to unseen organs using pyramid reasoning modules to model anatomical correlations. The method achieves state-of-the-art results in one-shot segmentation and produces competitive outcomes compared to fully-supervised models.
Learning by imitation is one of the most significant abilities of human beings and plays a vital role in human's computational neural system. In medical image analysis, given several exemplars (anchors), experienced radiologist has the ability to delineate unfamiliar organs by imitating the reasoning process learned from existing types of organs. Inspired by this observation, we propose OrganNet which learns a generalized organ concept from a set of annotated organ classes and then transfer this concept to unseen classes. In this paper, we show that such process can be integrated into the one-shot segmentation task which is a very challenging but meaningful topic. We propose pyramid reasoning modules (PRMs) to model the anatomical correlation between anchor and target volumes. In practice, the proposed module first computes a correlation matrix between target and anchor computerized tomography (CT) volumes. Then, this matrix is used to transform the feature representations of both anchor volume and its segmentation mask. Finally, OrganNet learns to fuse the representations from various inputs and predicts segmentation results for target volume. Extensive experiments show that OrganNet can effectively resist the wide variations in organ morphology and produce state-of-the-art results in one-shot segmentation task. Moreover, even when compared with fully-supervised segmentation models, OrganNet is still able to produce satisfying segmentation results.