Order-Guided Disentangled Representation Learning for Ulcerative Colitis Classification with Limited Labels
This work addresses a domain-specific problem in medical imaging for endoscopic diagnosis, offering an incremental improvement by adapting semi-supervised learning to handle variability in colon images.
The paper tackles ulcerative colitis classification from endoscopic images with limited labeled data and high appearance variability by proposing a semi-supervised method that uses location and image order features for disentangled representation learning, achieving improved performance over existing methods with few annotations.
Ulcerative colitis (UC) classification, which is an important task for endoscopic diagnosis, involves two main difficulties. First, endoscopic images with the annotation about UC (positive or negative) are usually limited. Second, they show a large variability in their appearance due to the location in the colon. Especially, the second difficulty prevents us from using existing semi-supervised learning techniques, which are the common remedy for the first difficulty. In this paper, we propose a practical semi-supervised learning method for UC classification by newly exploiting two additional features, the location in a colon (e.g., left colon) and image capturing order, both of which are often attached to individual images in endoscopic image sequences. The proposed method can extract the essential information of UC classification efficiently by a disentanglement process with those features. Experimental results demonstrate that the proposed method outperforms several existing semi-supervised learning methods in the classification task, even with a small number of annotated images.