Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy
This addresses the challenge of detecting polyps in colonoscopy videos, which is crucial for early cancer diagnosis, but the approach is incremental as it builds on existing anomaly detection frameworks.
The paper tackled the problem of anomaly detection in colonoscopy images, where existing methods are sensitive to outliers like small polyps, by proposing a few-shot method that learns from both inliers and a small set of outliers, achieving state-of-the-art detection results with stable performance after about 40 abnormal training images.
Anomaly detection methods generally target the learning of a normal image distribution (i.e., inliers showing healthy cases) and during testing, samples relatively far from the learned distribution are classified as anomalies (i.e., outliers showing disease cases). These approaches tend to be sensitive to outliers that lie relatively close to inliers (e.g., a colonoscopy image with a small polyp). In this paper, we address the inappropriate sensitivity to outliers by also learning from inliers. We propose a new few-shot anomaly detection method based on an encoder trained to maximise the mutual information between feature embeddings and normal images, followed by a few-shot score inference network, trained with a large set of inliers and a substantially smaller set of outliers. We evaluate our proposed method on the clinical problem of detecting frames containing polyps from colonoscopy video sequences, where the training set has 13350 normal images (i.e., without polyps) and less than 100 abnormal images (i.e., with polyps). The results of our proposed model on this data set reveal a state-of-the-art detection result, while the performance based on different number of anomaly samples is relatively stable after approximately 40 abnormal training images.