Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/128649
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Few-shot anomaly detection for polyp frames from colonoscopy |
Author: | Tian, Y. Maicas Suso, G. Zorron Cheng Tao Pu, L. Singh, R. Verjans, J.W. Carneiro, G. |
Citation: | Lecture Notes in Artificial Intelligence, 2020 / Martel, A.L., Abolmaesumi, P., Stoyanov, D., Mateus, D., Zuluaga, M.A., Zhou, S.K., Racoceanu, D., Joskowicz, L. (ed./s), vol.12266, pp.274-284 |
Publisher: | Springer Nature |
Publisher Place: | Switzerland |
Issue Date: | 2020 |
Series/Report no.: | Lecture Notes in Computer Science; 12266 |
ISBN: | 3030597245 9783030597245 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | Medical Image Computing and Computer-Assisted Intervention (MICCAI) (4 Oct 2020 - 8 Oct 2020 : virtual online) |
Editor: | Martel, A.L. Abolmaesumi, P. Stoyanov, D. Mateus, D. Zuluaga, M.A. Zhou, S.K. Racoceanu, D. Joskowicz, L. |
Statement of Responsibility: | Yu Tian, Gabriel Maicas, Leonardo Zorron Cheng Tao Pu, Rajvinder Singh, Johan W. Verjans, and Gustavo Carneiro |
Abstract: | 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. Code is available at https://github.com/tianyu0207/FSAD-Net. |
Keywords: | Machine learning; Anomaly detection; Few-shot learning; Weakly-supervised learning; Polyp detection; Colonoscopy |
Description: | Proceedings, Part VI |
Rights: | © Springer Nature Switzerland AG 2020 |
DOI: | 10.1007/978-3-030-59725-2_27 |
Grant ID: | http://purl.org/au-research/grants/arc/DP180103232 |
Published version: | https://link.springer.com/book/10.1007/978-3-030-59725-2 |
Appears in Collections: | Aurora harvest 8 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.