Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/136486
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos |
Author: | Butler, D. Zhang, Y. Chen, T. Shin, S.H. Singh, R. Carneiro, G. |
Citation: | Proceedings / IEEE International Symposium on Biomedical Imaging: from nano to macro. IEEE International Symposium on Biomedical Imaging, 2022, vol.2022 |
Publisher: | IEEE |
Publisher Place: | Online |
Issue Date: | 2022 |
Series/Report no.: | IEEE International Symposium on Biomedical Imaging |
ISBN: | 9781665429245 |
ISSN: | 1945-7928 1945-8452 |
Conference Name: | IEEE International Symposium on Biomedical Imaging (ISBI) (28 Mar 2022 - 31 Mar 2022 : virtual online, Kolkata, India) |
Statement of Responsibility: | David Butler, Yuan Zhang, Tim Chen, Seon Ho Shin, Rajvinder Singh, Gustavo Carneiro |
Abstract: | Real-time and robust automatic detection of polyps from colonoscopy videos are essential tasks to help improve the performance of doctors during this exam. The current focus of the field is on the development of accurate but inefficient detectors that will not enable a real-time application. We advocate that the field should instead focus on the development of simple and efficient detectors that can be combined with effective trackers to allow the implementation of real-time polyp detectors. In this paper, we propose a Kalman filtering tracker that can work together with powerful, but efficient detectors, enabling the implementation of real-time polyp detectors. In particular, we show that the combination of our Kalman filtering with the detector PP-YOLO shows state-of-the-art (SOTA) detection accuracy and real-time processing. More specifically, our approach has SOTA results on the CVC-ClinicDB dataset, with a recall of 0.740, precision of 0.869, F 1 score of 0.799, an average precision (AP) of 0.837, and can run in real time (i.e., 30 frames per second). We also evaluate our method on a subset of the Hyper-Kvasir annotated by our clinical collaborators, resulting in SOTA results, with a recall of 0.956, precision of 0.875, F 1 score of 0.914, AP of 0.952, and can run in real time 1. |
Rights: | ©2022 IEEE |
DOI: | 10.1109/ISBI52829.2022.9761436 |
Grant ID: | http://purl.org/au-research/grants/arc/DP180103232 http://purl.org/au-research/grants/arc/FT190100525 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/9761376/proceeding |
Appears in Collections: | Computer Science publications Medicine 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.