Journal
2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022)
Volume -, Issue -, Pages -Publisher
IEEE
DOI: 10.1109/ISBI52829.2022.9761436
Keywords
-
Funding
- Australian Research Council [DP180103232, FT190100525]
- Australian Research Council [FT190100525] Funding Source: Australian Research Council
Ask authors/readers for more resources
Real-time and robust automatic detection of polyps from colonoscopy videos is an essential task. The current focus is on accurate but inefficient detectors, but we advocate the development of simple and efficient detectors combined with effective trackers for real-time detection. This paper proposes a Kalman filtering tracker that can work with powerful and efficient detectors, achieving state-of-the-art detection accuracy and real-time processing.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available