Direct comparison of multiple computer-aided polyp detection systems
Endoscopy · 01.01.2024 · 56 (01) · 63-69
DOI: 10.1055/a-2147-0571 ↗Kurz gefasst
Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.01.2024. Verfasst von Joel Troya und 9 weiteren Autor:innen. Beteiligte Einrichtung: Interventional and Experimental Endoscopy (InExEn), Department of Internal Medicine II, University Hospital Würzburg, Würzburg, Germany. Hauptthemen laut MEDLINE: Colonic Polyps, Colorectal Neoplasms. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Forum Gesundheitsstandort, Bayerisches Zentrum für Krebsforschung, Interdisziplinäres Zentrum für Klinische Forschung, Universitätsklinikum Würzburg F-406.
Abstract (Originalsprache)
Background and study aims Artificial intelligence (AI)-based systems for computer-aided detection (CADe) of polyps receive regular updates and occasionally offer customizable detection thresholds, both of which impact their performance, but little is known about these effects. This study aimed to compare the performance of different CADe systems on the same benchmark dataset.
Methods
101 colonoscopy videos were used as benchmark. Each video frame with a visible polyp was manually annotated with bounding boxes, resulting in 129 705 polyp images. The videos were then analyzed by three different CADe systems, representing five conditions: two versions of GI Genius, Endo-AID with detection Types A and B, and EndoMind, a freely available system. Evaluation included an analysis of sensitivity and false-positive rate, among other metrics.
Results
Endo-AID detection Type A, the earlier version of GI Genius, and EndoMind detected all 93 polyps. Both the later version of GI Genius and Endo-AID Type B missed 1 polyp. The mean per-frame sensitivities were 50.63 % and 67.85 %, respectively, for the earlier and later versions of GI Genius, 65.60 % and 52.95 %, respectively, for Endo-AID Types A and B, and 60.22 % for EndoMind.
Conclusions
This study compares the performance of different CADe systems, different updates, and different configuration modes. This might help clinicians to select the most appropriate system for their specific needs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Interventional and Experimental Endoscopy (InExEn), Department of Internal Medicine II, University Hospital Würzburg, Würzburg, Germany.
- Bavarian Cancer Research Center, Würzburg, Germany.
- Department of Internal Medicine and Gastroenterology, Katharinenhospital, Stuttgart, Germany.
- Artificial Intelligence and Knowledge Systems, Institute for Computer Science, Julius-Maximilians-Universität, Würzburg, Germany.
- Department of Internal Medicine I, University Hospital Ulm, Ulm, Germany.
ORCID-Profile: Joel Troya, Adrian Krenzer, Markus Brand, Alexander Hann
Förderung
- Forum Gesundheitsstandort
- Bayerisches Zentrum für Krebsforschung
- Interdisziplinäres Zentrum für Klinische Forschung, Universitätsklinikum Würzburg F-406
Zitieren
APA
Troya, J., Sudarevic, B., Krenzer, A., Banck, M., Brand, M., Walter, B. M., Puppe, F., Zoller, W. G., Meining, A., & Hann, A. (2024). Direct comparison of multiple computer-aided polyp detection systems. Endoscopy, 56(01), 63-69. https://doi.org/10.1055/a-2147-0571
Vancouver
Troya J, Sudarevic B, Krenzer A, Banck M, Brand M, Walter BM, et al. Direct comparison of multiple computer-aided polyp detection systems. Endoscopy. 2024;56(01):63-69. doi:10.1055/a-2147-0571
BibTeX
@article{Troya2024,
author = {Troya, Joel and Sudarevic, Boban and Krenzer, Adrian and Banck, Michael and Brand, Markus and Walter, Benjamin M and Puppe, Frank and Zoller, Wolfram G and Meining, Alexander and Hann, Alexander},
title = {Direct comparison of multiple computer-aided polyp detection systems},
journal = {Endoscopy},
year = {2024},
volume = {56},
number = {01},
pages = {63--69},
doi = {10.1055/a-2147-0571}
}
EUVIMED