Negative Samples for Improving Object Detection—A Case Study in AI-Assisted Colonoscopy for Polyp Detection
Diagnostics · 03.03.2023 · 13 (5) · 966
DOI: 10.3390/diagnostics13050966 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 03.03.2023. Verfasst von Alba Nogueira-Rodríguez und 3 weiteren Autor:innen. Beteiligte Einrichtung: CINBIO, Department of Computer Science, ESEI-Escuela Superior de Ingeniería Informática, Universidade de Vigo, 32004 Ourense, Spain. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia y Competitividad, Gobierno de España, Ministerio de Ciencia e Innovación, Gobierno de España, Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia).
Abstract (Originalsprache)
Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- CINBIO, Department of Computer Science, ESEI-Escuela Superior de Ingeniería Informática, Universidade de Vigo, 32004 Ourense, Spain.
- SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, 36213 Vigo, Spain.
ORCID-Profile: Alba Nogueira-Rodríguez, Miguel Reboiro-Jato, Hugo López-Fernández
Förderung
- Ministerio de Ciencia y Competitividad, Gobierno de España
- Ministerio de Ciencia e Innovación, Gobierno de España
- Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia)
- Ministerio de Ciencia y Competitividad and Ministerio de Ciencia e Innovación, Gobierno de España
Zitieren
APA
Nogueira-Rodríguez, A., Glez-Peña, D., Reboiro-Jato, M., & López-Fernández, H. (2023). Negative Samples for Improving Object Detection—A Case Study in AI-Assisted Colonoscopy for Polyp Detection. Diagnostics, 13(5), 966. https://doi.org/10.3390/diagnostics13050966
Vancouver
Nogueira-Rodríguez A, Glez-Peña D, Reboiro-Jato M, López-Fernández H. Negative Samples for Improving Object Detection—A Case Study in AI-Assisted Colonoscopy for Polyp Detection. Diagnostics. 2023;13(5):966. doi:10.3390/diagnostics13050966
BibTeX
@article{NogueiraRodrguez2023,
author = {Nogueira-Rodríguez, Alba and Glez-Peña, Daniel and Reboiro-Jato, Miguel and López-Fernández, Hugo},
title = {Negative Samples for Improving Object Detection—A Case Study in AI-Assisted Colonoscopy for Polyp Detection},
journal = {Diagnostics},
year = {2023},
volume = {13},
number = {5},
pages = {966},
doi = {10.3390/diagnostics13050966}
}
EUVIMED