RT Journal Article
T1 Negative samples for improving object detection—A case study in aI-assisted colonoscopy for polyp detection
A1 Nogueira Rodríguez, Alba
A1 González Peña, Daniel
A1 Reboiro Jato, Miguel
A1 López Fernández, Hugo
K1 3207.03 Carcinogénesis
K1 3210 Medicina Preventiva
K1 1203.20 Sistemas de Control Médico
AB 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).
PB Diagnostics
SN 20754418
YR 2023
FD 2023-03-03
LK http://hdl.handle.net/11093/4679
UL http://hdl.handle.net/11093/4679
LA eng
NO Diagnostics, 13(5): 966 (2023)
NO Ministerio de Ciencia y Competitividad y Ministerio de Ciencia e Innovación | Ref. DPI2017-87494-R
DS Investigo
RD 24-ene-2025