Using YOLOv3 to detect colorectal polyps in video

Authors

Mary Chris Roperos Go ⋅ PH National Institute of Physics, University of the Philippines Diliman
Francis N. C. Paraan ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

A model based on the You Only Look Once (YOLO) algorithm was trained to detect polyps on a dataset of 503 polyp-positive images taken from colonoscopy video frames. We achieve precision on test sets that is comparable to the performance of a previously described model trained on a much larger set of 5,545 images. However, our model has a lower recall and missed some polyps in the test set.

Downloads

Issue

2020: Proceedings of the 38th Samahang Pisika ng Pilipinas Physics Conference

Shedding light on the pandemic through the lens of physics
Pagtanglaw sa pandemya sa lente ng pisika
19-23 October 2020

This is the first fully online SPP Physics Conference. Please visit the SPP2020 activity webpage for more information on this year's Physics Congress.

Article ID

SPP-2020-2A-05

Section

Complex Systems and Data Analytics (Short Presentations)

Published

2020-10-19

How to Cite

[1]

MCR Go and FNC Paraan, Using YOLOv3 to detect colorectal polyps in video, Proceedings of the Samahang Pisika ng Pilipinas 38, SPP-2020-2A-05 (2020). URL: https://proceedings.spp-online.org/article/view/SPP-2020-2A-05.