Publications by authors named "Quentin Angermann"
GTCreator: a flexible annotation tool for image-based datasets.
Int J Comput Assist Radiol Surg
February 2019
Purpose: Methodology evaluation for decision support systems for health is a time-consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use.
View Article and Find Full Text PDFArticle Synopsis
- Colonoscopy is the best method for screening colon cancer, but some polyps can still be overlooked, impacting early detection and treatment.
- Various computational systems have been suggested to help find these polyps, yet they lack proper evaluation due to limited publicly available annotated data.
- An Automatic Polyp Detection sub-challenge was held at MICCAI 2015 to assess and compare these methods, revealing that convolutional neural networks perform best, but a combination of different approaches can enhance overall results.