Semantic analysis of real endoscopies with unsupervised learned descriptors

O. León Barbed, Cristina Oriol, Pablo Azagra Millán, Ana C Murillo

Keywords: Endoscopy, unsupervised learning, image description, scene classification

TL;DR: We use representation learning to perform semantic video segmentation

Abstract: This work explores automatic analysis of medical procedure recordings, in particular, endoscopies. Regular medical practice recordings are noisy and challenging to process, so a quick and automatic overview of their content is essential. We show how advances in unsupervised representation learning can be applied to real medical data, obtaining rich descriptors to perform automatic semantic analysis of these recordings.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Unsupervised Learning and Representation Learning

Secondary Subject Area: Application: Endoscopy

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.