CoMixMatch: Semi-supervised Detection of Pancreatic Cancer on Noisy, Gigapixel Histology Images

J. Vince Pulido, Sana Syed, Donald E. Brown

2021

Abstract

One of the greatest obstacles in the adoption of deep neural networks for new medical applications is that training these models require a large number of manually labeled training samples. In order to circumvent the laborious annotation process, some researchers have turned to semi-supervised learning techniques where models learn from a large body of unlabeled data along with a smaller set of labeled data. However, these techniques have not been fully examined in the histology setting where there is a high degree of noise. This body of work investigates an extension of the semi-supervised method MixMatch–we call CoMixMatch– which applies semi-supervised co-teaching and a contrastive unlabeled loss. More specifically, we study these models’ impact under a highly noisy, open-set histology setting. The findings here motivate the development of semi-supervised methods to ameliorate annotation costs commonly encountered in medical data applications.

Paper Citation

in Harvard Style

Pulido J., Syed S. and Brown D. (2021). CoMixMatch: Semi-supervised Detection of Pancreatic Cancer on Noisy, Gigapixel Histology Images. In Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 2: BIOIMAGING; ISBN 978-989-758-490-9, SciTePress, pages 56-64. DOI: 10.5220/0010264100002865

in Bibtex Style

@conference{bioimaging21,
author={J. Vince Pulido and Sana Syed and Donald E. Brown},
title={CoMixMatch: Semi-supervised Detection of Pancreatic Cancer on Noisy, Gigapixel Histology Images},
booktitle={Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 2: BIOIMAGING},
year={2021},
pages={56-64},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010264100002865},
isbn={978-989-758-490-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 2: BIOIMAGING
TI - CoMixMatch: Semi-supervised Detection of Pancreatic Cancer on Noisy, Gigapixel Histology Images
SN - 978-989-758-490-9
AU - Pulido J.
AU - Syed S.
AU - Brown D.
PY - 2021
SP - 56
EP - 64
DO - 10.5220/0010264100002865
PB - SciTePress