Improving Uncertainty Estimations for Mammogram Classification Using Semi-Supervised Learning

Calderon-Ramırez, Saul; Murillo-Hernandez, Diego; Rojas-Salazar, Kevin; Calvo-Valverde, Luis-Alexander; Yang, Shengxiang; Moemeni, Armaghan; Elizondo, David; Lopez-Rubio, Ezequiel; Molina-Cabello, Miguel

Abstract

Computer aided diagnosis for mammogram images have seen positive results through the usage of deep learning architectures. However, limited sample sizes for the target datasets might prevent the usage of a deep learning model under real world scenarios. The usage of unlabeled data to improve the accuracy of the model can be an approach to tackle the lack of target data. Moreover, important model attributes for the medical domain as model uncertainty might be improved through the usage of unlabeled data. Therefore, in this work we explore the impact of using unlabeled data through the implementation of a recent approach known as MixMatch, for mammogram images. We evaluate the improvement on accuracy and uncertainty of the model using popular and simple approaches to estimate uncertainty. For this aim, we propose the usage of the uncertainty balanced accuracy metric.

Citation

Calderon-Ramırez, S., Murillo-Hernandez, D., Rojas-Salazar, K., Calvo-Valverde, L.-A., Yang, S., Moemeni, A., …Molina-Cabello, M. (2021). Improving Uncertainty Estimations for Mammogram Classification Using Semi-Supervised Learning. . https://doi.org/10.1109/IJCNN52387.2021.9533719

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: International Joint Conference on Neural Networks (IJCNN 2021)
• Start Date: Jul 18, 2021
• End Date: Jul 22, 2021
• Acceptance Date: Apr 10, 2021
• Online Publication Date: Sep 20, 2021
• Publication Date: Jul 18, 2021
• Deposit Date: May 13, 2021
• Publicly Available Date: Jul 18, 2021
• Publisher: Institute of Electrical and Electronics Engineers
• DOI: https://doi.org/10.1109/IJCNN52387.2021.9533719
• Keywords: Uncertainty Estimation, Breast Cancer, Mammogram, Semi-Supervised Deep Learning, MixMatch
• Public URL: https://nottingham-repository.worktribe.com/output/5526167
• Publisher URL: https://ieeexplore.ieee.org/document/9533719
• Related Public URLs: https://www.ijcnn.org/
• Additional Information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.