Multi-Tiered Self-Contrastive Learning for Medical Microwave Radiometry (MWR) Breast Cancer Detection

TL;DR

This paper presents a multi-tiered self-contrastive learning model for microwave radiometry that significantly improves breast cancer detection accuracy using a large patient dataset.

Contribution

Introduces a novel multi-tiered self-contrastive model for MWR, integrating local, regional, and global analyses to enhance diagnostic performance.

Findings

J-MWR achieves a Matthew's correlation coefficient of 0.74

Model outperforms existing neural networks and contrastive methods

Demonstrates potential for point-of-care breast cancer testing

Abstract

Improving breast cancer detection and monitoring techniques is a critical objective in healthcare, driving the need for innovative imaging technologies and diagnostic approaches. This study introduces a novel multi-tiered self-contrastive model tailored for microwave radiometry (MWR) in breast cancer detection. Our approach incorporates three distinct models: Local-MWR (L-MWR), Regional-MWR (R-MWR), and Global-MWR (G-MWR), designed to analyze varying sub-regional comparisons within the breasts. These models are integrated through the Joint-MWR (J-MWR) network, which leverages self-contrastive results at each analytical level to improve diagnostic accuracy. Utilizing a dataset of 4,932 female patients, our research demonstrates the efficacy of our proposed models. Notably, the J-MWR model achieves a Matthew's correlation coefficient of 0.74 $\pm$ 0.018, surpassing existing MWR neural networks and contrastive methods. These findings highlight the potential of self-contrastive learning techniques in improving the diagnostic accuracy and generalizability for MWR-based breast cancer detection. This advancement holds considerable promise for future investigations into enabling point-of-care testing. The source code is available at: https://github.com/cgalaz01/self_contrastive_mwr.