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

TL;DR

This study introduces a multi-tiered self-contrastive framework (Local-MWR, Regional-MWR, Global-MWR) whose outputs are fused by Joint-MWR for breast cancer detection using microwave radiometry. On a dataset of 4,932 female cases, the J-MWR model achieves a high MCC of $0.74 \\pm \\ 0.018$, with accuracy $0.95 \\pm \\ 0.003$ and ROC AUC $0.96 \\pm \\ 0.001$, outperforming the base and single-tier variants. The approach emphasizes intra-case contrasts and region-aware comparisons, showing robustness to data augmentation and favorable generalization, while offering insights into embedding spaces and batch-size effects. These findings suggest self-contrastive learning as a promising direction for MWR-based breast cancer screening and support further exploration toward point-of-care, multi-modal extensions and automated architecture design.

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.

Figures (8)

• Figure 1: Overview of the proposed self-contrastive models for breast cancer detection. 1) A microwave radiometry (MWR) device, MWR-2020, is used to capture skin and internal temperatures at 2) predetermined locations on the breasts. 3) The data is processed through three hierarchical levels of supervised self-contrastive models: Local-MWR (L-MWR) compares individual temperature points, Regional-MWR (R-MWR) compares temperature features between the left and right breasts, and Global-MWR (G-MWR) compares features of both breasts with their inverted counterparts. 4) The outputs from these pre-trained models are aggregated and fine-tuned using a meta-classifier, Joint-MWR (J-MWR).
• Figure 2: An illustration of the skin and internal acquisition points on the breasts. Point 0 represents the nipple, points 1–8 are arranged equidistantly around the nipple, point 9 corresponds to the axillary region, and reference points T1 and T2 are located beneath the chest.
• Figure 3: Comparison of internal breast temperature profiles between a healthy case (Panel A) and a high-growth-rate cancerous case (Panel B). In the healthy case, temperature profiles exhibit no significant asymmetries. On the other hand, in the cancerous case, elevated temperatures are observed in regions 1 and 8 of the right gland, indicating localized abnormalities.
• Figure 4: Overview of the proposed multi-tiered self-contrastive MWR models for breast cancer detection. A) The shared MWR-Block, a common residual block used across all networks. B) L-MWR network, which performs point-to-point comparisons within each breast. C) R-MWR network, which conducts comparisons between the left and right breasts. D) G-MWR network, which compares each breast with its positional inverse counterpart. E) J-MWR network, which integrates predictions from L-MWR, R-MWR, and G-MWR to produce the final prediction.
• Figure 5: Uniform Manifold Approximation and Projection (UMAP) mcinnes2018umap visualizations of the embedding spaces generated by (a) L-MWR, (b) R-MWR, (c) G-MWR, and (d) base contrastive models. In each plot, blue circles represent correct healthy predictions, yellow squares denote correct cancerous predictions, and red crosses overlaid on these markers indicate incorrect predictions.