DensiThAI, A Multi-View Deep Learning Framework for Breast Density Estimation using Infrared Images

2026-01-29

AI Summary

Current breast density assessment relies on X-ray mammography, which involves ionizing radiation and lacks a safe, radiation-free alternative. This study proposes the first end-to-end deep learning framework based on multi-view infrared thermography to classify breast density without radiation, leveraging differences in surface temperature distributions. The model is trained under supervision using mammographic annotations as the gold standard. Evaluated on a multicenter dataset comprising 3,500 women, the five-view fusion model achieves an average AUROC of 0.73, with statistically significant performance differences across density categories (p ≪ 0.05). Moreover, the model demonstrates consistent performance across age groups, confirming the feasibility and potential of radiation-free breast density assessment through infrared thermography.

Technology Category

Machine Learning: Multi-instance/Multi-view LearningComputer Vision: Multi-modal VisionReasoning under Uncertainty: Graphical Models

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingSecurity and Privacy: Large-scale security measurements

Abstract

Breast tissue density is a key biomarker of breast cancer risk and a major factor affecting mammographic sensitivity. However, density assessment currently relies almost exclusively on X-ray mammography, an ionizing imaging modality. This study investigates the feasibility of estimating breast density using artificial intelligence over infrared thermal images, offering a non-ionizing imaging approach. The underlying hypothesis is that fibroglandular and adipose tissues exhibit distinct thermophysical and physiological properties, leading to subtle but spatially coherent temperature variations on the breast surface. In this paper, we propose DensiThAI, a multi-view deep learning framework for breast density classification from thermal images. The framework was evaluated on a multi-center dataset of 3,500 women using mammography-derived density labels as reference. Using five standard thermal views, DensiThAI achieved a mean AUROC of 0.73 across 10 random splits, with statistically significant separation between density classes across all splits (p<<0.05). Consistent performance across age cohorts supports the potential of thermal imaging as a non-ionizing approach for breast density assessment with implications for improved patient experience and workflow optimization.

Problem

• breast density estimation
• infrared thermal imaging
• non-ionizing imaging
• breast cancer risk
• mammographic sensitivity

Innovation

• infrared thermography
• breast density estimation
• multi-view deep learning
• non-ionizing imaging
• DensiThAI