A Density-Informed Multimodal Artificial Intelligence Framework for Improving Breast Cancer Detection Across All Breast Densities

2025-10-16

AI Summary

Mammography exhibits significantly reduced sensitivity in dense breasts, increasing the risk of missed diagnoses. To address this, we propose a breast density–driven multimodal AI framework that adaptively fuses mammography-based AI and thermography-based AI (Thermalytix), dynamically selecting the optimal imaging modality and model pathway based on individual breast density. Methodologically, the framework employs multi-view deep learning for mammographic analysis and introduces vasculo-thermal radiomics to model thermographic data, yielding an interpretable, lightweight decision system. Its key innovation lies in the first use of breast density as the central guiding variable for modality selection and model fusion—balancing high performance, broad applicability, and low-cost deployment. Experimental results demonstrate superior performance: 94.55% sensitivity and 79.93% specificity—significantly outperforming single-modality baselines—while maintaining robust detection rates across both dense and fatty breast types.

Technology Category

Computer Vision: Multi-modal VisionIntelligent Robots: Multimodal Perception & Sensor FusionMachine Learning: Multimodal Learning

Application Category

Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Mammography, the current standard for breast cancer screening, has reduced sensitivity in women with dense breast tissue, contributing to missed or delayed diagnoses. Thermalytix, an AI-based thermal imaging modality, captures functional vascular and metabolic cues that may complement mammographic structural data. This study investigates whether a breast density-informed multi-modal AI framework can improve cancer detection by dynamically selecting the appropriate imaging modality based on breast tissue composition. A total of 324 women underwent both mammography and thermal imaging. Mammography images were analyzed using a multi-view deep learning model, while Thermalytix assessed thermal images through vascular and thermal radiomics. The proposed framework utilized Mammography AI for fatty breasts and Thermalytix AI for dense breasts, optimizing predictions based on tissue type. This multi-modal AI framework achieved a sensitivity of 94.55% (95% CI: 88.54-100) and specificity of 79.93% (95% CI: 75.14-84.71), outperforming standalone mammography AI (sensitivity 81.82%, specificity 86.25%) and Thermalytix AI (sensitivity 92.73%, specificity 75.46%). Importantly, the sensitivity of Mammography dropped significantly in dense breasts (67.86%) versus fatty breasts (96.30%), whereas Thermalytix AI maintained high and consistent sensitivity in both (92.59% and 92.86%, respectively). This demonstrates that a density-informed multi-modal AI framework can overcome key limitations of unimodal screening and deliver high performance across diverse breast compositions. The proposed framework is interpretable, low-cost, and easily deployable, offering a practical path to improving breast cancer screening outcomes in both high-resource and resource-limited settings.

Problem

• Improving breast cancer detection sensitivity in dense breast tissue
• Combining mammography and thermal imaging with AI modality selection
• Overcoming limitations of unimodal screening across diverse breast densities

Innovation

• Dynamic modality selection based on breast density
• Multi-modal AI combining mammography and thermal imaging
• Optimizing predictions through tissue-type-specific AI models