Visualizing the Invisible: Enhancing Radiologist Performance in Breast Mammography via Task-Driven Chromatic Encoding

2026-02-07

AI Summary

This study addresses the limited sensitivity of mammography in dense breasts, where lesion detection is hindered by tissue overlap and subtle radiographic appearances. To overcome this challenge, the authors propose MammoColor, a novel framework that introduces task-driven color encoding (TDCE)—a mechanism that transforms single-channel mammograms into enhanced, colorized visualizations optimized for BI-RADS classification. The lightweight TDCE module is jointly trained end-to-end with a classifier, yielding improved diagnostic performance. On the VinDr-Mammo dataset, the method increases the AUC from 0.7669 to 0.8461, with even greater gains observed in dense breast cases. Multi-reader evaluation demonstrates a high specificity of 0.96 while maintaining stable sensitivity, effectively enhancing lesion conspicuity and reducing false-positive recall rates.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Purpose:Mammography screening is less sensitive in dense breasts, where tissue overlap and subtle findings increase perceptual difficulty. We present MammoColor, an end-to-end framework with a Task-Driven Chromatic Encoding (TDCE) module that converts single-channel mammograms into TDCE-encoded views for visual augmentation. Materials and Methods:MammoColor couples a lightweight TDCE module with a BI-RADS triage classifier and was trained end-to-end on VinDr-Mammo. Performance was evaluated on an internal test set, two public datasets (CBIS-DDSM and INBreast), and three external clinical cohorts. We also conducted a multi-reader, multi-case (MRMC) observer study with a washout period, comparing (1) grayscale-only, (2) TDCE-only, and (3) side-by-side grayscale+TDCE. Results:On VinDr-Mammo, MammoColor improved AUC from 0.7669 to 0.8461 (P=0.004). Gains were larger in dense breasts (AUC 0.749 to 0.835). In the MRMC study, TDCE-encoded images improved specificity (0.90 to 0.96; P=0.052) with comparable sensitivity. Conclusion:TDCE provides a task-optimized chromatic representation that may improve perceptual salience and reduce false-positive recalls in mammography triage.

Problem

• mammography
• dense breasts
• perceptual difficulty
• false-positive recalls
• visual augmentation

Innovation

• Task-Driven Chromatic Encoding
• MammoColor
• mammography triage
• visual augmentation
• dense breast imaging