Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population

TL;DR

This study develops and validates a deep learning system for breast cancer detection in mammography, demonstrating high accuracy, robust lesion localization, and strong clinical acceptance across multiple datasets in the Thai population.

Contribution

Introduces a modified EfficientNetV2-based deep learning model with attention mechanisms, validated across diverse datasets, showing high diagnostic performance and clinical usability in Thai mammography screening.

Findings

AUROCs of 0.89, 0.96, and 0.94 on different datasets

83.5% and 84.0% concordance with radiologists in biopsy-confirmed cases

Average usability scores above 69 indicating good clinical acceptance

Abstract

This study presents a deep learning system for breast cancer detection in mammography, developed using a modified EfficientNetV2 architecture with enhanced attention mechanisms. The model was trained on mammograms from a major Thai medical center and validated on three distinct datasets: an in-domain test set (9,421 cases), a biopsy-confirmed set (883 cases), and an out-of-domain generalizability set (761 cases) collected from two different hospitals. For cancer detection, the model achieved AUROCs of 0.89, 0.96, and 0.94 on the respective datasets. The system's lesion localization capability, evaluated using metrics including Lesion Localization Fraction (LLF) and Non-Lesion Localization Fraction (NLF), demonstrated robust performance in identifying suspicious regions. Clinical validation through concordance tests showed strong agreement with radiologists: 83.5% classification and 84.0% localization concordance for biopsy-confirmed cases, and 78.1% classification and 79.6% localization concordance for out-of-domain cases. Expert radiologists' acceptance rate also averaged 96.7% for biopsy-confirmed cases, and 89.3% for out-of-domain cases. The system achieved a System Usability Scale score of 74.17 for source hospital, and 69.20 for validation hospitals, indicating good clinical acceptance. These results demonstrate the model's effectiveness in assisting mammogram interpretation, with the potential to enhance breast cancer screening workflows in clinical practice.