Modern Backbones Improve Multi-task DETR for Mammography Classification and Lesion Localization

📅 2026-08-10
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the joint optimization of exam-level malignancy prediction and lesion localization in mammography. The authors propose a unified multi-task DETR-based framework that leverages shared features to simultaneously perform image-level classification and region-level localization. For the first time, they systematically evaluate the performance of various modern vision backbones—including ConvNeXtV2, DINOv3, and MambaVision—on this dual objective. Experimental results demonstrate that advanced backbones substantially outperform conventional ResNet architectures: on the OPTIMAM dataset, ConvNeXtV2 achieves 97.96% AUC and 25.08% mAP@.5, while on SGM1k, DINOv3 attains 90.97% AUC and 27.04% mAP@.5, underscoring the critical influence of backbone architecture on multi-task performance in mammographic analysis.
📝 Abstract
Joint exam-level prediction and candidate-region localization may improve the usefulness of AI support in mammography. We study this setting using a multi-task DETR framework, where shared representations support both image-level malignancy prediction and lesion localization, and evaluate its performance on OPTIMAM and a biopsy-confirmed SGM1k cohort. Across both datasets, modern backbones consistently outperformed older ResNet-style features, with ConvNeXtV2 and DINOv3 giving the strongest overall results, whereas MambaVision was less competitive. On OPTIMAM, ConvNeXtV2 achieved the best overall performance, reaching 97.96% AUC, 99.89% sensitivity, 25.08% mAP@.5, and 74.38% recall@.25. On SGM1k, DINOv3 gave the strongest overall results, with 90.97% AUC, 86.28% sensitivity, 82.00% specificity, 27.04% mAP@.5, and 77.32% recall@.25. These findings suggest that backbone quality is a critical factor in effective multi-task mammography, with ConvNeXtV2 emerging as a particularly strong and well-matched CNN backbone for mammography in this framework.
Problem

Research questions and friction points this paper is trying to address.

mammography
multi-task learning
lesion localization
malignancy prediction
AI-assisted diagnosis
Innovation

Methods, ideas, or system contributions that make the work stand out.

multi-task DETR
modern backbones
mammography
lesion localization
ConvNeXtV2
💼 Related Jobs
No related jobs found.
D
Dinh Tan Nguyen
University of Technology Sydney, Australia.
Q
Quang-Hien Kha
Saigon Precision Medicine Research Center, Vietnam.
L
Le-Hoang Nguyen
College of Medicine, Taipei Medical University, Taiwan.
M
Minh-Toan Dinh
International Graduate Program in Artificial Intelligence, National Central University, Taiwan.
X
Xuan-Huy Nguyen
Saigon Precision Medicine Research Center, Vietnam.
D
Dac Phu Ho
University of Technology Sydney, Australia.
C
Cao Truong Tran
Le Qui Don Technical University, Vietnam.
S
Sai Ho Ling
University of Technology Sydney, Australia.
L
Lan T Ho-Pham
College of Medicine, Taipei Medical University, Taiwan.
L
Liem Pham
Saigon Precision Medicine Research Center, Vietnam.
N
Nguyen Quoc Khanh Le
College of Medicine, Taipei Medical University, Taiwan.