Deep Learning–driven Segmentation of Breast Cancer MR Imaging Using a Hybrid ResNet–Transformer Architecture and Cross-dataset Validation
Abstract
PURPOSE: To develop and cross-dataset validate a hybrid ResNet50-Transformer U-Net for automated segmentation of breast cancer (BC) lesions on 2D dynamic contrast-enhanced MRI (DCE-MRI). METHODS: A total of 20434 BC MRI images from the BC MRI Segmentation Benchmark (BC-MRI-SEG), comprising 4 independent public datasets, were included. A strict patient-level data splitting strategy was applied to avoid data leakage. The proposed model was based on a U-Net architecture integrating a ResNet50 encoder for local feature extraction and a bottleneck Transformer module for global contextual modeling. Model performance was evaluated using a leave-one-dataset-out cross-dataset external validation strategy. Segmentation performance was assessed using the Dice similarity coefficient (DSC), intersection over union (IoU), 95% Hausdorff distance (HD95), sensitivity, and precision. RESULTS: The proposed hybrid model achieved stable segmentation performance across the evaluated datasets. In leave-one-dataset-out external validation, patient-level DSC ranged from 0.75 ± 0.13 to 0.79 ± 0.10, while IoU ranged from 0.61 ± 0.15 to 0.66 ± 0.12. In the fixed held-out comparison cohort, the proposed model achieved a DSC of 0.82 ± 0.08 and an IoU of 0.70 ± 0.10 and outperformed the evaluated baseline models (Holm-adjusted P ≤ 0.021). Qualitative analysis showed generally close agreement between the predicted masks and reference annotations across lesions with different morphologic appearances. CONCLUSION: The proposed ResNet-Transformer-based U-Net framework provided a robust approach for automated BC MRI segmentation across heterogeneous public datasets. These findings suggest that combining local feature extraction with global contextual modeling may be useful for computer-assisted breast MRI analysis and related clinical workflows.
Related
- Convolutional, State-Space and Transformer Liver-Tumor Segmentation Models Trained on Hepatocellular Carcinoma Fail on the Same External Cases: Lesion Size Outweighs Architecture in Cross-Dataset Generalization
- Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
- Quantitative super-resolution imaging with deep learning segmentation reveals early mitochondrial network remodeling and altered mitochondria-lysosome interactions in Pompe disease muscle
- HemaViT: transformer-based deep learning for automated non-invasive anemia detection using conjunctival imaging
- YOLO-LS: a novel deep learning framework for brain tumor segmentation in Magnetic Resonance Imaging
BibTeX
@article{sui2026deep,
title = {{Deep Learning–driven Segmentation of Breast Cancer MR Imaging Using a Hybrid ResNet–Transformer Architecture and Cross-dataset Validation}},
author = {Yongjian Sui and Peiru Li and Jiacheng Li and Peng Zhou and Xiaolong Zheng},
journal = {Magnetic Resonance in Medical Sciences},
year = {2026},
month = oct,
doi = {10.2463/mrms.mp.2026-0099},
url = {https://www.jstage.jst.go.jp/article/mrms/25/4/25_mp.2026-0099/_article},
note = {CC BY},
}
RIS
TY - JOUR
TI - Deep Learning–driven Segmentation of Breast Cancer MR Imaging Using a Hybrid ResNet–Transformer Architecture and Cross-dataset Validation
AU - Yongjian Sui
AU - Peiru Li
AU - Jiacheng Li
AU - Peng Zhou
AU - Xiaolong Zheng
PY - 2026
DA - 2026/10/08
JO - Magnetic Resonance in Medical Sciences
DO - 10.2463/mrms.mp.2026-0099
UR - https://www.jstage.jst.go.jp/article/mrms/25/4/25_mp.2026-0099/_article
AB - PURPOSE: To develop and cross-dataset validate a hybrid ResNet50-Transformer U-Net for automated segmentation of breast cancer (BC) lesions on 2D dynamic contrast-enhanced MRI (DCE-MRI). METHODS: A total of 20434 BC MRI images from the BC MRI Segmentation Benchmark (BC-MRI-SEG), comprising 4 independent public datasets, were included. A strict patient-level data splitting strategy was applied to avoid data leakage. The proposed model was based on a U-Net architecture integrating a ResNet50 encoder for local feature extraction and a bottleneck Transformer module for global contextual modeling. Model performance was evaluated using a leave-one-dataset-out cross-dataset external validation strategy. Segmentation performance was assessed using the Dice similarity coefficient (DSC), intersection over union (IoU), 95% Hausdorff distance (HD95), sensitivity, and precision. RESULTS: The proposed hybrid model achieved stable segmentation performance across the evaluated datasets. In leave-one-dataset-out external validation, patient-level DSC ranged from 0.75 ± 0.13 to 0.79 ± 0.10, while IoU ranged from 0.61 ± 0.15 to 0.66 ± 0.12. In the fixed held-out comparison cohort, the proposed model achieved a DSC of 0.82 ± 0.08 and an IoU of 0.70 ± 0.10 and outperformed the evaluated baseline models (Holm-adjusted P ≤ 0.021). Qualitative analysis showed generally close agreement between the predicted masks and reference annotations across lesions with different morphologic appearances. CONCLUSION: The proposed ResNet-Transformer-based U-Net framework provided a robust approach for automated BC MRI segmentation across heterogeneous public datasets. These findings suggest that combining local feature extraction with global contextual modeling may be useful for computer-assisted breast MRI analysis and related clinical workflows.
SN - 1880-2206
SN - 1347-3182
ER -