RST2G: Residual-Guided Spatiotemporal Transformer Graph Fusion Enhancement for Breast Cancer Segmentation in DCE-MRI
Cyborg and Bionic Systems · 01.01.2026 · 7
DOI: 10.34133/cbsystems.0502 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cyborg and Bionic Systems, online erschienen am 23.03.2026. Verfasst von Shaoli Xie und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thyroid and Breast Surgery, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan 637000, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Accurate segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for effective diagnosis, treatment planning, and monitoring of breast cancer. However, the high heterogeneity of tumor appearance and the complex spatiotemporal dynamics of contrast enhancement present critical challenges for existing segmentation methods. In this study, we propose a novel residual-guided spatiotemporal transformer with graph fusion enhancement (RST2G) framework for precise breast tumor segmentation in DCE-MRI. RST2G explicitly leverages pre-contrast MRI, post-contrast MRI, and their residual differences to capture rich inter-temporal kinetic information. Specifically, RST2G employs a weight-sharing hybrid encoder that combines convolutional neural networks and vision transformers to extract local and global features, followed by a residual-guided multi-scale refinement module to enhance feature discriminability. To effectively model spatial and temporal contextual dependencies, we construct modality-specific graphs and apply inter-slice and inter-temporal attention mechanisms for spatiotemporal graph enhancement. Extensive experiments on 2 publicly available breast DCE-MRI datasets demonstrate that RST2G significantly outperforms state-of-the-art 2-dimensional (2D), 3D, and 4D segmentation methods. Given its effectiveness in capturing complex spatiotemporal tumor characteristics for cancer annotation, RST2G has the potential to improve clinical breast cancer treatment.
Autor:innen und Institutionen
- Department of Thyroid and Breast Surgery, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan 637000, China.
- Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China.
- Department of Urology, Kidney and Urology Center, Pelvic Floor Disorders Center, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, Guangdong 518107, China.
- Department of Clinical Medicine, North Sichuan Medical College, Nanchong, Sichuan 637000, China.
- Department of Surgical Anesthesia, Suining Central Hospital, Suining, Sichuan 629000, China.
- Department of Orthopedics, Shenzhen Children's Hospital, Shenzhen, Guangdong 518000, China.
ORCID-Profile: Maoshan Chen
Zitieren
APA
Xie, S., Xu, L., Lei, C., Wang, J., Wang, J., Wang, Z., Sun, Y., Li, D., Li, F., Lin, R., Yang, H., Xiao, Y., Lv, T., Huang, Y., Hou, L., Li, J., & Chen, M. (2026). RST2G: Residual-Guided Spatiotemporal Transformer Graph Fusion Enhancement for Breast Cancer Segmentation in DCE-MRI. Cyborg and Bionic Systems, 7. https://doi.org/10.34133/cbsystems.0502
Vancouver
Xie S, Xu L, Lei C, Wang J, Wang J, Wang Z, et al. RST2G: Residual-Guided Spatiotemporal Transformer Graph Fusion Enhancement for Breast Cancer Segmentation in DCE-MRI. Cyborg and Bionic Systems. 2026;7. doi:10.34133/cbsystems.0502
BibTeX
@article{Xie2026,
author = {Xie, Shaoli and Xu, Lulu and Lei, Chenyi and Wang, Jinxiang and Wang, Jason and Wang, Zhibin and Sun, Yiran and Li, Danyi and Li, Fangfang and Lin, Rubing and Yang, Hongwei and Xiao, Yang and Lv, Tianxu and Huang, Yixuan and Hou, Lingmi and Li, Junyan and Chen, Maoshan},
title = {RST2G: Residual-Guided Spatiotemporal Transformer Graph Fusion Enhancement for Breast Cancer Segmentation in DCE-MRI},
journal = {Cyborg and Bionic Systems},
year = {2026},
volume = {7},
doi = {10.34133/cbsystems.0502}
}
EUVIMED