DataVXAdvanced SciencePaper
journal article·2026-02Open access

MR‐DELTAnet: A Longitudinal MRI‐Transformer Model Predicting Pathological Complete Response and Revealing Immune Microenvironment via scRNA‐seq in Locally Advanced Rectal Cancer

Wuteng Cao, Huaxian Chen, Jiao Li, Yihui Zheng, Liqing Xie, Guozhong Xiao, Zeyan Wang, Fen Yuan, Junhong Chen, Chongbao Sun, Jing Dai, Jinping Zeng, Xinhua Wang, Lei Wu, Hongcheng Lin

Advanced Science· Volume 13· Issue 11
Publisher pageOpen full text
Source abstract

Abstract

Abstract Accurate tumor response assessment to neoadjuvant chemoradiotherapy (NCRT) is crucial for personalized treatment strategies in locally advanced rectal cancer (LARC). However, reliable non‐invasive assessment tool remains clinically lacking. To fill this unmet need, MR‐DELTAnet, a longitudinal MRI‐based Transformer framework that integrates Delta‐Efficient Latent‐Temporal Attention, is constructed to predict pathological complete response (pCR) to NCRT in locally advanced rectal cancer patients. In a multicenter retrospective cohort of 1,026 LARC patients between July 2012 and July 2023, MR‐DELTAnet demonstrated robust discriminative performance across independent datasets, with the area under the curves (AUC) of 0.93 (95% CI 0.90‐0.96), 0.88 (95% CI 0.82‐0.94) and 0.90 (95% CI 0.79‐1.00) and in training (n═633), internal validation (n═212) and external validation (n═181) sets, respectively. Risk‐stratification by MR‐DELTAnet prediction scores reveals significant survival differences: low‐score patients exhibit prolonged disease‐free and overall survival versus high‐score patients (log‐rank p <0.05). Applying the model to an independent single‐cell RNA sequencing cohort (n═26) discloses biologically distinct immune microenvironments: high‐score tumors are myeloid‐rich and immunosuppressive, whereas low‐score tumors harbor cytotoxic T‐cell‐dominant. Clinically, MR‐DELTAnet provides an accurate, non‐invasive tool for preoperative identification of pCR likelihood and biological phenotype, thereby potentially informing individualized treatment strategies for LARC management.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Single-cell and spatial transcriptomics · Ferroptosis and cancer prognosis · Cancer Immunotherapy and Biomarkers

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Radiology, The Sixth Affiliated Hospital Sun Yat‐sen University No.26, Yuancun Er Heng Road, Tianhe District Guangzhou Guangdong 510655 China

Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Guangdong Research Institute of Gastroenterology, The Sixth Affiliated Hospital Sun Yat‐sen University No.26, Yuancun Er Heng Road, Tianhe District Guangzhou Guangdong 510655 China

Biomedical Innovation Center, The Sixth Affiliated Hospital Sun Yat‐sen University No.26, Yuancun Er Heng Road, Tianhe District Guangzhou Guangdong 510655 China

Department of Coloproctology, The Sixth Affiliated Hospital Sun Yat‐sen University No.26, Yuancun Er Heng Road, Tianhe District Guangzhou Guangdong 510655 China

Department of Radiology Longyan First Affiliated Hospital of Fujian Medical University No.105, Jiuyi North Road, Xinluo District Longyan City Fujian 364028 China

Department of Radiology Zhongshan City People's Hospital No.2 Sunwen East Road Zhongshan City Guangdong 528403 China

Department of Radiology Jiangsu Provincial Hospital of Chinese Medicine No.155 Hanzhong Road, Qinhuai District Nanjing JiangSu 210029 China

BGI Research No. 9 Yunhua Road, Meisha Street, Yantian District Shenzhen Guangdong 518085 China

Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University No.106, Zhongshan 2nd Road Guangzhou Guangdong 510080 China

Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application No.106, Zhongshan 2nd Road Guangzhou Guangdong 510080 China

Funding

Science Fund for Distinguished Young Scholars of Guangdong Province · National Natural Science Foundation of China

References (31)

Show source-provided references
1. 10.1001/jamaoncol.2018.589610.1001/jamaoncol.2018.5896 ↗
2. 10.1016/S2468-1253(17)30074-210.1016/S2468-1253(17)30074-2 ↗
3. 10.1148/radiol.232202132610.1148/radiol.2322021326 ↗
4. 10.1200/JCO.2011.34.906810.1200/JCO.2011.34.9068 ↗
5. 10.1097/DCR.000000000000066710.1097/DCR.0000000000000667 ↗
6. 10.1007/s00330-019-06565-210.1007/s00330-019-06565-2 ↗
7. 10.1148/radiol.252108120010.1148/radiol.2521081200 ↗
8. 10.1016/j.crad.2011.11.00410.1016/j.crad.2011.11.004 ↗
9. 10.1148/radiol.22222310.1148/radiol.222223 ↗
10. 10.1016/j.ejca.2021.07.01210.1016/j.ejca.2021.07.012 ↗
11. 10.1038/s41698-024-00516-x10.1038/s41698-024-00516-x ↗
12. 10.1186/s12880-025-01844-510.1186/s12880-025-01844-5 ↗
13. 10.1016/j.eclinm.2023.10189910.1016/j.eclinm.2023.101899 ↗
14. 10.1186/s13014-024-02574-810.1186/s13014-024-02574-8 ↗
15. 10.1186/s12967-023-04004-x10.1186/s12967-023-04004-x ↗
16. 10.1109/TPAMI.2021.305556410.1109/TPAMI.2021.3055564 ↗
17. 10.1016/j.media.2022.10247010.1016/j.media.2022.102470 ↗
18. 10.1158/1078-0432.CCR-21-070610.1158/1078-0432.CCR-21-0706 ↗
19. 10.1148/radiol.22129110.1148/radiol.221291 ↗
20. 10.1093/brain/awab34010.1093/brain/awab340 ↗
21. 10.1148/radiol.21198610.1148/radiol.211986 ↗
22. 10.1007/s00330-022-09204-510.1007/s00330-022-09204-5 ↗
23. 10.1148/radiol.202019093610.1148/radiol.2020190936 ↗
24. 10.1007/s00330-024-11081-z10.1007/s00330-024-11081-z ↗
25. 10.1186/s13014-023-02352-y10.1186/s13014-023-02352-y ↗
26. 10.1109/TBME.2019.290902710.1109/TBME.2019.2909027 ↗
27. 10.1038/s41467-021-22188-y10.1038/s41467-021-22188-y ↗
28. 10.1016/j.pbiomolbio.2011.06.00610.1016/j.pbiomolbio.2011.06.006 ↗
29. 10.1148/radiol.202120361410.1148/radiol.2021203614 ↗
30. 10.1016/j.xcrm.2023.10123110.1016/j.xcrm.2023.101231 ↗
31. 10.3322/caac.2138810.3322/caac.21388 ↗