Multiparametric MRI-derived radiomic signatures enable noninvasive prediction of HER2 expression in bladder cancer
International Urology and Nephrology · 03.07.2026 · 58 (12) · 5203-5213
DOI: 10.1007/s11255-026-05256-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Urology and Nephrology, online erschienen am 03.07.2026. Verfasst von Yali Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Nanjing Medical University, Nanjing, 211166, China. Hauptthemen laut MEDLINE: Erb-b2 Receptor Tyrosine Kinases, Multiparametric Magnetic Resonance Imaging, Urinary Bladder Neoplasms. Die Arbeit nennt 23 Literaturangaben. Gefördert von: the Jiangsu Provincial Key Discipline and Laboratory Construction Funds of Urology, the National Clinical Key Discipline Construction Funds.
Abstract (Originalsprache)
OBJECTIVE: To assess the value of multiparametric MRI (mpMRI)-derived radiomic signatures and a combined model for non-invasive prediction of human epidermal growth factor receptor 2 (HER2) expression in bladder cancer (BCa). METHODS: A total of 113 BCa patients with preoperative pelvic mpMRI were retrospectively enrolled. Radiomic features were extracted from T2WI, DWI, DCE and their combinations. Five machine learning algorithms were used to construct radiomic models. A combined model and a nomogram were developed by integrating radiomic signatures and clinicoradiological variables. RESULTS: The T2WI + DWI + DCE-based RandomForest model achieved the best performance, with an AUC of 0.877 in the training cohort and 0.754 in the validation cohort. Age, risk group, and maximum tumor diameter were independent predictors of HER2 overexpression. The combined model yielded AUCs of 0.808 and 0.870 in the training and validation cohorts, respectively. CONCLUSION: mpMRI radiomics can non-invasively predict HER2 expression in BCa. The combined nomogram shows good clinical utility, supporting personalized treatment planning for BCa patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Nanjing Medical University, Nanjing, 211166, China.
- Department of Urology, Affiliated Zhongda Hospital of Southeast University, No. 87Dingjiaqiao, Gulou District, Nanjing, 210009, China.
- Southeast University School of Medicine, Nanjing, 210003, China.
- Department of Urology, Nanjing Lishui District People's Hospital, Zhongda Hospital Lishui Branch of Southeast University, No.86 Chongwen Road, Yong Yang Street, Lishui District, Nanjing, 211200, China.
- Department of Urology, Nanjing Lishui District People's Hospital, Zhongda Hospital Lishui Branch of Southeast University, No.86 Chongwen Road, Yong Yang Street, Lishui District, Nanjing, 211200, China. lishumy03@163.com.
- Department of Urology, Affiliated Zhongda Hospital of Southeast University, No. 87Dingjiaqiao, Gulou District, Nanjing, 210009, China. maoweipu88@163.com.
Förderung
- the Jiangsu Provincial Key Discipline and Laboratory Construction Funds of Urology
- the National Clinical Key Discipline Construction Funds
Zitieren
APA
Wang, Y., Zhao, T., Liang, B., Zhen, L., Ding, Y., Jiang, Y., Wu, J., Meng, Y., Mao, W., & Chen, M. (2026). Multiparametric MRI-derived radiomic signatures enable noninvasive prediction of HER2 expression in bladder cancer. International Urology and Nephrology, 58(12), 5203-5213. https://doi.org/10.1007/s11255-026-05256-4
Vancouver
Wang Y, Zhao T, Liang B, Zhen L, Ding Y, Jiang Y, et al. Multiparametric MRI-derived radiomic signatures enable noninvasive prediction of HER2 expression in bladder cancer. International Urology and Nephrology. 2026;58(12):5203-5213. doi:10.1007/s11255-026-05256-4
BibTeX
@article{Wang2026,
author = {Wang, Yali and Zhao, Tonglei and Liang, Baotai and Zhen, Lan and Ding, Yiming and Jiang, Yanji and Wu, Jianping and Meng, Yuan and Mao, Weipu and Chen, Ming},
title = {Multiparametric MRI-derived radiomic signatures enable noninvasive prediction of HER2 expression in bladder cancer},
journal = {International Urology and Nephrology},
year = {2026},
volume = {58},
number = {12},
pages = {5203--5213},
doi = {10.1007/s11255-026-05256-4}
}
EUVIMED