EUVIMEDEUVIMED entdecken
Multizentrische Studie

Multiparametric MRI-Based Integrated Analysis of Clinical, Radiomics, Deep Learning, and Machine Learning for Predicting Tumor Proliferation and Prognosis in Locally Advanced Rectal Cancer

Zhiheng Li, Huizhen Huang, Rongzhi Cai, Yangyang Qin, Zengxin Lu, Dandan Wang

Academic Radiology · 2026-06 · 33 (6) · 2466-2477

DOI: 10.1016/j.acra.2026.03.033 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Academic Radiology, 2026-06. Verfasst von Zhiheng Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The Shao xing People's Hospital, Shaoxing 312000, Zhejiang, China (Z.H.L., Z.X.L., D.W.). Hauptthemen laut MEDLINE: Rectal Neoplasms, Deep Learning, Multiparametric Magnetic Resonance Imaging, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Huimin Technology Research and Development Projects of Ningbo Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES This study aimed to develop and validate a predictive model integrating clinical, radiomics, deep learning (DL), and machine learning (ML) from multiparametric magnetic resonance imaging (MRI) for predicting tumor cell proliferation status and prognosis in patients with locally advanced rectal cancer (LARC). MATERIALS AND METHODS A total of 384 LARC patients from three centers (January 2016-August 2022) were retrospectively enrolled. Radiomics and DL features were extracted from multisequence MRI (T2WI, DWI, T1WI, and contrast-enhanced T1WI). Twelve ML algorithms across 107 combinations were used to construct models. The optimal algorithm combination for radiomics-DL (RDL) model construction was determined by the highest average area under the curve (AUC) across cohorts. The resulting predictive probability (RDL-score) was integrated with clinical risk features to construct a combined model, visualized as a nomogram. Model performance was evaluated using AUC, DeLong test, calibration curves, and decision curve analysis (DCA). The prognostic value of the nomogram for recurrence-free survival (RFS) was assessed by Kaplan-Meier analysis. RESULTS The Stepglm[both] + glmBoost combination achieved the highest predictive performance for tumor cell proliferation status. The nomogram integrating the RDL-score, maximal tumor thickness, and carcinoembryonic antigen (CEA) demonstrated excellent discrimination, with AUCs of 0.939, 0.884, and 0.895 in the training, internal validation, and external validation cohorts, respectively. Furthermore, the nomogram effectively stratified patients by RFS in all cohorts (all log-rank p < 0.01). CONCLUSION This multiparametric MRI-based nomogram integrating clinical data, radiomics, DL, and ML techniques demonstrated robust performance in predicting Ki-67 expression and stratifying prognosis in LARC patients, supporting personalized management in LARC. TAKE-HOME MESSAGE

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Rectal NeoplasmsDeep LearningMultiparametric Magnetic Resonance ImagingMachine LearningRadiomicsHumansPrognosisFemaleRetrospective StudiesMaleCell ProliferationMiddle AgedNomogramsAgedPredictive Learning Models

Stichwörter der Autor:innen

Deep learningKi-67Locally advanced rectal cancerMRIRadiomics

Autor:innen und Institutionen

  • Department of Radiology, The Shao xing People's Hospital, Shaoxing 312000, Zhejiang, China (Z.H.L., Z.X.L., D.W.).
  • Department of Radiology, Fudan University Shanghai Cancer Center Xiamen Hospital, Xiamen, Fujian, China (H.H.).
  • Department of Radiology, Cancer Hospital of Shantou University Medical College, Shantou, Guangdong, China (R.C.).
  • Department of Radiology, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China (Y.Q.).
  • Department of Radiology, The Shao xing People's Hospital, Shaoxing 312000, Zhejiang, China (Z.H.L., Z.X.L., D.W.). Electronic address: lzxwdd@163.com.

Förderung

  • Huimin Technology Research and Development Projects of Ningbo Municipality

Zitieren

APA

Li, Z., Huang, H., Cai, R., Qin, Y., Lu, Z., & Wang, D. (2026). Multiparametric MRI-Based Integrated Analysis of Clinical, Radiomics, Deep Learning, and Machine Learning for Predicting Tumor Proliferation and Prognosis in Locally Advanced Rectal Cancer. Academic Radiology, 33(6), 2466-2477. https://doi.org/10.1016/j.acra.2026.03.033

Vancouver

Li Z, Huang H, Cai R, Qin Y, Lu Z, Wang D. Multiparametric MRI-Based Integrated Analysis of Clinical, Radiomics, Deep Learning, and Machine Learning for Predicting Tumor Proliferation and Prognosis in Locally Advanced Rectal Cancer. Academic Radiology. 2026;33(6):2466-2477. doi:10.1016/j.acra.2026.03.033

BibTeX
@article{Li2026,
  author = {Li, Zhiheng and Huang, Huizhen and Cai, Rongzhi and Qin, Yangyang and Lu, Zengxin and Wang, Dandan},
  title = {Multiparametric MRI-Based Integrated Analysis of Clinical, Radiomics, Deep Learning, and Machine Learning for Predicting Tumor Proliferation and Prognosis in Locally Advanced Rectal Cancer},
  journal = {Academic Radiology},
  year = {2026},
  volume = {33},
  number = {6},
  pages = {2466--2477},
  doi = {10.1016/j.acra.2026.03.033}
}
Kostenlos starten →