EUVIMEDEUVIMED entdecken
Crossref

Radiologist-Informed Radiomics: Improving the Accuracy of Preoperative Assessment for Lymph Node Metastasis in Rectal Cancer

Chunl-Ong Fu, Long Zhou, Ze-Bin Yang, Kang-Fei Shan, Jiao-Jiao Xu, Zhen-Zhu Pang, Chi-Jun Ma, Jie-Ping Xu, Wei-Hua Zhu, Ji-Hong Sun, Fen-Hua Zhao

Academic Radiology · 2026-09 · 33 (9) · 3768-3779

DOI: 10.1016/j.acra.2026.06.017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2026-09. Verfasst von Chunl-Ong Fu und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang 322100, China (C.O.F., L.Z., Z.B.Y., K.F.S., J.J.X., Z.…. Hauptthemen laut MEDLINE: Radiomics, Lymphatic Metastasis, Rectal Neoplasms. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Jinhua City Science and Technology Bureau.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVE: The study aimed to develop and validate a multimodal radiomics model that integrates radiologist-informed feature augmentation leveraging expert-selected suspicious lymph nodes (LNs) based on ESGAR criteria to improve the accuracy of preoperative lymph node metastasis (LNM) prediction in patients with rectal cancer (RC). MATERIALS AND METHODS: This retrospective study included 563 eligible patients with RC. From each patient's high-resolution T2-weighted imaging (HRT2WI) and diffusion-weighted imaging (DWI) sequences, we extracted radiomic features from three distinct regions: the primary tumor, the entire mesorectal nodal region, and suspicious mesorectal nodes identified by radiologists. Clinical factors associated with LNM were identified through univariate and multivariate logistic regression analyses to establish a clinical prediction model. Finally, we constructed an integrated predictive model by combining these clinical factors with multimodal radiomic features, followed by a comprehensive comparison and evaluation of the predictive performance across all developed models. RESULTS: The integrated model, incorporating radiomic features derived from DWI sequences of the entire mesorectal nodal region and radiologist-annotated suspicious LNs, along with clinical factors, achieved optimal performance in predicting LNM. It yielded an area under the curve of 0.87 (95% confidence interval [CI]: 0.83-0.90) in the internal validation cohort and 0.83 (95% CI: 0.78-0.89) in the external validation cohort. CONCLUSION: Our findings show that the multimodal radiomics model integrating radiologists' prior knowledge offers potential for improving preoperative LNM assessment in RC, particularly in internal validation, and may provide supportive information for personalized treatment strategies in clinical practice. However, the incremental benefit of the radiologist-informed component was not consistently demonstrated in external validation, and further multi-center prospective studies are warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiomicsLymphatic MetastasisRectal NeoplasmsHumansFemaleRetrospective StudiesMiddle AgedMaleAgedPreoperative CareReproducibility of ResultsLymph NodesSensitivity and Specificity

Stichwörter der Autor:innen

Imaging histologyLymph node metastasisPredictive modelingPrior knowledgeRectal cancer

Autor:innen und Institutionen

  • Department of Radiology, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang 322100, China (C.O.F., L.Z., Z.B.Y., K.F.S., J.J.X., Z.Z.P., C.J.M., J.P.X., W.H.Z., F.H.Z.).
  • Department of Radiology, Sir Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310016, China (J.H.S.); Key Laboratory of Diagnosis and Treatment of Digestive System Tumors of Zhejiang Province, Ningbo 3150…
  • Department of Radiology, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang 322100, China (C.O.F., L.Z., Z.B.Y., K.F.S., J.J.X., Z.Z.P., C.J.M., J.P.X., W.H.Z., F.H.Z.). Electronic address: zhfenhua@16…

Förderung

  • Jinhua City Science and Technology Bureau

Zitieren

APA

Fu, C. O., Zhou, L., Yang, Z. B., Shan, K. F., Xu, J. J., Pang, Z. Z., Ma, C. J., Xu, J. P., Zhu, W. H., Sun, J. H., & Zhao, F. H. (2026). Radiologist-Informed Radiomics: Improving the Accuracy of Preoperative Assessment for Lymph Node Metastasis in Rectal Cancer. Academic Radiology, 33(9), 3768-3779. https://doi.org/10.1016/j.acra.2026.06.017

Vancouver

Fu CO, Zhou L, Yang ZB, Shan KF, Xu JJ, Pang ZZ, et al. Radiologist-Informed Radiomics: Improving the Accuracy of Preoperative Assessment for Lymph Node Metastasis in Rectal Cancer. Academic Radiology. 2026;33(9):3768-3779. doi:10.1016/j.acra.2026.06.017

BibTeX
@article{Fu2026,
  author = {Fu, Chunl-Ong and Zhou, Long and Yang, Ze-Bin and Shan, Kang-Fei and Xu, Jiao-Jiao and Pang, Zhen-Zhu and Ma, Chi-Jun and Xu, Jie-Ping and Zhu, Wei-Hua and Sun, Ji-Hong and Zhao, Fen-Hua},
  title = {Radiologist-Informed Radiomics: Improving the Accuracy of Preoperative Assessment for Lymph Node Metastasis in Rectal Cancer},
  journal = {Academic Radiology},
  year = {2026},
  volume = {33},
  number = {9},
  pages = {3768--3779},
  doi = {10.1016/j.acra.2026.06.017}
}
Kostenlos starten →