Preoperative prediction of lymphatic metastasis in rectal cancer using a fusion model based on multiparameter magnetic resonance imaging: a retrospective validation study - Takeaways - MDSpire

Preoperative prediction of lymphatic metastasis in rectal cancer using a fusion model based on multiparameter magnetic resonance imaging: a retrospective validation study

  • By

  • Peng Zheng

  • Donghao Xu

  • Kaiwen Chen

  • Zhekun Huang

  • Ziqi Zhang

  • Songbin Lin

  • May 22, 2026

  • 0 min

Share

  • 1

    The study validated an MRI-based deep learning algorithm for predicting lymphatic metastasis in rectal cancer using a retrospective cohort.

  • 2

    The integrated fusion model combining imaging and clinical factors improved preoperative diagnostic performance with an AUC of 0.873.

  • 3

    Independent risk factors for lymph node metastasis identified were carcinoembryonic antigen level >5 µg/L and poor differentiation.

  • 4

    The fusion model demonstrated promising diagnostic efficacy in an external validation cohort with an AUC of 0.838.

  • 5

    This model enhances N-staging accuracy and aids in personalized treatment decisions, reducing interobserver variability.

Original Source(s)

Preoperative prediction of lymphatic metastasis in rectal cancer using a fusion model based on multiparameter magnetic resonance imaging: a retrospective validation study

  • by Peng Zheng, Donghao Xu, Kaiwen Chen, Zhekun Huang, Ziqi Zhang, Songbin Lin

  • May 22, 2026

Related Content

Differentiation of hepatocellular carcinoma from hepatic hemangioma using diffusion-derived vessel density map-based radiomics features

Retraction: MicroRNA-935 directly targets FZD6 to inhibit the proliferation of human glioblastoma and correlate to glioma malignancy and prognosis

  • May 28, 2026

Recurrent IDH-mutant astrocytoma WHO grade 4 diagnosed during pregnancy: case report with literature review