Habitat-Radiomics combining multichannel 2.5D deep learning for differentiating adrenal adenomas from metastases using automatic segmentation: a multicenter study - Summary - MDSpire

Habitat-Radiomics combining multichannel 2.5D deep learning for differentiating adrenal adenomas from metastases using automatic segmentation: a multicenter study

  • By

  • shengnan, Yin

  • Ning, Ding

  • Chuqi, Yang

  • Shaocai, Wang

  • Mengjuan, Li

  • Ji, Yiding

  • Tong, Liu

  • Long, Jin

  • May 27, 2026

  • 0 min

Share

Objective:

To develop a model for the automated segmentation and differentiation of lipid-poor adrenal adenomas from metastatic lesions.

Approach:
    Key Findings:
    • The fusion model achieved AUCs of 0.983, 0.913, and 0.886 in training, internal validation, and external test sets, respectively.
    • Standalone 2.5D deep learning and habitat-radiomics models showed AUCs ranging from 0.830–0.945 and 0.825–0.970, respectively.
    Interpretation:

    Conclusion:

Original Source(s)

Habitat-Radiomics combining multichannel 2.5D deep learning for differentiating adrenal adenomas from metastases using automatic segmentation: a multicenter study

  • by shengnan, Yin , Ning, Ding , Chuqi, Yang , Shaocai, Wang , Mengjuan, Li , Ji, Yiding , Tong, Liu , Long, Jin

  • May 27, 2026

Related Content

POU2F3-positive small cell neuroendocrine carcinoma of the urinary tract: a clinicopathological analysis of five cases

L-arginine metabolism in breast cancer: mechanisms and therapeutic targets

Nucleo-mitochondrial asymmetry profiles the proliferative engine and spatial niche reconstruction in clear cell renal cell carcinoma