The predictive value of 18F-FDG PET/CT habitat radiomics combined model in evaluating EGFR gene mutations in lung adenocarcinoma - Takeaways - MDSpire

The predictive value of 18F-FDG PET/CT habitat radiomics combined model in evaluating EGFR gene mutations in lung adenocarcinoma

  • By

  • Lai, Ruihe

  • Sheng, Dandan

  • Geng, Yuzhi

  • Yang, Ding Chong

  • Tan, Qianqian

  • Zhao, Lianjun

  • May 28, 2026

  • 0 min

Share

  • 1

    This study evaluated the effectiveness of 18F-FDG PET/CT radiomics in predicting EGFR mutation status in lung adenocarcinoma.

  • 2

    A total of 724 patients were analyzed using machine learning algorithms to develop various predictive models.

  • 3

    The combined model achieved the highest predictive performance for EGFR mutation with an AUC of 0.862.

  • 4

    SHAP analysis revealed that most key features in the habitat model were derived from specific tumor habitat subregions.

  • 5

    The findings support the use of radiomics and habitat analysis for personalized treatment strategies in lung adenocarcinoma.

Original Source(s)

The predictive value of 18F-FDG PET/CT habitat radiomics combined model in evaluating EGFR gene mutations in lung adenocarcinoma

  • by Lai, Ruihe , Sheng, Dandan , Geng, Yuzhi , Yang, Ding Chong, Tan, Qianqian , Zhao, Lianjun

  • May 28, 2026

Related Content

Imaging features and differentiation between benign and malignant Brenner tumors in a multi-center cohort

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

Tislelizumab-induced distal renal tubular acidosis presenting with life-threatening hypokalemia: a case report