Automated Deep Learning Segmentation and CT Elastography Radiomics for Predicting Lymph Node Metastasis Near the Right Recurrent Laryngeal Nerve in Esophageal Cancer Preoperatively - Summary - MDSpire

Automated Deep Learning Segmentation and CT Elastography Radiomics for Predicting Lymph Node Metastasis Near the Right Recurrent Laryngeal Nerve in Esophageal Cancer Preoperatively

  • By

  • Chao Ji

  • Qingqing Li

  • Shumin Jiang

  • Lingling Wang

  • Sunkui Ke

  • Feng Wang

  • Hongbin Duan

  • Xiaomei Lin

  • Xi’e Xu

  • Xiaoli Huang

  • April 24, 2026

  • 0 min

Share

Objective:

Consider adding a sentence on the clinical significance of accurate predictions for treatment planning.

Key Findings:
  • Automatic segmentation model achieved a Dice coefficient of 0.898 ± 0.024.
  • Five DEM-derived radiomic features were selected, including one first-order entropy feature and four fractal dimension features.
  • The entropy feature showed the highest diagnostic performance (AUC = 0.814, sensitivity = 0.895, specificity = 0.709).
  • Fractal dimension features were significantly elevated in the metastatic group (all P < 0.001).
  • Calibration curves demonstrated robustness of entropy-based probability estimation.
Interpretation:

Expand on the implications of the findings for clinical practice and decision-making.

Limitations:
  • Add a point about potential biases in feature extraction methods.
Conclusion:

Reiterate the importance of the findings in relation to existing diagnostic methods.

Original Source(s)

Automated Deep Learning Segmentation and CT Elastography Radiomics for Predicting Lymph Node Metastasis Near the Right Recurrent Laryngeal Nerve in Esophageal Cancer Preoperatively

  • by Chao Ji, Qingqing Li, Shumin Jiang, Lingling Wang, Sunkui Ke, Feng Wang, Hongbin Duan, Xiaomei Lin, Xi’e Xu, Xiaoli Huang

  • April 24, 2026

Related Content

Is full adherence mandatory? Real-world outcomes of completing perioperative chemoimmunotherapy in resectable non-small cell lung cancer

Artificial intelligence for optimization of immunotherapy: current applications and transformative potential

Icaritin plus TACE improves survival in advanced HCC with macrovascular invasion: a multicenter cohort study