Related Experiment Video
Updated: May 20, 2025

05:52
Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy
Published on: August 19, 2021
11.2K
Mediastinal staging lymph node probability map in non-small cell lung cancer
J Bordas-Martinez1,2, J L Vercher-Conejero3, G Rodriguez-González1
1Pulmonology Department, Hospital General de Granollers, Barcelona, Catalonia, Spain.
Respiratory Research
|March 25, 2025
Summary
This study developed a predictive algorithm combining EBUS, PET/CT, and clinical data to estimate lymph node malignancy probability in lung cancer patients. The model achieved an 0.89 Area Under the ROC curve, aiding in staging accuracy.
Area of Science:
- Oncology
- Medical Imaging
- Pulmonology
Background:
- Mediastinal lymph node staging is crucial for non-small cell lung carcinoma (NSCLC).
- Current methods like PET/CT and endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) have limitations.
- Predictive algorithms integrating these modalities show promise for improved accuracy.
Purpose of the Study:
- To develop a predictive algorithm for lymph node malignancy probability.
- To integrate EBUS, PET/CT, and clinical data into a single predictive model.
- To provide a pre-sampling probability map for lymph node malignancy.
Main Methods:
- Retrospective study of 116 NSCLC patients staged with PET/CT and EBUS-TBNA.
- Collected lymph node data: level, anatomical region, SUVmax (PET/CT), and ultrasound features (DSA, morphology, border, echogenicity, vascular hilum).
- Developed a logistic regression model to estimate malignancy probability using age, DSA, SUVmax, and anatomical region.
Main Results:
- 358 lymph nodes were evaluated from 116 patients (mean age 66, 93% male).
- The predictive model achieved an Area Under the ROC curve of 0.89.
- A user-friendly application was developed to implement the algorithm.
Conclusions:
- Integrating clinical, EBUS, and PET/CT data can create a pre-sampling malignancy probability map for lymph nodes.
- This approach may enhance the accuracy of mediastinal lymph node staging in NSCLC.
- Prospective and external validation of the model is necessary.

