Related Experiment Video
Updated: Jun 15, 2025
10:26
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
1.8K
The value of computed tomography-based radiomics for predicting malignant pleural effusions
Zhen-Chuan Xing1, Hua-Zheng Guo2, Zi-Liang Hou1
1Department of Pulmonary and Critical Care Medicine, Beijing Luhe Hospital, Capital Medical University, Beijing, China.
Frontiers in Oncology
|August 27, 2024
Summary
This study developed a radiomics model using unenhanced chest CT scans to predict malignant pleural effusion (MPE). The model shows high accuracy, offering a non-invasive tool for diagnosing MPE.
Area of Science:
- Radiology
- Medical Imaging
- Oncology
Background:
- Malignant pleural effusion (MPE) diagnosis typically requires invasive procedures.
- Radiomics offers a potential non-invasive method for MPE identification.
Purpose of the Study:
- To develop and validate a radiomics model for predicting MPE using unenhanced chest CT.
- To assess the diagnostic performance of the radiomics model.
Main Methods:
- Retrospective study of patients with pleural effusions (2016-2020).
- Extraction of 944 radiomic features from unenhanced chest CT, reduced to 14 features using LASSO.
- Development of a support vector machine (SVM) based radiomics model.
- Model evaluation using ROC analysis and calibration curves.
Main Results:
- The radiomics model achieved an AUC of 0.96 in the training cohort and 0.86 in the test cohort.
- Calibration curves indicated good agreement between predicted and actual data.
- The model effectively predicted MPE in the studied cohorts.
Conclusions:
- A radiomics model derived from unenhanced chest CT demonstrates strong performance in predicting MPE.
- This non-invasive approach can aid clinicians in MPE diagnosis and decision-making.
