Related Experiment Video
Updated: Sep 25, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.3K
Quantifying lung cancer heterogeneity using novel CT features: a cross-institute study
Zixing Wang1, Cuihong Yang1, Wei Han1
1Department of Epidemiology and Biostatistics, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences / School of Basic Medicine, Peking Union Medical College, Beijing, China.
Insights Into Imaging
|April 28, 2022
Summary
Radiomic features extracted from CT scans show promise in understanding lung cancer heterogeneity and predicting patient outcomes. These validated metrics may enhance individualized patient care in clinical practice.
Area of Science:
- Radiology and Oncology
- Medical Imaging Analysis
- Computational Pathology
Background:
- Radiomics-based image metrics are underutilized in clinical settings despite extensive research.
- Eight selected radiomic features were chosen to investigate their potential in decoding lung cancer heterogeneity.
Purpose of the Study:
- To validate the clinical utility of specific radiomic features in lung cancer.
- To assess the association of these features with patient prognosis, semantic characteristics, genetic profiles (e.g., EGFR mutation), and histopathological data.
Main Methods:
- CT images from 236 lung cancer patients across three institutions were analyzed.
- Radiomic features were extracted using a standardized procedure.
- Reproducibility of feature measurements was evaluated.
Main Results:
- All eight radiomic features demonstrated robustness across repeat scans (ICC: 0.81-0.99).
- Features correlated with prognostic, semantic, genetic, and histopathological cancer profiles.
- A combined radiomic score outperformed routine characteristics in predicting 5-year survival and stratifying patient death risk.
Conclusions:
- Radiomic features hold significant clinical value for lung cancer assessment.
- Further confirmation may lead to integration into CT imaging protocols for personalized patient care.
