Related Experiment Video
Updated: Sep 18, 2025
11:31
Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer
Published on: May 20, 2016
10.8K
Radiomics: Assessing Significance and Correlation with Ground-Truth Data in Precision Medicine in Lung Adenocarcinoma
Rama Vasantha Adiraju1, Kapula Kalyani1, Gunnam Suryanarayana2
1Department of Electronics and Communication Engineering, Aditya University, Surampalem 533437, Andhra Pradesh, India.
Bioengineering (Basel, Switzerland)
|June 26, 2025
Summary
This study introduces a robust radiomic feature extraction and validation method for lung nodules. The findings support radiomics
Area of Science:
- Radiomics
- Medical Imaging
- Computational Biology
- Clinical Oncology
Background:
- Radiomics offers quantitative biomarkers from medical images for improved cancer diagnosis and prognosis.
- Variability in imaging protocols and limited validation studies impede the clinical adoption of radiomic biomarkers in precision medicine.
Purpose of the Study:
- To propose and validate an RW-ensemble method for extracting and validating radiomic features from segmented lung nodules.
- To address the challenges of protocol variability and insufficient validation in radiomics.
Main Methods:
- Utilized the Lung CT-Diagnosis dataset with CT images and segmentation annotations from 61 patients.
- Extracted approximately 38 radiomic features, including texture-based (GLCM, GLRLM) and histogram-based features.
- Validated features against ground-truth data using Spearman's correlation coefficient (SCC).
Main Results:
- Demonstrated moderate to strong correlations between extracted radiomic features and ground-truth data.
- Confirmed the robustness of the RW-ensemble segmentation method.
- Highlighted the potential of radiomics in enhancing diagnostic accuracy for lung nodules.
Conclusions:
- The RW-ensemble method provides reliable radiomic features for lung nodule analysis.
- Validated radiomic features show promise for improving diagnostic accuracy and guiding precision oncology treatments.
- Emphasized the need for reliability and reproducibility for seamless clinical integration of radiomics in lung adenocarcinoma diagnosis and treatment.
