Assessment of Radiomic Feature Consistency in Low-Dose CT Screening for Lung Cancer Using Phantom Models
-
By
-
Sunyi Zheng
-
Xiaomeng Yang
-
Hongren Wang
-
Zhipeng Gao
-
Pengchun Ye
-
Weiping Wang
-
Wenhua Li
-
Donghua Meng
-
Shuai Zhang
-
Wenjia Zhang
-
Houpu Liu
-
Shuyuan Huang
-
Chunlin Zhang
-
Jing Wang
-
Jihui Hao
-
Xiaonan Cui
-
July 21, 2026
Clinical Scorecard: Assessment of Radiomic Feature Consistency in Low-Dose CT Screening for Lung Cancer Using Phantom Models
At a Glance
| Category | Detail |
|---|
| Condition | Lung Cancer Screening |
| Key Mechanisms | Radiomic feature extraction and stability evaluation under low-dose CT conditions. |
| Target Population | Individuals undergoing lung cancer screening, particularly high-risk populations. |
| Care Setting | Low-dose computed tomography (LDCT) lung cancer screening. |
Key Highlights
- Inter-scanner variability significantly impacts radiomic feature stability.
- Models using stable features outperform those using unstable features in malignancy assessment and growth prediction.
- Stable features lead to smaller performance differences between training and test sets.
Guideline-Based Recommendations
Diagnosis
- Utilize stable radiomic features for improved malignancy assessment in lung nodules.
Management
- Incorporate stability-informed feature selection in radiomics applications for lung cancer screening.
Monitoring & Follow-up
- Regularly evaluate the stability of radiomic features in clinical settings.
Risks
- Consider inter-scanner and intra-scanner variability when interpreting radiomic features.
Patient & Prescribing Data
Patients at high risk for lung cancer undergoing LDCT screening.
Stable radiomic features may enhance the accuracy of lung cancer screening models.
Clinical Best Practices
- Implement standardized scanning protocols to minimize variability in radiomic feature extraction.
- Use hierarchical clustering to identify and select stable radiomic features.
Related Resources & Content
