Related Experiment Video
Updated: Apr 23, 2026
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
MUSIOMICS: A multi-region radiomics framework that outperforms single-region analysis in classifying malignant
Shu-Ju Tu1, Vuong Thuy Tran2, Chen-Te Wu3
1Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Nuclear Medicine, Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan.
New spatial delta-radiomics models (Delta-1 and Delta-2) using the MUSIOMICS framework significantly improved the classification of pulmonary nodules. These models integrate intranodular and perinodular features, outperforming traditional single-zone approaches for better diagnostic accuracy.
Area of Science:
- Radiomics and Medical Imaging
- Oncology and Cancer Research
- Computational Pathology
Background:
- Current lung cancer radiomic studies often analyze intranodular (Zone-1) and perinodular (Zone-2) regions separately.
- This separation may overlook the crucial biological interdependence between these regions.
- A novel multi-region radiomic framework is needed to integrate information from connected structures.
Purpose of the Study:
- To develop and evaluate MUSIOMICS (Multiregional Unified and Spatially Integrated Oncologic Model for Imaging-based Connected Structures), a multi-region radiomic framework.
- To construct and validate two region-dependent delta-radiomic models (Delta-1 and Delta-2) for classifying primary versus metastatic pulmonary nodules.
- To assess the performance improvement offered by integrating spatial information compared to single-region models.
Main Methods:
- Retrospective analysis of 443 malignant pulmonary nodules (360 training, 83 testing).
- Application of the MUSIOMICS framework to create spatial delta-radiomic models integrating Zone-1 and Zone-2 features.
- Feature selection, classification using Random Forest, AdaBoost, and SVM, and validation with t-tests and SHAP analysis.
Main Results:
- Spatial delta-radiomic models (Delta-1: 82%, Delta-2: 81%) outperformed single-region models (Zone-1: 75%, Zone-2: 67%) in the test set.
- Delta-1 with SVM achieved the highest accuracy (86%) and AUC (0.90).
- Identified reproducible and informative delta-features, with Intensity_QCD being a key contributor in both models.
Conclusions:
- The MUSIOMICS framework and its spatial delta-radiomic models effectively integrate complementary information from connected nodule compartments.
- This integrated approach yields superior and more reproducible predictive performance for characterizing malignant pulmonary nodules.
- Spatial delta-radiomics represents a significant advancement over conventional single-zone radiomic models.
Related Concept Videos
01:13Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
01:30Radiological Investigation II: MRI and Ventilation Perfusion Scan
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...