Related Experiment Video
Updated: Jan 11, 2026
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
Published on: March 29, 2019
MRI-based radiomics for noninvasive prediction of T790M resistance mutation in lung cancer spinal metastases: an
Xiaoya Zhou1, Jiashi Zheng2, Hua Ai3
1Jining Key Laboratory of Pharmacology, School of Basic Medicine, Jining Medical University, Jining, Shandong, China.
Background:
The T790M mutation is a significant mechanism of acquired resistance to EGFR-TKIs in non-small cell lung cancer (NSCLC). Its noninvasive detection in spinal metastases remains challenging due to tumour heterogeneity and limitations of current diagnostic methods. This study aimed to develop an MRI-based radiomics model derived from spinal metastases to non-invasively predict T790M resistance mutations in NSCLC patients, by incorporating intratumoral spatial heterogeneity.
Methods:
One hundred ten EGFR-mutant NSCLC patients with spinal metastases (80 from Center 1, 30 from Center 2) underwent T1W and T2FS MRI scans. Spinal lesions were partitioned into phenotypically consistent subregions using patient- and population-level clustering based on local entropy to capture spatial heterogeneity. Radiomic features were extracted from each subregion, and reproducibility was assessed using the intraclass correlation coefficient (ICC >0.80). Significant features were selected via the Mann-Whitney U test and LASSO regression, and logistic regression models were constructed for each subregion and MRI sequence. A multi-sequence regional fusion model was subsequently developed based on the best-performing subregion. Model performance was evaluated by AUC, sensitivity, and specificity in both internal and external validation cohorts. SHAP analysis was conducted to interpret feature contributions.
Results:
Models based on inner subregions with higher heterogeneity outperformed those from marginal or whole-tumor regions. The fusion model combining T1W and T2FS features achieved AUCs of 0.916 (training), 0.867 (internal validation), and 0.839 (external validation). SHAP analysis identified key textural features associated with the T790M mutation.
Conclusion:
Subregion-based MRI radiomics enables accurate, noninvasive prediction of T790M mutations in NSCLC spinal metastases. This subregion-based MRI radiomics model, to our knowledge, is the first to non-invasively predict T790M resistance mutations in spinal metastases by integrating spatial heterogeneity and SHAP interpretability. This subregion-based MRI radiomics model is exploratory and showed a consistent trend toward improved discrimination and net benefit.
Insights
This study developed an MRI radiomics model to predict T790M mutations in non-small cell lung cancer (NSCLC) spinal metastases. The model accurately identifies resistance mutations noninvasively by analyzing intratumoral heterogeneity.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- The T790M mutation confers acquired resistance to EGFR-TKIs in non-small cell lung cancer (NSCLC).
- Noninvasive detection of T790M in spinal metastases is challenging due to tumor heterogeneity and current diagnostic limitations.
- This study addresses the need for noninvasive methods to predict T790M mutations in NSCLC spinal metastases.
Purpose of the Study:
- To develop and validate an MRI-based radiomics model for noninvasive prediction of T790M resistance mutations in NSCLC spinal metastases.
- To incorporate intratumoral spatial heterogeneity into the radiomics model for improved prediction accuracy.
- To assess the model's performance using internal and external validation cohorts.
Main Methods:
- 110 EGFR-mutant NSCLC patients with spinal metastases underwent T1W and T2FS MRI scans.
- Spinal lesions were sub-partitioned based on local entropy to capture spatial heterogeneity.
- Radiomic features were extracted, and a multi-sequence regional fusion model was developed and validated using AUC, sensitivity, and specificity.
Main Results:
- Subregion-based models incorporating heterogeneity outperformed whole-tumor models.
- The fusion model achieved AUCs of 0.916 (training), 0.867 (internal validation), and 0.839 (external validation).
- SHAP analysis identified key textural features predictive of the T790M mutation.
Conclusions:
- Subregion-based MRI radiomics enables accurate, noninvasive prediction of T790M mutations in NSCLC spinal metastases.
- This novel approach integrates spatial heterogeneity and SHAP interpretability for predicting resistance mutations.
- The exploratory model demonstrates potential for improved discrimination and clinical utility in managing NSCLC treatment resistance.
More Related Videos
11:31Using 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
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
