A5019073598- Radiomics and Machine Learning in Medical Imaging
- Computational Drug Discovery Methods
- Mathematical Biology Tumor Growth
- Transportation and Mobility Innovations
- Urban Transport and Accessibility
- Electric Vehicles and Infrastructure
- Food Waste Reduction and Sustainability
- Municipal Solid Waste Management
- Transportation Planning and Optimization
- Ferroptosis and cancer prognosis
- Cancer Cells and Metastasis
- Advanced Battery Technologies Research
- Urban Agriculture and Sustainability
- Sustainable Supply Chain Management
- Vehicle emissions and performance
- Cancer Immunotherapy and Biomarkers
- Environmental Justice and Health Disparities
- Extraction and Separation Processes
- Urban and Freight Transport Logistics
- Immune cells in cancer
- Gene expression and cancer classification
Houston Methodist
2024
University of Illinois Chicago
2017-2021
Wuhan University
2020
<p>S10. Variable importance for prediction of BCLM Collagen+, E-cad+, HIF1α+, and Ki-67+ using ML models.</p>
<p>S13. Metric F1 achieved by ML models using primary tumor IMC clusters across a variable number of features to predict BCLM cluster densities (as stated in gray box each panel)</p>
<p>S12. AUROC achieved by ML models using primary tumor IMC clusters across a variable number of features to predict BCLM cluster densities (as stated in gray box each panel)</p>
<p>S1. Heatmap of IMC cluster densities originating from breast primary and cancer liver metastases (BCLM) before mean aggregation ROIs.</p>
<p>S3. PLS-DA of primary breast and BCLM IMC ROI data by batch number showing that the batches were homogeneous.</p>
<p>S6. PLS-DA score plots of classifying BCLM patient IMC clusters into Low (</p>
<p>S7. Variable importance for prediction of BCLM CD14+, CD163+, CD163+MMP9+, and CD206+ using ML models.</p>
<p>Table S11. Variable importance for prediction of BCLM MMP9+, PD-L1+, pERK+, and αSMA+ using ML models.</p>
<p>S9. Variable importance for prediction of BCLM CD68+CD163+CD206+, CD68+MMP9+, CD8a+PD1-, and CD8a+PD1+ using ML models.</p>
<p>S8. Variable importance for prediction of BCLM CD31+, CD4+PD1+, CD56+, and CD68+ using ML models.</p>