Fig 1.
Different data sources that can be leveraged by WSO-SVM and existing ML algorithms.
Fig 2.
Pipeline of the proposed method.
Left: model training; Right: model deployment.
Fig 3.
Biological connection between genetic alterations and imaging-phenotypic features.
Fig 4.
A graphical illustration of the model formulation of WSO-SVM.
Fig 5.
Classification performance of WSO-SVM in comparison with the best competing algorithm in each category.
The overall best competing algorithm is highlighted by **.
Table 1.
Classification performance of EGFR using CV based on biopsy samples.
Table 2.
Classification performance of PDGFRA using CV based on biopsy samples.
Table 3.
Classification performance of PTEN using CV based on biopsy samples.
Fig 6.
Contributions of MRI contrast images to the classification of (a) EGFR, (b) PDGFRA, and (c) PTEN, by WSO-SVM.
Fig 7.
EGFR & PDGFRA prediction map (left column) and PTEN prediction map (right column) in tumoral AOI for four patients (rows). Yellow dots represent biopsy samples whose predicted gene statuses by WSO-SVM are reported underneath the maps (all predictions are correct).