Table 4.

AI model for radiogenomics study on the brain tumor.

Author, Year and Reference	Image Modality	Radiomics Feature	Genomics Feature	AI Model Used	Result
Akkus et al. [53] (2016)	MRI: T1-CE, T2	Deep radiomics	1p19q deletion of LGG	DL (CNN)	Acc.: 87.7
Kickingereder et al. [64] (2016)	MRI: T1, T1-CE, FLAIR, DWI, DSWCEI, PSWI	Hand-crafted	EGFR, PTEN, PDGFRA, MDM4, CDK4 CDKN2A, NF1, and RB1	ML	Acc.: 63 AUC: 69
Chang et al. [60] (2017)	MRI: T1, T1-CE, T2, FLAIR	Deep radiomics	IDH1 prediction for LGG	DL (ResNet)	Acc.: 89.1 AUC: 95
Li et al. [66] (2017)	MRI: T1, T2	Deep radiomics	IDH1 prediction for LGG	DL (CNN)	Acc.: 92.4 AUC: 95
Liang et al. [67] (2017)	MRI: T1, T1-CE, T2, FLAIR	Deep radiomics	IDH1 prediction for Glioma	DL (DenseNet)	Acc.: 91.4 AUC: 94.8
Korfiatis et al. [65] (2017)	MRI: T2	Deep radiomics	MGMT status	DL (ResNet50)	Acc.: 94.9
Chang et al. [61] (2018)	MRI: T1, FLAIR	Deep radiomics	IDH1, 1p/19q co-deletion, MGMT	DL (ResNet)	Acc.: 94 AUC: 91
Smedley et al. [68] (2018)	MRI: T1-CE, T2, FLAIR	Deep radiomics	Tumor morphology	DL (AE)	MAE: 0.0114
Calabrese et al. [131] (2020)	MRI: T1, T1-CE, T2, FLAIR, SWI, DWI, ASLPI, HARDI	Deep radiomics	ATRX, IDH, 7/10aneuploidy, CDKN2, EGFR, TERT, PTEN, TP53, MGMT	TL (CNN+ RF)	AUC: 97
Kawaguchi et al. [63] (2021)	MRI: T1, T1-CE, T2, FLAIR	Hand-crafted	IDH, MGMT, TERT, 1p19q	ML	AUC: 90

Abbreviation: DWI: diffusion-weighted image, SWI: susceptibility-weighted image, DSWCEI: dynamic susceptibility-weighted contrast-enhanced imaging, PSWI: pre-contrast susceptibility-weighted imaging, ASLPI: arterial spin labeling perfusion images, HARDI: high angular resolution diffusion imaging, Acc: accuracy, AUC: area under ROC curve, MAE: mean absolute error, AE: auto-encoder, RF: random forest.