Table 4.

Comparison among different studies on TMB prediction.

Study	Method Summary	Kind of Cancer	Result
Jain et al. [14]	Machine learning algorithm, Image2TMB, integrated three deep learning models.	Lung cancer	auPRC = 0.92 Precision = 0.89
Shi et al. [15]	Deep learning model is based on the ResNet18 architecture.	Lung cancer	AUC = 0.64
Shimada et al. [16]	Convolutional neural network (CNN)-based algorithm.	Colorectal cancer	AUC = 0.934
Tang et al. [23]	LASSO regression selected features. Nomogram model predicted TMB.	Bladder cancer	AUC = 0.853
Liu et al. [24]	Nomogram model predicted TMB.	Lower-grade glioma	AUC = 0.736
The proposed study	The genetic algorithm selected radiomics signatures. LGBM algorithm predicted TMB.	Lower-grade glioma	AUC = 0.7875 auPRC = 0.7556

Only Liu et al. predicted TMB on LGG patients and our proposed study achieved a better performance than this study.