Table 3.

A comparison of the current study’s performance with the recent related articles.

Authors (year)	Number of subjects	Method	Performance
Dhinagar et al. (2020) (10)	617	VGG-16 based deep learning method	ROC-AUC = 0.74 (score 2, 3) vs. (score 4, 5)
Sanford et al. (2019) (20)	196	Convolutional neural network with a ResNet101	Correct classification rate = 60% Sensitivity = 74% for correct depiction of PI-RADS 4/5 lesions
Singh et al. (current study)	59	Image processing and supervised machine learning based model	Overall correct classification rate = 85% accuracy = 88% and AUC = 0.94 for score 2 vs. score 3 vs. score 4 vs. score 5 classification accuracy = 93.20% and AUC 0.99 for (Score 2, 3) vs. (Score 4, 5)