Table 1.

Summary of radiomic manuscripts for detection and location of prostate cancer.

Author	MRI Sequences	Software and Features	Conclusion
Ginsburg SB at al., 2017	T2, ADC, DCE	Signal intensities on T2w and ADC values, kinetic features on DCE, edge descriptors, first-order statistical, co-occurrence, Gabor, Haar	Zone-aware classifier significantly improves the accuracy of cancer detection in the PZ
Bleker J et al., 2020	T2, ADC, DCE	Pyradiomics	Clinically significant PZ prostate cancer lesions can be quantified using a radiomics approach based on features extracted from T2w + DWI
Sidhu HS et al. 2017	T1, T2, ADC	TexRAD v.3.3	Textural evaluation technique may have particular relevance for such patients who are more likely to have TZ tumors that are systematically undersampled by TRUS
Cameron A et al., 2016	T2, DWI, ADC, Correlated Diffusion Imaging (CDI)	MAPS	In addition to being easier to interpret by radiologists, the MAPS feature model achieves higher classification performance (respect to conventional mpMRI)
Khalvati F et al., 2018	T2, DWI, Computed High-b Diffusion-Weighted Imaging (CHB-DWI), Correlated Diffusion Imaging (CDI), ADC	MPCAD	Quantitative radiomic features extracted from mpMRI of prostate can be utilized to detect and localize prostate cancer
Wibmer A et al., 2015	T2, ADC	Haralick Texture Analysis	Haralick-based texture features showed significant differences between noncancerous and malignant prostate tissue
Nketiah et al., 2021	T2, ADC	GLCM and GLRLM features, Spearman correlations, Mann–Whitney U-tests, SVM	T2W MRI-derived textural features correlated significantly with pathological findings (cancer grade group) from multiple institutions