**7. Future Work**

The potential applications of ML to PCa surpass volume estimation, lesion detection, and lesion characterization. Further developments in prostate lesion classification may lead to a more practical clinical use, include training ML algorithms for tumor grade prediction. In addition to analyzing data solely from images, ML could augment the clinical management of PCa by incorporating demographic and biochemical data. ML could enable clinicians to make more assured decisions regarding the need for biopsy, medication dosing, and cancer recurrence. Biopsies that are performed for diagnosing PCa could be rendered unnecessary with a ML tool. Two studies by Hu et al. [102] and Chen et al. [103] used data such as age, digital rectal exam findings, PSA, and prostate volume for biopsy prediction. These studies made accurate PCa diagnoses and showed the potential for ML to eliminate the need for biopsy. In addition to diagnosis, ML could impact PCa medication dosing in PCa management. Radiation therapy requires accurate dosing, which is frequently operator dependent [104]. By minimizing operator dependency, ML could offer better standardization leading to more precise dosing. Nicola et al. [105] employed ML to predict prostate brachytherapy dosing by analyzing images and prior treatment plans from other patients. This study showed that ML implementation was comparable to brachytherapists and could be advanced by using a DL instead of a traditional ML algorithm. Along with diagnosis and dosing, ML could be used for predicting cancer recurrence after prostatectomy. Two studies by Wong et al. [106] and Cordon et al. [107] gathered data such as Gleason score, PSA, seminal vesical invasion, and surgical margins to predict recurrence after prostatectomy. The accuracy of these studies could be increased by adding postoperative imaging data for improved recurrence prediction.
