Prospects for the use of big data, artificial intelligence, machine learning, neural networks, and deep learning in the diagnosis and treatment of malignant tumors of the genitourinary system: a review

The review presents a comprehensive analysis of the latest advances in machine learning (ML), artificial neural networks (ANN), and deep learning (DL) in urologic oncology. As part of the study, the Russian and foreign scientific literature was ranked based on PubMed, MEDLINE, E-library, CYBERLENINKA, etc. The data related to the use of ML, ANN, and DL in the diagnosis and treatment of prostate cancer (PCa), bladder cancer (BC), testicular cancer, and kidney cancer was collected. Most often, ANN and ML in PCa were used for early diagnosis, prognosis, and personalized systemic treatment strategy development. ANN and DL models were trained with clinical parameters, NGS-sequencing results, Gleason scores, and digitized radiological, and histological images. Radiomics was also used to diagnose PCa, followed by analysis of special image texture features on a digital slide. In metastatic castration-resistant PCa, artificial intelligence (AI) algorithms were used to predict the response to docetaxel treatment. The prospects of using AI for tumor imaging during radical prostatectomy and when performing robot-assisted kidney resection were also addressed. A diagnostic approach for testicular malignancies based on computed tomography data is proposed using ML. Neuro-fuzzy modeling and ANN were used to diagnose BC. The algorithms were based on molecular biomarkers, including gene expression and methylation. The ML method based on images of cells obtained from urine samples of patients diagnosed with BC showed a diagnostic accuracy of 94%. DL in BC was used for accurate tumor typing based on their response to chemotherapy. Based on the results of deep machine learning, the molecular subtype of BC samples was predicted using histological examination. ML and DL algorithms for diagnosis, differential diagnosis, and prediction of recurrence and survival in kidney cancer were trained on CT texture analysis, genetic mutations, and Fuhrman nuclear grade. In addition to diagnosis, AI is used to optimize the treatment strategy for kidney cancer. In all cases, the ML, ANN, and DL algorithms improved the accuracy of diagnosis, survival assessment, and the effectiveness of pharmacological and surgical treatment of urologic malignancies.