Artificial Intelligence–assisted Prostate Cancer Diagnosis: Radiologic-Pathologic Correlation

Transverse prostate maximum sectional area can predict clinically significant prostate cancer in PI-RADS 3 lesions at multiparametric magnetic resonance imaging

“…Risk calculators, the most effective of which are the ERSPC and PCPT, can be utilised to predict the individual risk of csPCa before and after performing mpMRI in order to correctly select patients who require mpMRI in the first case and of biopsy in the second case. Artificial Intelligence (AI) can currently be applied to the use of risk calculations, allowing the processing of a large amount of data in a short time and providing predictive models useful in daily clinical practice, leading to the development of medication more and more tailored to the individual patient ( 15 ). Therefore, risk calculators can aid in selecting patients with PI-RADS 3 lesions at mpMRI who can benefit from follow-up or, alternatively, from immediate biopsy.…”

“…Of the clinical parameters, PSA density (with different cut-offs) represents the most investigated clinical predictor of PCa and a useful criterion in patient selection, especially in the grey area of PI-RADS 3 lesions ( 13 , 16 ). To date, evidence has suggested that risk calculators and PSA density could be used in combination with risk stratification of patients with equivocal mpMRI results ( 15 ).…”

“…However, with the advent of Computed Assisted Diagnosis (CAD) systems, it is much simpler to obtain this value as part of the standardised evaluation of the mpMRI exam and this parameter is integrated into the final report. Furthermore, a new generation of CAD has been implemented with the use of artificial intelligence (AI); it can support the diagnosis with the delineation of a probabilistic map of PCa for each lesion identified in the entire prostate gland ( 15 ). Artificial intelligence could be trained to obtain new tools, such as the TransPA, and integrate them into a predictive model of csPCa for each individual patient.…”

An update on computational pathology tools for genitourinary pathology practice: A review paper from the Genitourinary Pathology Society (GUPS)

“…Recent years have welcomed a foundation of literature supporting the use of AI for urology; 96 , 100 however, the rapid accumulation of promising clinical trials and published articles detailing urological ML applications have not been met with an equivalent proliferation of educational efforts preparing clinicians for discussions of implementation. AI literacy will be tantamount to practical competency in the emergent future, as more WSI devices obtain regulatory approval in the USA and globally, 1 , 77 , 96 , 101 , 102 , 103 , 104 while pathologists encroachingly find themselves in leadership roles that dictate the interdisciplinary interplay of AI across urology, pathology, radiology, metabolomics, genomics, and other disciplines.…”

Advances in radiology and pathology of prostate cancer: a review for the pathologist

“…Artificial intelligence-based tools have shown promise in improving the accuracy and speed of radiologists by automating or improving the human workflow 81 , 82 Similarly, some dated problems in PCa histopathology such as a relatively low interobserver and intraobserver concordance on measurements and Gleason grading 83-85 are being mitigated by these new techniques. Notably, AI-based systems hold the promise of augmenting the diagnostic capabilities of pathologists by providing them with decisional support, thereby mitigating interobserver variability and offering a more standardized and reproducible diagnostic framework.…”