P rostate cancer (PCa) is the second most prevalent cancer among men worldwide. 1 Timely and accurate diagnosis is important to avoid overtreatment of men with indolent, clinically insignificant PCa and to offer radical curative treatment with life-threatening, clinically significant PCa. 2 Radical prostatectomy (RP) has become the standard care for eligible patients because of its cancer control and improved survival. Although most patients remained disease-free after RP, 20%-30% of patients develop recurrence of the disease at follow-up. 3 Therefore, the assessment of reliable prognostic predictors of recurrence after RP is clinically important for guiding clinical decision-making and patient counseling. To date, several factors are considered adverse pathology (AP) features such as preoperative prostate-specific antigen (PSA) levels, Gleason score, tumor stage, surgical margin status, lymph node invasion, extracapsular extension (ECE), and seminal vesicle invasion (SVI). All of them have been identified as prognostic factors for recurrence after RP. 3,4 MRI has an established role in diagnosis of PCa. 5 Due to the complex nature of the PCa diagnosis pathway by MRI, diagnostic performance has varied widely. 6,7 The use of biparametric MRI, excluding dynamic contrast-enhanced (DCE), despite its enormous potential, is still controversial, particularly when there is suboptimal diagnostic quality for T2WI and DWI sequences. 8 Developing artificial intelligence models using machine learning, particularly deep learning, has an expanding role in radiology with great potential in prostate MRI. 9 In this JMRI paper, 10 the authors use a deep learning approach of 3D Swin-Transformer (TransNet) based on biparametric MRI to predicting AP of PCa. An integrated model combining TransNet signature and clinical characteristics (TransCL) has also been developed. These models can provide personalized surgical treatment planning and are very important for clinical decisions.