DIAGNOSTIC ACCURACY OF ARTIFICIAL INTELLIGENCE-ASSISTED MULTIPARAMETRIC MAGNETIC RESONANCE IMAGING FOR THE DETECTION OF CLINICALLY SIGNIFICANT PROSTATE CANCER

Abstract

Background: Prostate cancer is one of the leading malignancies among men worldwide.Multiparametric magnetic resonance imaging (mpMRI) has become an essential imaging modality for the detection of clinically significant prostate cancer.Recent advances in artificial intelligence (AI) have shown promising potential in improving the accuracy and consistency of prostate MRI interpretation.Objective: To evaluate the diagnostic accuracy of artificial intelligence-assisted multiparametric magnetic resonance imaging for the detection of clinically significant prostate cancer.Materials and Methods: A hospital-based prospective diagnostic accuracy study was conducted among 50 male patients with clinical suspicion of prostate cancer.All participants underwent AI-assisted multiparametric MRI of the prostate, including T2-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient mapping, and dynamic contrast-enhanced imaging where indicated.MRI findings were interpreted using AI-assisted software, and all patients subsequently underwent prostate biopsy.Histopathological examination served as the reference standard.Diagnostic performance was assessed by calculating sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), diagnostic accuracy, and area under the receiver operating characteristic (ROC) curve.Results: The mean age of the participants was 66.2 ± 7.8 years.Histopathology confirmed clinically significant prostate cancer in 34 (68%) patients.AI-assisted mpMRI correctly identified 31 true-positive and 12 true-negative cases, with 4 false-positive and 3 false-negative results.The sensitivity, specificity, PPV, NPV, and overall diagnostic accuracy were 91.2%, 75.0%, 88.6%, 80.0%, and 86.0%, respectively.The area under the ROC curve was 0.89, indicating excellent diagnostic performance.A statistically significant association was observed between AI-assisted mpMRI findings and histopathological diagnosis (Chi-square test, p < 0.001).Conclusion: Artificial intelligence-assisted multiparametric MRI demonstrated high diagnostic accuracy for detecting clinically significant prostate cancer and showed excellent agreement with histopathological findings.AI can serve as an effective decision-support tool for radiologists by improving lesion detection, reducing interobserver variability, and facilitating appropriate patient selection for biopsy.Larger multicentre studies are required to further validate these findings before widespread clinical implementation.