Machine Learning and Clinical-Radiological Characteristics for the Classification of Prostate Cancer in PI-RADS 3 Lesions

Abstract

The Prostate Imaging Reporting and Data System (PI-RADS) classification is based on a scale of values from 1 to 5. The value is assigned according to the probability that a finding is a malignant tumor (prostate carcinoma) and is calculated by evaluating the signal behavior in morphological, diffusion, and post-contrastographic sequences. A PI-RADS score of 3 is recognized as the equivocal likelihood of clinically significant prostate cancer, making its diagnosis very challenging. While PI-RADS values of 4 and 5 make biopsy necessary, it is very hard to establish whether to perform a biopsy or not in patients with a PI-RADS score 3. In recent years, machine learning algorithms have been proposed for a wide range of applications in medical fields, thanks to their ability to extract hidden information and to learn from a set of data without previous specific programming. In this paper, we evaluate machine learning approaches in detecting prostate cancer in patients with PI-RADS score 3 lesions via considering clinical-radiological characteristics. A total of 109 patients were included in this study. We collected data on body mass index (BMI), location of suspicious PI-RADS 3 lesions, serum prostate-specific antigen (PSA) level, prostate volume, PSA density, and histopathology results. The implemented classifiers exploit a patient’s clinical and radiological information to generate a probability of malignancy that could help the physicians in diagnostic decisions, including the need for a biopsy.

Recognition of Postoperative Cystography Features by Artificial Intelligence to Predict Recovery from Postprostatectomy Urinary Incontinence: A Rapid and Easy Way to Predict Functional Outcome

“…A combination of AI and radiomics has been increasingly utilized in the field of urology, including prostate cancer in recent years. In addition to our study, Gravina et al also demonstrated that combining clinical information and radiological parameters with machine learning can better detect the prostate malignancy probability of equivocal prostate lesions [ 34 ].…”

Reliability and Efficiency of the CAPRI-3 Metastatic Prostate Cancer Registry Driven by Artificial Intelligence

“…Specifically, research into prostate cancer has demonstrated promising performances of ML models in detecting prostate cancer on MRI scans. Their best performing models achieved area under the curve (AUC) rates between 0.78 and 0.87 [38][39][40][41], surpassing the diagnostic performance of radiologists in one paper (AUC 0.81 vs. 0.69, p = 0.02) [39] and enhancing the specificity of PI-RADS assessment by senior radiologists in another (from 52.5% to 72.6%) [40].…”

Emerging Role of Nuclear Medicine in Prostate Cancer: Current State and Future Perspectives

“…It can extract multiple features from pathological findings and potentially define new markers of disease [183][184][185]. Radiomics has the potential to further increase the value of imaging in PC management; nevertheless, its introduction into current clinical practice is full of questions, as emphasized by several radiomic studies [186][187][188][189]. Several approaches have been proposed and standardization is the major issue.…”