Related Experiment Video
Updated: Aug 17, 2025
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Machine learning-based analysis of a semi-automated PI-RADS v2.1 scoring for prostate cancer
Dharmesh Singh1, Virendra Kumar2, Chandan J Das3
1Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India.
Background:
Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) was developed to standardize the interpretation of multiparametric MRI (mpMRI) for prostate cancer (PCa) detection. However, a significant inter-reader variability among radiologists has been found in the PI-RADS assessment. The purpose of this study was to evaluate the diagnostic performance of an in-house developed semi-automated model for PI-RADS v2.1 scoring using machine learning methods.
Methods:
The study cohort included an MRI dataset of 59 patients (PI-RADS v2.1 score 2 = 18, score 3 = 10, score 4 = 16, and score 5 = 15). The proposed semi-automated model involved prostate gland and zonal segmentation, 3D co-registration, lesion region of interest marking, and lesion measurement. PI-RADS v2.1 scores were assessed based on lesion measurements and compared with the radiologist PI-RADS assessment. Machine learning methods were used to evaluate the diagnostic accuracy of the proposed model by classification of PI-RADS v2.1 scores.
Results:
The semi-automated PI-RADS assessment based on the proposed model correctly classified 50 out of 59 patients and showed a significant correlation (r = 0.94, p < 0.05) with the radiologist assessment. The proposed model achieved an accuracy of 88.00% ± 0.98% and an area under the receiver-operating characteristic curve (AUC) of 0.94 for score 2 vs. score 3 vs. score 4 vs. score 5 classification and accuracy of 93.20 ± 2.10% and AUC of 0.99 for low score vs. high score classification using fivefold cross-validation.
Conclusion:
The proposed semi-automated PI-RADS v2.1 assessment system could minimize the inter-reader variability among radiologists and improve the objectivity of scoring.
Insights
A new semi-automated model for Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) scoring demonstrated high accuracy in prostate cancer detection. This machine learning approach reduces variability in radiologist assessments of multiparametric MRI.
Area of Science:
- Radiology and Medical Imaging
- Machine Learning in Healthcare
- Prostate Cancer Diagnostics
Background:
- Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS v2.1) standardizes multiparametric MRI (mpMRI) for prostate cancer (PCa) detection.
- Significant inter-reader variability exists among radiologists in PI-RADS assessments.
- This variability can impact the accuracy and consistency of PCa diagnosis.
Purpose of the Study:
- To evaluate the diagnostic performance of a novel semi-automated model for PI-RADS v2.1 scoring.
- To assess the model's ability to improve objectivity and reduce inter-reader variability in PI-RADS scoring.
- To utilize machine learning methods for enhanced PI-RADS v2.1 assessment.
Main Methods:
- A cohort of 59 patients with mpMRI scans and PI-RADS v2.1 scores was analyzed.
- The semi-automated model included prostate segmentation, 3D co-registration, lesion identification, and measurement.
- Machine learning techniques were employed to classify PI-RADS v2.1 scores and evaluate diagnostic accuracy.
Main Results:
- The semi-automated model correctly classified 50 out of 59 patients, showing high agreement with radiologist assessments (r = 0.94, p < 0.05).
- The model achieved an accuracy of 88.00% ± 0.98% for PI-RADS v2.1 score classification (2-5) and 93.20% ± 2.10% for low vs. high score classification.
- Area under the ROC curve (AUC) values were 0.94 for score classification and 0.99 for low vs. high score classification.
Conclusions:
- The developed semi-automated PI-RADS v2.1 assessment system shows significant potential for improving diagnostic accuracy.
- This system can effectively minimize inter-reader variability among radiologists in PI-RADS scoring.
- The model enhances the objectivity of PI-RADS scoring, leading to more consistent prostate cancer detection.
