Related Experiment Video
Updated: Aug 16, 2025
08:08
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
144
Detection of prostate cancer using diffusion-relaxation correlation spectrum imaging with support vector machine
Xiaobin Wei1, Li Zhu1, Yanyan Zeng2
1Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
Summary
Diffusion-relaxation correlation spectrum imaging (DR-CSI) with support vector machine (SVM) shows improved accuracy in detecting prostate cancer (PCa) compared to PI-RADS. This advanced imaging technique offers a promising tool for PCa diagnosis.
Area of Science:
- Radiology
- Medical Imaging
- Oncology
Background:
- Prostate cancer (PCa) detection relies on imaging techniques.
- Diffusion-relaxation correlation spectrum imaging (DR-CSI) is an advanced MRI method.
- Support vector machine (SVM) is a machine learning algorithm.
Purpose of the Study:
- To evaluate the diagnostic performance of DR-CSI with SVM for detecting PCa.
- To compare DR-CSI's accuracy against PI-RADS scoring.
Main Methods:
- 114 patients undergoing prostate MRI and biopsy were enrolled.
- A DR-CSI model was developed and validated in stages.
- Diagnostic performance was compared between DR-CSI and PI-RADS.
Main Results:
- DR-CSI model outperformed ADC and T2 values in the exploration stage.
- DR-CSI demonstrated higher accuracy than PI-RADS ≥ 3 for both patient and lesion-based detection.
- DR-CSI showed comparable accuracy to PI-RADS ≥ 4 on lesion level.
Conclusions:
- DR-CSI combined with SVM may enhance diagnostic accuracy for PCa.
- This approach shows potential for improving PCa detection rates.
