Sign in Subscribe
Artificial intelligence

AI-Powered Diagnostic System for High-Grade Prostate Cancer Shows Promising Results

Strategic Insights

— 2 min read

Researchers from Chiba University, Japan, have developed an artificial intelligence (AI) powered diagnostic system for high-grade prostate cancer using innovative 3D magnetic resonance imaging (MRI) sequences and a 3-dimensional deep convolutional neural network (3DCNN). The study, published in the journal Current Urology, aimed to develop a diagnostic support system for high-grade prostate cancer and demonstrated its effectiveness in identifying patients at a higher risk of pretreatment.

The researchers used a dataset of 254 patients with prostate cancer, obtained from diffusion-weighted and T2-weighted imaging, to train the AI system. The 3DCNN was used as the AI for image recognition, and data augmentation was conducted to enhance the image dataset. The sensitivity and area under the curve values of the AI system were 85% and 0.82, respectively, indicating a high degree of accuracy in diagnosing high-grade prostate cancer.

Key Takeaways:

  • The AI-powered diagnostic system uses innovative 3D multiparametric MRI sequences to identify patients at a higher risk of pretreatment of high-grade prostate cancer.
  • The system uses a 3-dimensional deep convolutional neural network (3DCNN) to analyze image sequences and determine the presence of high-grade prostate cancer.
  • The sensitivity and area under the curve values of the AI system were 85% and 0.82, respectively, indicating a high degree of accuracy in diagnosing high-grade prostate cancer.
  • The study aimed to develop a diagnostic support system for high-grade prostate cancer, which could aid in the diagnosis of this type of cancer.
  • The researchers developed a learning system using a 3DCNN as a diagnostic support system for high-grade prostate cancer.
  • The study demonstrated the effectiveness of the AI-powered diagnostic system in identifying patients at a higher risk of pretreatment.

Statistics:

  • 254 patients with prostate cancer were used in the study.
  • 85% sensitivity of the AI system in diagnosing high-grade prostate cancer.
  • 0.82 area under the curve value of the AI system.
  • 3D magnetic resonance imaging (MRI) sequences were used to analyze image sequences.
  • The AI system used a 3-dimensional deep convolutional neural network (3DCNN) as the AI for image recognition.

Sources:

  • Li, B., Oka, R., Kato, S., Utsumi, T., Endo, T., Kamiya, N., Nakaguchi, T., Suzuki, H. (2025). Computer-aided diagnosis based on 3D deep convolutional neural network system using novel 3D magnetic resonance imaging sequences for high-grade prostate cancer. Current Urology, 19(5), 309-313.
  • NewsRx. Reports on Prostate Cancer Findings from Chiba University Provide New Insights (Computer-aided diagnosis based on 3D deep convolutional neural network system using novel 3D magnetic resonance imaging sequences for high-grade prostate cancer). Cancer Weekly. September 16, 2025; p 2362.

Read more