Photo Credit: Paul Biris
The following is a summary of “Computer-aided diagnosis based on 3D deep convolutional neural network system using novel 3D magnetic resonance imaging sequences for high-grade prostate cancer,” published in the February 2025 issue of Current Urology by oka et al.
The increasing incidence of prostate cancer (PCa) highlights the need for diagnostic tools to identify high-grade PCa.
Researchers conducted a retrospective study to develop a diagnostic support system for high-grade PCa using innovative magnetic resonance imaging (MRI) sequences and artificial intelligence (AI).
They examined image sequences of 254 patients with PCa obtained from diffusion-weighted and T2-weighted imaging using novel MRI sequences before prostatectomy. The presence of PCa was determined based on the final diagnosis derived from pathological results after prostatectomy. A 3-dimensional (3D) deep convolutional neural network (3DCNN) was used for image recognition, and data augmentation was conducted to enhance the image dataset. High-grade PCa was defined as Gleason grade group 4 or higher.
The results showed that the 3DCNN-based diagnostic support system for high-grade PCa achieved a sensitivity of 85% and an area under the curve of 0.82.
Investigators developed a 3DCNN-based AI diagnostic support system using 3D multiparametric MRI sequences. It has the potential to assist in identifying patients at higher risk of high-grade PCa before treatment.
Source: journals.lww.com/cur/fulltext/9900/computer_aided_diagnosis_based_on_3d_deep.187.aspx
