Providing a Prostate Cancer Detection and Prevention Method With Developed Deep Learning Approach

Area of Science:

• Oncology
• Medical Imaging
• Artificial Intelligence

Background:

• Prostate cancer is a significant global health concern, ranking as the second most common cancer in men.
• Recent years have seen a noticeable increase in prostate cancer incidence among Iranian men, linked to lifestyle factors and unmonitored hormone use.

Purpose of the Study:

• To develop and evaluate a deep learning-based model for accurate prostate cancer diagnosis using histopathology images.
• To investigate factors contributing to prostate cancer presentation through literature review and simulation.

Main Methods:

• Utilized deep learning techniques, specifically incorporating Tile and Grad-CAM features, on histopathology images for prostate cancer diagnosis.
• Developed a novel deep learning model based on the manifold model to enhance diagnostic performance.

Main Results:

• The proposed deep learning model demonstrated superior performance compared to existing state-of-the-art methods.
• Achieved a high diagnostic accuracy of up to 97.41% for prostate cancer detection.

Conclusions:

• The developed deep learning approach offers a significant advancement in the accurate diagnosis of prostate cancer from histopathology images.
• The study identified key factors influencing the presentation of prostate cancer, aiding in understanding disease patterns.