Archimedes Optimization Algorithm with Deep Learning-Based Prostate Cancer Classification on Magnetic Resonance...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Prostate cancer (PCa) is a leading cause of cancer-related deaths in men.
• Accurate PCa detection from medical images is challenging due to tumor complexity.
• Existing PCa detection methods lack sufficient efficiency and accuracy.

Purpose of the Study:

• To introduce an advanced AI model for accurate prostate cancer classification using MRI images.
• To enhance the efficiency and accuracy of PCa detection through deep learning and optimization algorithms.

Main Methods:

• A novel Archimedes Optimization Algorithm with Deep Learning-based Prostate Cancer Classification (AOADLB-P2C) model was developed.
• The model utilizes adaptive median filtering (AMF) for noise reduction and contrast enhancement in MRI images.
• Feature extraction is performed using DenseNet-161 with RMSProp optimization, followed by classification with AOA and LS-SVM.

Main Results:

• The AOADLB-P2C model demonstrated significant improvements in prostate cancer identification accuracy on a benchmark MRI dataset.
• Comparative analysis confirmed the superiority of the AOADLB-P2C model over existing state-of-the-art approaches.
• The model effectively handles complex tumor masses in MRI scans for precise classification.

Conclusions:

• The AOADLB-P2C model offers a highly accurate and efficient solution for prostate cancer detection from MRI.
• AI-driven approaches, like AOADLB-P2C, show great promise in improving oncological diagnostics.
• This study highlights the potential of integrating advanced AI algorithms for better healthcare outcomes in cancer screening.