3D APA-Net: 3D Adversarial Pyramid Anisotropic Convolutional Network for Prostate Segmentation in MR Images

In this work, detection of Prostate Gland is performed using 3D Magnetic Resonance Images (MRI). Accurate and reliable segmentation of the prostate gland using magnetic resonance (MR) imaging has critical importance for the diagnosis and treatment of prostate diseases, especially prostate cancer. 

Although many automated detection approaches including those based on image processing techniques have been proposed, the detection performance still has room for improvement due to the large variability in image appearance, imaging interference. Here, we will implement the detection of prostate gland using deep learning technique like YOLO network. 

The dataset for this work is collected from the database of Cancer Imaging Archive. We evaluated the proposed network against several state-of-the-art deep learning-based segmentation approaches on CIA databases.

Keywords: Prostate Gland, Detection, Magnetic Resonance Images (MRI), YOLO network.