An Overview and Application of Deep Convolutional Neural Networks for Medical Image Segmentation

Medical imaging technologies are widely utilized as a non-invasive diagnostic process that helps professionals identify diseases and injuries. Convolutional neural networks (CNNs) have become increasingly popular since they are considered to be the best approach for a variety of computer vision problems includes medical imaging and diagnostics. Image segmentation using CNN models makes image analysis easier that can effectively use with different image modalities like X-ray, MRI, CT, Ultrasound and PET. This review article provides a perspective on using CNN models for various medical image segmentation tasks. It contains the details of benchmark deep CNN models available for image segmentation, publicly available medical imaging datasets and various applications of deep CNN models for medical image segmentation tasks.

I. Introduction

Computer-aided diagnosis greatly assists doctors to interpret medical images with different imaging modalities like X-ray, PET scan, MRI, ultrasound etc. Medical imaging technologies extensively used as a diagnostic non-invasive procedure which allows medical professionals to support in diagnoses diseases and injures. It improves the treatments by allowing doctors to assess human body organs, blood vessels or tissues and bones. It can be used for variety of diagnosis tasks like whether surgery would be required; treatment of bone fractures; assisting doctors in replacement of joints and placement of devices like stents etc. in the body; locating and removal of tumors; identification of blockages or clots in blood vessels and many more.