Unveiling the Power of Deep Learning: A Trailblazing Review on Different Techniques used for Medical Image Segmentation Analysis
Syed Amin Ullah, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Arbab Waseem Abbas, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Mohib Ullah, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Rafiullah Khan, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Atta Ur Rehman, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Corresponding Author:
Syed Amin Ullah(syedaminullah.kmu@gmail.com)
Abstract:
Medical image analysis refers to the use of scientific methods for analyzing medical images generated in clinical practice. The aim is to efficiently and effectively extract information to improve the clinical diagnosis and its accuracy. With recent advances in biomedical engineering, medical image analysis has become an attractive and emerging domain for research. One of the key factors of this growth is the application of numerous machine learning techniques, particularly deep learning, which allows for the automatic learning of features by a neural network. This is in contrast to traditional methods that use hand-crafted features, which can be challenging to select and calculate. Deep convolutional networks, in particular, are widely used in medical image analysis tasks such as abnormality detection, segmentation, and computer-aided diagnosis. This paper provides a thorough appraisal of the current advanced techniques in medical image segmentation analysis using deep convolutional networks and other methods and also examines the performance of various techniques.
Keywords:
Medical Image Analysis; Segmentation; Deep Learning (DL); Convolutional Neural Network (CNN); Computer Aided Diagnosis (CAD); Fully Convolutional Network (FCN)