Page 37 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

2

Deep convolutional neural

network in medical image

processing

1
2
Subhashree Mohapatra, Tripti Swarnkar, Jayashankar Das 3
1
Department of Computer Science and Engineering, Institute of Technical
Education and Research, Siksha ‘O’ Anusandhan Deemed to be University,
2
Bhubaneswar, Odisha, India; Department of Computer Application, Institute
of Technical Education and Research, Siksha ‘O’ Anusandhan Deemed to be
3
University, Bhubaneswar, Odisha, India; Centre for Genomics and
Biomedical Informatics, Institute of Medical Sciences and SUM Hospital,
Siksha ‘O’ Anusandhan Deemed to be University, Bhubaneswar, Odisha,
India

1. Introduction
Medical image analysis is the science that involves the analysis
of images in clinical practices to solve medical problems. The
main focus is to gain knowledge in an efficient and effective
way for enhanced medical diagnosis. The current advancement
in the field of biomedical engineering has made image analysis
one of the buzzing research areas. One of the important motiva-
tions for this field is the advances in the application of machine
learning (ML) techniques for medical image analysis. Deep
learning (DL) is another technology that is effectively used as a
subset of ML in which the system can extract feature set automat-
ically. Comparing with those techniques that use manually
extracted features, the DL techniques are highly acceptable.
The calculation and extraction of features is always a challenging
task. Deep convolutional networks that come under DL tech-
nique are widely used for the task of medical imaging. It has
several application areas such as computer-aided diagnosis, seg-
mentation, disease classification, and abnormality detection.

Handbook of Deep Learning in Biomedical Engineering. https://doi.org/10.1016/B978-0-12-823014-5.00006-5
Copyright © 2021 Elsevier Inc. All rights reserved. 25