14 - Brain tumor segmentation using deep learning: taxonomy, survey and challenges

https://doi.org/10.1016/B978-0-323-91171-9.00003-XGet rights and content

Abstract

In medical image processing, brain tumor segmentation is the challenging task for the healthcare professionals in monitoring and diagnosing the tumor in humans. The survival of the patient can be improved by diagnosing it in the initial stage. In today's era of deep learning (DL), the automated segmentation of the brain tumors can be done effectively by using many approaches. Unlike conventional algorithms, self-learning, automatic feature extraction, representing complex structures, handling large amount of data, etc. are some of the characteristics of the DL algorithms. This chapter covers the taxonomy of DL techniques used for brain tumor segmentation, survey of deep segmentation methods used from 2018 to 2020 by various researchers, and challenges faced while performing deep segmentation. Different DL algorithms and their advantages and disadvantages are discussed in this chapter to provide the crux information to the researchers, healthcare professionals to diagnose the tumors with smart healthcare facilities.

Access through your organization

Check access to the full text by signing in through your organization.

Access through your organization

References (0)

View full text
Copyright © 2022 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.