Review on brain tumor segmentation: hard and soft computing approaches

1Citations
Citations of this article
2Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Segmenting the brain of the human is essential to obtain an exact analysis of tumors from the brain medical image dataset. A lot of research works have conceded in novice algorithms and approaches for exact segmentation of tumor, however, as of now, no solitary standard techniques have been proposed. This article aims to emphasis over the computing methods that are soft and hard for the segregation of medical image data set on tumor cause din brain. The taxonomy of hard-computing approaches of segmentation includes edge-based segmentation, normalized cut method, mean shift method, and so on. Soft computing methods include approaches based on fuzzy logic, ANN, and genetic algorithms. Nowadays, deep learning plays a very vital for brain tumor segmentation significantly. This provides an efficient structure of the review of different pieces of literature based on soft and hard computing methods for brain tumor segmentation. After going through this paper, researchers can easily analyze the methods based on data used, observation, research results, advantages, and disadvantages.

Cite

CITATION STYLE

APA

Mishra, P., Garg, A., Gupta, D., Tuteja, M., Sinha, P., & Saxena, S. (2021). Review on brain tumor segmentation: hard and soft computing approaches. In Advances in Intelligent Systems and Computing (Vol. 1200 AISC, pp. 190–200). Springer. https://doi.org/10.1007/978-3-030-51859-2_18

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free