Pre and Post Operative Brain Tumor Segmentation and Classification for Prolonged Survival

Title

Pre and Post Operative Brain Tumor Segmentation and Classification for Prolonged Survival

Creator

Xavier P.S.; Raju G.; Asawthy S.U.

Description

The aim of this research was to provide a detailed overview of the techniques in detecting and segmenting meningioma brain tumor in pre- and post-operative MRI images and classify for presence of meningioma thereby giving an early diagnosis to decrease the death rate. This study examines trending techniques for brain tumour segmentation and classification in Magnetic Resonance (MR) images of pre and post-surgery. For the segmentation and anomalies in the brain categorization, several approaches such as regular machine learning techniques (K-mean bunching, Fuzzy C mean grouping etc.), Deep Learning-based approaches (CNN, ResNET, Dense Net, VGG etc.), classical algorithms (Snake contour, watershed method etc.), and hybridization approaches were applied, according to the analysis. Information base, for example, BRATS, Fig-Share, EPISURG or TCIA can be taken to gather clinical pictures which principally contains of 2 classifications, pre and post pictures of Brain tumor. The multiple processes of brain tumour segmentation methodologies, such as preprocessing, feature extraction, segmentation, and classification, are also explained in this work. The task of segmenting residual and recurrent tumors differs greatly from that of segmenting tumors on baseline scans before surgery. This study shows that each approach has its own set of pros and limitations, as well as notable findings in terms of precision, sensitivity, and specificity, according to the comparison research. The use of segmentation approaches to determine success and reliability has been discovered. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Source

Lecture Notes in Networks and Systems, Vol-417 LNNS, pp. 608-616.

Date

2022-01-01

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

BRATS; CNN; Dense net; EPISURG; Fig-Share; ResNET; TCIA; VGG

Coverage

Xavier P.S., Department of Computer Science, CHRIST (Deemed to be) University, Bangalore, India; Raju G., Department of Computer Science, CHRIST (Deemed to be) University, Bangalore, India; Asawthy S.U., Department of Computer Science, JYOTHI Engineering College Cheruthuruthy, Cheruthuruthy, India

Rights

Restricted Access

Relation

ISSN: 23673370; ISBN: 978-303096301-9

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-3-030-96302-6_57

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126236124&doi=10.1007%2f978-3-030-96302-6_57&partnerID=40&md5=a70f0c72effd925db9eb82b5008bd511