A novel depth search based light weight CAR network for the segmentation of brain tumour from MR images

Tankala, Sreekar; Pavani, Geetha; Biswal, Birendra; Siddartha, G.; Sahu, Gupteswar; Subrahmanyam, N.B.V.; Aakash, S.

doi:10.1016/j.neuri.2022.100105

Cited by 3 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The brain is a major organ consisting of nerve cells with supporting tissues such as glial cells as well as meninges. Damage to these specific brain subparts is irreversible and can lead to severe conditions, including life-threatening brain tumors [1]. Brain tumors are formed by abnormal shouldn't concentrate only on creating a model that learns and does the segmentation autonomously.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Based Effective Model for Brain Tumor Segmentation and Classification Using MRI Images

T.,

2023

JAIT

View full text Add to dashboard Cite

cells that develop in the human brain [2]. The present occurrence of malignant tumors is excessive, which has a significant impact on persons as well as the community [3−6]. The most essential clinical image method for detecting brain cancers is Magnetic Resonance Imaging (MRI). MRI seems to be a secure as well as noninvasive diagnosis technology that delivers more sufficient data on brain tissues than computed tomography scans [7−9]. The precise segmentation of brain tumors from clinical images are required to give a statistical and understandable guideline for medical diagnosis and therapy of disorders [10]. As a result, precise segmentation of brain tumors is an important phase in brain tumor diagnosis and therapy [11]. However, the precise segmentation of brain tumors is still considered a highly difficult process, because of various reasons such as changes in tumor form, size, and location, hazy borders [12], and so on. In recent decades, some brain tumor segmentation approaches have been presented. Traditional techniques based on handmade features as well as Machine Learning (ML) models: Support Vector Machines (SVMs) and Random Forests (RFs) typically perform poorly [13]. Deep Learning (DL) approaches for the segmentation of medical images have attracted a lot of interest in current decades, due to many studies with remarkable results for detecting and estimating target structures in images [14]. The level of user engagement with the system and the ease of use of segmentation methods often influence their adoption in medical applications. Manual brain tumor segmentation is a timeconsuming method that requires researchers to physically identify the Region of Interest (ROI) on MRI segments utilizing advanced graphical user interface tools. Manual segmentation requires a lot of time [15] and is vulnerable to user errors, which include inter and intra-variations. An autonomous approach for brain tumor segmentation might reduce the limitations of human errors while being immune to external influences which include disturbances as well as the physician's mental state. Under the related works area, current studies have developed several efficient automatic systems. As a result, a practitioner constructing an autonomous segmentation system really Manuscript

show abstract

Section: Introductionmentioning

confidence: 99%