A state-of-the-art technique to perform cloud-based semantic segmentation using deep learning 3D U-Net architecture

Glioma is the most aggressive and dangerous primary brain tumor with a survival time of less than 14 months. Segmentation of tumors is a necessary task in the image processing of the gliomas and is important for its timely diagnosis and starting a treatment. Using 3D U-net architecture to perform se...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 23; no. 1; pp. 251 - 21
Main Authors: Shaukat, Zeeshan, Farooq, Qurat ul Ain, Tu, Shanshan, Xiao, Chuangbai, Ali, Saqib
Format: Journal Article
Language:English
Published: London BioMed Central 24.06.2022
Springer Nature B.V
BMC
Subjects:
3D U-Net
Accuracy
Algorithms
Bioinformatics
Biomedical and Life Sciences
Brain
Brain cancer
Brain Neoplasms - diagnostic imaging
Brain Neoplasms - pathology
Brain tumor
Brain tumors
Cloud Computing
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Datasets
Deep Learning
Experiments
Glioma
Humans
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Life Sciences
Literature reviews
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Mathematical analysis
Medical diagnosis
Methods
Microarrays
Neural networks
Optimization
Semantic segmentation
Semantics
Tomography
Traumatic brain injury
Tumors
Deep learning
Brain tumor
Cloud computing
Semantic segmentation
3D U-Net
ISSN:1471-2105, 1471-2105
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Glioma is the most aggressive and dangerous primary brain tumor with a survival time of less than 14 months. Segmentation of tumors is a necessary task in the image processing of the gliomas and is important for its timely diagnosis and starting a treatment. Using 3D U-net architecture to perform semantic segmentation on brain tumor dataset is at the core of deep learning. In this paper, we present a unique cloud-based 3D U-Net method to perform brain tumor segmentation using BRATS dataset. The system was effectively trained by using Adam optimization solver by utilizing multiple hyper parameters. We got an average dice score of 95% which makes our method the first cloud-based method to achieve maximum accuracy. The dice score is calculated by using Sørensen-Dice similarity coefficient. We also performed an extensive literature review of the brain tumor segmentation methods implemented in the last five years to get a state-of-the-art picture of well-known methodologies with a higher dice score. In comparison to the already implemented architectures, our method ranks on top in terms of accuracy in using a cloud-based 3D U-Net framework for glioma segmentation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-022-04794-9