3D Brain image segmentation using 3D tiled convolution neural networks

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Podrobná bibliografie
Hlavní autoři:	Haque, Md Mahibul, Ria, Jobeda Khanam, Mannan, Fahad Al, Majumder, Sadman, Uddin, Md Reaz
Další autoři:	Alam,Md. Ashraful
Médium:	Diplomová práce
Jazyk:	English
Vydáno:	Brac University 2024
Témata:	Deep learning 3D tiled convolution MRI Segmentation Data mining 3-D(Three-dimensional imaging) Magnetic resonance imaging
On-line přístup:	http://hdl.handle.net/10361/23542

id	10361-23542
record_format	dspace
spelling	10361-235422024-06-24T21:01:16Z 3D Brain image segmentation using 3D tiled convolution neural networks Haque, Md Mahibul Ria, Jobeda Khanam Mannan, Fahad Al Majumder, Sadman Uddin, Md Reaz Alam,Md. Ashraful Department of Computer Science and Engineering, Brac University Deep learning 3D tiled convolution MRI Segmentation Data mining 3-D(Three-dimensional imaging) Magnetic resonance imaging This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 41-44). Gliomas are the primary brain tumors that are most commonly observed in adult patients and exhibit varying degrees of aggressiveness and prognosis. The accurate identification and diagnosis of Gliomas in surgical procedures heavily rely on the acquisition of precise segmentation results, which involve delineating the tumor region from magnetic resonance imaging (MRI) scans of the brain. The segmentation process in conventional 3D CNN methods is often reliant on patch processing as a result of the limitations in GPU memory. This paper presents an approach for segmenting brain tumors into distinct subregions, namely the WT, TC, and ET, utilizing a 3D tiled convolution-based segmentation method. The utilization of the 3DTC method enables the inclusion of larger patch sizes without requiring hardware with high GPU memory. This study presents three significant modifications to the standard 3D U-Net. Firstly, we incorporate 3D tiled convolution as the initial layer in our proposed models. Secondly, we substitute the trilinear upsampling layer with a dense upsampling convolution layer. Lastly, we replace the standard convolution block with recurrent residual blocks in the proposed R2AU-Net. The best framework was utilized to apply an average ensembling technique, aiming to achieve accurate results on the validation set of the BraTS 2020 dataset. The network proposed in this study was utilized for the analysis of the BraTS 2020 dataset. The evaluation of our method on the validation dataset yielded Dice scores of 90.76%, 83.39%, and 74.77% for the WT, TC, and ET regions, respectively. Md Mahibul Haque Jobeda Khanam Ria Fahad Al Mannan Sadman Majumder Md Reaz Uddin B.Sc in Computer Science 2024-06-24T06:13:28Z 2024-06-24T06:13:28Z ©2023 2023-09 Thesis ID 20101503 ID 20101217 ID 20101155 ID 20101224 ID 20101228 http://hdl.handle.net/10361/23542 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 55 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Deep learning 3D tiled convolution MRI Segmentation Data mining 3-D(Three-dimensional imaging) Magnetic resonance imaging
spellingShingle	Deep learning 3D tiled convolution MRI Segmentation Data mining 3-D(Three-dimensional imaging) Magnetic resonance imaging Haque, Md Mahibul Ria, Jobeda Khanam Mannan, Fahad Al Majumder, Sadman Uddin, Md Reaz 3D Brain image segmentation using 3D tiled convolution neural networks
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.
author2	Alam,Md. Ashraful
author_facet	Alam,Md. Ashraful Haque, Md Mahibul Ria, Jobeda Khanam Mannan, Fahad Al Majumder, Sadman Uddin, Md Reaz
format	Thesis
author	Haque, Md Mahibul Ria, Jobeda Khanam Mannan, Fahad Al Majumder, Sadman Uddin, Md Reaz
author_sort	Haque, Md Mahibul
title	3D Brain image segmentation using 3D tiled convolution neural networks
title_short	3D Brain image segmentation using 3D tiled convolution neural networks
title_full	3D Brain image segmentation using 3D tiled convolution neural networks
title_fullStr	3D Brain image segmentation using 3D tiled convolution neural networks
title_full_unstemmed	3D Brain image segmentation using 3D tiled convolution neural networks
title_sort	3d brain image segmentation using 3d tiled convolution neural networks
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/23542
work_keys_str_mv	AT haquemdmahibul 3dbrainimagesegmentationusing3dtiledconvolutionneuralnetworks AT riajobedakhanam 3dbrainimagesegmentationusing3dtiledconvolutionneuralnetworks AT mannanfahadal 3dbrainimagesegmentationusing3dtiledconvolutionneuralnetworks AT majumdersadman 3dbrainimagesegmentationusing3dtiledconvolutionneuralnetworks AT uddinmdreaz 3dbrainimagesegmentationusing3dtiledconvolutionneuralnetworks
_version_	1814307445126725632

3D Brain image segmentation using 3D tiled convolution neural networks

Podobné jednotky