Analysis of transformer and CNN based approaches for classifying renal abnormality from image data

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.

Bibliographic Details
Main Authors:	Reza, S. M. Mushfiq, Hasnath, Abu Bakar, Roy, Ankita, Rahman, Amreen, Faruk, Abdullah Bin
Other Authors:	Reza, Md. Tanzim
Format:	Thesis
Language:	English
Published:	Brac University 2024
Subjects:	Deep learning Convolutional neural networks Renal abnormality Transformers Deep learning. Kidney > Abnormalities.
Online Access:	http://hdl.handle.net/10361/24017

id	10361-24017
record_format	dspace
spelling	10361-240172024-09-10T06:35:07Z Analysis of transformer and CNN based approaches for classifying renal abnormality from image data Reza, S. M. Mushfiq Hasnath, Abu Bakar Roy, Ankita Rahman, Amreen Faruk, Abdullah Bin Reza, Md. Tanzim Sadeque, Farig Yousuf Department of Computer Science and Engineering, Brac University Deep learning Convolutional neural networks Renal abnormality Transformers Deep learning. Kidney--Abnormalities. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 40-42). There is a pressing need to revise the current diagnostic framework for renal abnor mality due to the projected increase in its global prevalence as about 10% of people worldwide are suffering from renal diseases. Recognizing the escalating trends of renal disease, proactive measures are warranted to overcome upcoming challenges in accurate diagnosis and management. Renal abnormalities, often symptomless and hard to diagnose, can be dangerous but curable if detected early. Therefore, machine learning and deep learning techniques can be instrumental if implemented correctly to determine this anomaly early in this modern time. Our approach for renal abnormality detection from image data incorporates the topologies of Con volutional Neural Networks and transformer-based image classification topologies, as well as data augmentation methods and precise hyperparameter tuning (learn ing rate, batch size, dropout rate, regularization strength, etc.); additionally, we proposed CNN-based and transformer-based architectures for renal abnormality de tection. Transformer-based deep learning methods are the latest trend in classify ing diseases from medical images; for this reason, we analyzed the performance of CNN-based architectures and transformer-based architectures. We build a hybrid binary class dataset of Computed Tomography(CT) scan renal images using pri mary data collected from Kidney Foundation Hospital & Research Institute, Dhaka, Bangladesh and secondary data from publicly available online source. Our approach is a sequence of steps that allows for the abnormality detection using state-of-the art classifiers ResNet50, Inception ResNetV2, InceptionV3 and VGG16 along with our proposed ResNet152 based custom model and ViT architecture-based custom model without manual intervention. Our experimental results showed that our pro posed transformer-based model achieved the highest accuracy of 99.99% while our proposed CNN model achieved an accuracy of 99.97%. Among the four pre-trained CNN models, ResNet50 scored the highest accuracy of 99.95%, and VGG16 scored 99.92%, InceptionResNetV2 was able to score 98.87%, while the lowest performance was shown by the InceptionV3 model, which was 96.87%. All four pre-trained mod els have demonstrated acceptable performance, and our proposed model was able to perform better than state-of-the-art prepared models. S. M. Mushfiq Reza Abu Bakar Hasnath Ankita Roy Amreen Rahman Abdullah Bin Faruk B.Sc in Computer Science 2024-09-08T10:20:13Z 2024-09-08T10:20:13Z 2024-06 Thesis ID 20101254 ID 20301037 ID 23141059 ID 20301479 ID 23341108 http://hdl.handle.net/10361/24017 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. 42 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Deep learning Convolutional neural networks Renal abnormality Transformers Deep learning. Kidney--Abnormalities.
spellingShingle	Deep learning Convolutional neural networks Renal abnormality Transformers Deep learning. Kidney--Abnormalities. Reza, S. M. Mushfiq Hasnath, Abu Bakar Roy, Ankita Rahman, Amreen Faruk, Abdullah Bin Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.
author2	Reza, Md. Tanzim
author_facet	Reza, Md. Tanzim Reza, S. M. Mushfiq Hasnath, Abu Bakar Roy, Ankita Rahman, Amreen Faruk, Abdullah Bin
format	Thesis
author	Reza, S. M. Mushfiq Hasnath, Abu Bakar Roy, Ankita Rahman, Amreen Faruk, Abdullah Bin
author_sort	Reza, S. M. Mushfiq
title	Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
title_short	Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
title_full	Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
title_fullStr	Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
title_full_unstemmed	Analysis of transformer and CNN based approaches for classifying renal abnormality from image data
title_sort	analysis of transformer and cnn based approaches for classifying renal abnormality from image data
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/24017
work_keys_str_mv	AT rezasmmushfiq analysisoftransformerandcnnbasedapproachesforclassifyingrenalabnormalityfromimagedata AT hasnathabubakar analysisoftransformerandcnnbasedapproachesforclassifyingrenalabnormalityfromimagedata AT royankita analysisoftransformerandcnnbasedapproachesforclassifyingrenalabnormalityfromimagedata AT rahmanamreen analysisoftransformerandcnnbasedapproachesforclassifyingrenalabnormalityfromimagedata AT farukabdullahbin analysisoftransformerandcnnbasedapproachesforclassifyingrenalabnormalityfromimagedata
_version_	1814307377404444672

Analysis of transformer and CNN based approaches for classifying renal abnormality from image data

Similar Items