Diabetic retinopathy detection and classification by using deep learning

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.

Մատենագիտական մանրամասներ
Հիմնական հեղինակներ:	Hossain, Shahriar, Evan, Md. Nurusshafi, Farhin, Fariya Zakir, Nabil, Mashrur Karim, Sadman, Sameen
Այլ հեղինակներ:	Chakrabarty, Amitabha
Ձևաչափ:	Թեզիս
Լեզու:	English
Հրապարակվել է:	Brac University 2022
Խորագրեր:	Convolutional neural network Deep learning Diabetic retinopathy InceptionV3 Xception DenseNet-169 Cognitive learning theory (Deep learning) Neural networks (Computer science)
Առցանց հասանելիություն:	http://hdl.handle.net/10361/16810

id	10361-16810
record_format	dspace
spelling	10361-168102022-06-01T21:02:52Z Diabetic retinopathy detection and classification by using deep learning Hossain, Shahriar Evan, Md. Nurusshafi Farhin, Fariya Zakir Nabil, Mashrur Karim Sadman, Sameen Chakrabarty, Amitabha Department of Computer Science and Engineering, Brac University Convolutional neural network Deep learning Diabetic retinopathy InceptionV3 Xception DenseNet-169 Cognitive learning theory (Deep learning) Neural networks (Computer science) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 53-55). Eyes are the most sensitive part of a human being and it is one of the most challenging tasks for a computer-aided system to classify its diseases. Many visionthreatening diseases such as, Glaucoma and Diabetic Retinopathy are treated using digital fundus imaging and retinal images by the specialist at a primary level. However, a computer-aided system that can classify if the eye has a disease or not could be a handy tool for the specialists and a challenging task for computer aided system developers. A branch of machine learning which is deep learning is making a revolutionary impact on medical diagnosis using image processing and pattern recognition. Therefore, we aim to make use of some Convolutional Neural Network (CNN) architectures such as ResNet50, Inception V3, Xception, DenseNet-169 and MobileNetV3 Large to extract the features and classify if the eye has a disease or not using digital fundus photography and retinal image. For our research, we used a competition dataset available from Kaggle [1] and another dataset from IDRiD [2]. Our final dataset contained a total of 2,517 images with each stage having around 500 images in them. Upon training and testing the selected architectures, we have found that Inception V3 has an accuracy of 86.31% and 87.7% (with a lowered learning rate). Similarly for Xception, we attained 86.9% accuracy with default learning rate and 87.9% accuracy with lowered learning rate. ResNet50 gave an accuracy of 46.83%, MobileNetV3 Large gave the lowest accuracy standing at 23.81%. DenseNet-169 gave us the highest accuracy among all other models, soaring at 88.29% accuracy. Shahriar Hossain Md. Nurusshafi Evan Fariya Zakir Farhin Mashrur Karim Nabil Sameen Sadman B. Computer Science 2022-06-01T08:57:52Z 2022-06-01T08:57:52Z 2022 2022-01 Thesis ID 21141036 ID 18101525 ID 18101505 ID 19101659 ID 21341058 http://hdl.handle.net/10361/16810 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	Convolutional neural network Deep learning Diabetic retinopathy InceptionV3 Xception DenseNet-169 Cognitive learning theory (Deep learning) Neural networks (Computer science)
spellingShingle	Convolutional neural network Deep learning Diabetic retinopathy InceptionV3 Xception DenseNet-169 Cognitive learning theory (Deep learning) Neural networks (Computer science) Hossain, Shahriar Evan, Md. Nurusshafi Farhin, Fariya Zakir Nabil, Mashrur Karim Sadman, Sameen Diabetic retinopathy detection and classification by using deep learning
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
author2	Chakrabarty, Amitabha
author_facet	Chakrabarty, Amitabha Hossain, Shahriar Evan, Md. Nurusshafi Farhin, Fariya Zakir Nabil, Mashrur Karim Sadman, Sameen
format	Thesis
author	Hossain, Shahriar Evan, Md. Nurusshafi Farhin, Fariya Zakir Nabil, Mashrur Karim Sadman, Sameen
author_sort	Hossain, Shahriar
title	Diabetic retinopathy detection and classification by using deep learning
title_short	Diabetic retinopathy detection and classification by using deep learning
title_full	Diabetic retinopathy detection and classification by using deep learning
title_fullStr	Diabetic retinopathy detection and classification by using deep learning
title_full_unstemmed	Diabetic retinopathy detection and classification by using deep learning
title_sort	diabetic retinopathy detection and classification by using deep learning
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/16810
work_keys_str_mv	AT hossainshahriar diabeticretinopathydetectionandclassificationbyusingdeeplearning AT evanmdnurusshafi diabeticretinopathydetectionandclassificationbyusingdeeplearning AT farhinfariyazakir diabeticretinopathydetectionandclassificationbyusingdeeplearning AT nabilmashrurkarim diabeticretinopathydetectionandclassificationbyusingdeeplearning AT sadmansameen diabeticretinopathydetectionandclassificationbyusingdeeplearning
_version_	1814307933361537024

Diabetic retinopathy detection and classification by using deep learning

Նմանատիպ նյութեր