Decipherable classification of glaucoma using deep neural network leveraging XAI
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| Hoofdauteurs: | , , , |
|---|---|
| Andere auteurs: | |
| Formaat: | Thesis |
| Taal: | English |
| Gepubliceerd in: |
Brac University
2023
|
| Onderwerpen: | |
| Online toegang: | http://hdl.handle.net/10361/21820 |
| id |
10361-21820 |
|---|---|
| record_format |
dspace |
| spelling |
10361-218202023-10-15T21:02:31Z Decipherable classification of glaucoma using deep neural network leveraging XAI Chayan, Touhidul Islam Islam, Anita Tonny, Anika Rahman Rahman, Eftykhar Reza, MD Tanzim Department of Computer Science and Engineering, Brac University Glaucoma Blindness Diagnosis Neural network XAI Goal Glaucoma--diagnosis Ophthalmology--Developing countries 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 49-53). Glaucoma is the second driving reason for partial or complete blindness among all the visual deficiencies which mainly occurs because of excessive pressure in the eye due to anxiety or depression which damages the optic nerve and creates complications in vision. In this research, we used the Glaucoma Dataset in our algorithm to predict outcomes related to Glaucoma and non-glaucoma. The main goal of the author of this research was to develop an automated deep learning neural network architecture for early detection of Glaucoma disease. For the classification of glaucoma two Black Box models have been used in the paper. Fully Connected Neural Net-work (FCNNs) which is a Conventional Neural Network (CNN) composed of a fully connected layer. These Deep FCNN Black Box models have been described through Explainable Artificial Intelligence (XAI) to achieve the ultimate goal of our research. However, to serve our purpose we have used VGG-16, VGG-19, DenseNet121, In-ceptionV3 and ResNet50 Deep FCNNs models for our study. To begin with we pre-processed the images and grouped them into three sets: training, testing and validation. Afterwards, These models have been initialized with the pre-existing models trained on the ImageNet dataset. Conclusively, the training and evaluating of all the Deep FCNN has been done. The validation accuracy of our models we got are as follows: In InceptionV3 we got 86.4% accuracy, in DenseNet121 we got 86.8%accuracy, in ResNet50 we got 94.7% accuracy, in VGG-19 we got 93.3% accuracy and lastly in VGG-16 we got 88.6% accuracy. As follows, after 50 epochs, ResNet50 got the highest score among the other models with a validation accuracy of 94.7%. Afterwards, we compared all models’ accuracy and loss graph together, where we can see that VGG-19 and ResNet50 were the Good-Fit than the other models. As a result, our research achieved outstanding classification accuracy in a short period of time. However, it seems to be vital to understand that a human can rely on black-box level Deep Learning Models to make decisions. Throughout this work, a hybrid approach combining image processing with deep learning has been used with the support of XAI to assure reliable glaucoma detection at an early stage. Touhidul Islam Chayan Anita Islam Anika Rahman Tonny Eftykhar Rahman B.Sc. in Computer Science and Engineering 2023-10-15T09:04:02Z 2023-10-15T09:04:02Z ©2022 2022-01-18 Thesis ID 17101362 ID 17301021 ID 18101569 ID 18301041 http://hdl.handle.net/10361/21820 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. 65 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Glaucoma Blindness Diagnosis Neural network XAI Goal Glaucoma--diagnosis Ophthalmology--Developing countries |
| spellingShingle |
Glaucoma Blindness Diagnosis Neural network XAI Goal Glaucoma--diagnosis Ophthalmology--Developing countries Chayan, Touhidul Islam Islam, Anita Tonny, Anika Rahman Rahman, Eftykhar Decipherable classification of glaucoma using deep neural network leveraging XAI |
| 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 |
Reza, MD Tanzim |
| author_facet |
Reza, MD Tanzim Chayan, Touhidul Islam Islam, Anita Tonny, Anika Rahman Rahman, Eftykhar |
| format |
Thesis |
| author |
Chayan, Touhidul Islam Islam, Anita Tonny, Anika Rahman Rahman, Eftykhar |
| author_sort |
Chayan, Touhidul Islam |
| title |
Decipherable classification of glaucoma using deep neural network leveraging XAI |
| title_short |
Decipherable classification of glaucoma using deep neural network leveraging XAI |
| title_full |
Decipherable classification of glaucoma using deep neural network leveraging XAI |
| title_fullStr |
Decipherable classification of glaucoma using deep neural network leveraging XAI |
| title_full_unstemmed |
Decipherable classification of glaucoma using deep neural network leveraging XAI |
| title_sort |
decipherable classification of glaucoma using deep neural network leveraging xai |
| publisher |
Brac University |
| publishDate |
2023 |
| url |
http://hdl.handle.net/10361/21820 |
| work_keys_str_mv |
AT chayantouhidulislam decipherableclassificationofglaucomausingdeepneuralnetworkleveragingxai AT islamanita decipherableclassificationofglaucomausingdeepneuralnetworkleveragingxai AT tonnyanikarahman decipherableclassificationofglaucomausingdeepneuralnetworkleveragingxai AT rahmaneftykhar decipherableclassificationofglaucomausingdeepneuralnetworkleveragingxai |
| _version_ |
1814307669370994688 |