An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.
| Автори: | , , , , |
|---|---|
| Інші автори: | |
| Формат: | Дисертація |
| Мова: | English |
| Опубліковано: |
Brac University
2024
|
| Предмети: | |
| Онлайн доступ: | http://hdl.handle.net/10361/22888 |
| id |
10361-22888 |
|---|---|
| record_format |
dspace |
| spelling |
10361-228882024-05-20T21:04:49Z An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM Bhuiyan, Mahdi Hasan Haldar, Sumit Chowdhury, Maisha Shabnam Bushra, Nazifa Jilan, Tahsin Zaman Alam, Md. Ashraful Department of Computer Science and Engineering, Brac University Disease detection Ocular diseases screening GradCAM Deep learning Vision transformers Retinal diseases Neural networks (Computer science) Eye--Diseases Deep learning (Machine learning) 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 33-36). Early detection of retinal diseases can help people avoid going completely or partially blind. In this research, we will be implementing an interpretable diagnosis of retinal diseases using a hybrid model containing VGG-16 and Swin Transformer and then visualize with Grad-CAM. Using Optical Coherence Tomography (OCT) Images gathered from various sources, a unique multi-label classification approach is developed in this study for the diagnosis of various retinal diseases. For the research, a transformer-like hybrid architecture will be used, which is Vision Transformer that works by classifying images. Recent developments in competitive architecture for image classification include the original concept of Transformers. The implication of this architecture is done over patches of images often called visual tokens. It can handle different data modality. A ViT employs several embedding and tokenization techniques. In order to accurately highlight key areas in pictures, the gradient-weighted class activation mapping, known as (Grad-CAM) technique has been used so that deep model prediction can be obtained in image classification, image captioning and several other tasks. It explains network decisions by using the gradients in back-propagation as weights. We used both VGG-16 that is a variant of Convolutional Neural Networks (CNN) and Swin Transformers in our model. We combined these two and introduced a hybrid model. After being tested, the VGG-16 component’s output accuracy was 0.8888, while the Vision Transformer component’s accuracy was 0.9139. Then the hybrid model was tested after some fine tuning and it performed extraordinarily. The output accuracy of the hybrid model is 0.988. Mahdi Hasan Bhuiyan Sumit Haldar Maisha Shabnam Chowdhury Nazifa Bushra Tahsin Zaman Jilan B.Sc in Computer Science 2024-05-20T06:48:30Z 2024-05-20T06:48:30Z ©2024 2024-01 Thesis ID: 20101541 ID: 20101544 ID: 20101459 ID: 20101536 ID: 20101581 http://hdl.handle.net/10361/22888 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. 41 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Disease detection Ocular diseases screening GradCAM Deep learning Vision transformers Retinal diseases Neural networks (Computer science) Eye--Diseases Deep learning (Machine learning) |
| spellingShingle |
Disease detection Ocular diseases screening GradCAM Deep learning Vision transformers Retinal diseases Neural networks (Computer science) Eye--Diseases Deep learning (Machine learning) Bhuiyan, Mahdi Hasan Haldar, Sumit Chowdhury, Maisha Shabnam Bushra, Nazifa Jilan, Tahsin Zaman An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024. |
| author2 |
Alam, Md. Ashraful |
| author_facet |
Alam, Md. Ashraful Bhuiyan, Mahdi Hasan Haldar, Sumit Chowdhury, Maisha Shabnam Bushra, Nazifa Jilan, Tahsin Zaman |
| format |
Thesis |
| author |
Bhuiyan, Mahdi Hasan Haldar, Sumit Chowdhury, Maisha Shabnam Bushra, Nazifa Jilan, Tahsin Zaman |
| author_sort |
Bhuiyan, Mahdi Hasan |
| title |
An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| title_short |
An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| title_full |
An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| title_fullStr |
An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| title_full_unstemmed |
An interpretable diagnosis of retinal diseases using vision transformer and Grad-CAM |
| title_sort |
interpretable diagnosis of retinal diseases using vision transformer and grad-cam |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/22888 |
| work_keys_str_mv |
AT bhuiyanmahdihasan aninterpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT haldarsumit aninterpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT chowdhurymaishashabnam aninterpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT bushranazifa aninterpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT jilantahsinzaman aninterpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT bhuiyanmahdihasan interpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT haldarsumit interpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT chowdhurymaishashabnam interpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT bushranazifa interpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam AT jilantahsinzaman interpretablediagnosisofretinaldiseasesusingvisiontransformerandgradcam |
| _version_ |
1814309664835239936 |