Optimal transport theory based GAN for medical image augmentation and classification

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

Bibliografiske detaljer
Main Authors:	Siddiki Shan, Md. Abdul Kahhar, Quaiyum, Md. Abdul, Saha, Sugata, Nayer Anik, S. M. Navin
Andre forfattere:	Rabiul Alam, Dr. Md. Golam
Format:	Thesis
Sprog:	English
Udgivet:	Brac University 2023
Fag:	Optimal Transport(OT) Theory Generative Adversarial Networks (GANs) Unsupervised neural networks Wasserstein distance Maximum Mean Discrepancy(MMD) Chest X-Ray Covid-19 Viral pneumonia Lung opacity Natural language processing (Computer science) Machine learning
Online adgang:	http://hdl.handle.net/10361/19232

id	10361-19232
record_format	dspace
spelling	10361-192322023-08-01T21:02:04Z Optimal transport theory based GAN for medical image augmentation and classification Siddiki Shan, Md. Abdul Kahhar Quaiyum, Md. Abdul Saha, Sugata Nayer Anik, S. M. Navin Rabiul Alam, Dr. Md. Golam Department of Computer Science and Engineering, Brac University Optimal Transport(OT) Theory Generative Adversarial Networks (GANs) Unsupervised neural networks Wasserstein distance Maximum Mean Discrepancy(MMD) Chest X-Ray Covid-19 Viral pneumonia Lung opacity Natural language processing (Computer science) Machine learning 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 45-47). Unsupervised neural networks called Generative Adversarial Networks (GANs) are used to provide realistic pictures without relying on the original data. Due to dis parities in illness occurrence, the challenge of class imbalance is prevalent in the medical area, making the development of these applications tough. In order to solve the issue of class imbalance, several GAN-based approaches have been presented. However, since extracting significant information from just a few pixels is laborious, these designs have not effectively trained for small-scale disorders. To address the difficulty of insufficient quantities and imbalances of medical imaging data, data augmentation methods such as image modifications have been utilized to minimize performance degradation. Optimal Transport (OT) theory allows for the develop ment of a geometry for a space of functions, providing a definition of distance in this space, a technique for interpolating between various functions, and, in a more general sense, establishing the barycenter of a family of weighted functions. Con sequently, optimal transport is presented as a fundamental tool in many applied domains. Measures with non-overlapping supports are well-suited to occupational therapy. However, using OT to train generative machines raises challenges like (1) a lack of smoothness, (2) the computational burden of evaluating OT losses, and (3) the difficulty of estimating gradients in high dimensions. Because of this, Skinhorn divergence will be utilized to create a loss family that includes both Wasserstein (OT) and Maximum Mean Discrepancy (MMD) losses. It will help us identify a sweet spot by utilizing OT’s geometry and generating high-dimensional spaces from low-dimensional manifolds. Applications of the transport map for image augmenta tion and classification include computing geodesics between pictures and transferring one image’s attributes to another. The nature of the seen items must be preserved in this situation in order to create pictures that are both physically and aesthetically convincing. Our proposed Optimal Transport Theory-based GAN model is able to detect and differentiate between chest X-ray images with a high degree of accu racy. The proposed method of image augmentation was used for the classification of normal, COVID-19-effected, lung opacity, and viral pneumonia images. In terms of accuracy, precision, recall, and f1 score, which are all tested in this paper, our proposed Optimal Transport Theory-based GAN model performs comparably on the available datasets. The suggested model is accurate to 96.94%, which is greater than any of the experimental results of CNN models utilized in this research due to the fact that the recommended model was developed. Md. Abdul Kahhar Siddiki Shan Md. Abdul Quaiyum Sugata Saha S. M. Navin Nayer Anik B. Computer Science 2023-08-01T06:03:39Z 2023-08-01T06:03:39Z 2023 2023-01 Thesis ID: 18301221 ID: 18301195 ID: 18301089 ID: 18301189 http://hdl.handle.net/10361/19232 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. 47 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Optimal Transport(OT) Theory Generative Adversarial Networks (GANs) Unsupervised neural networks Wasserstein distance Maximum Mean Discrepancy(MMD) Chest X-Ray Covid-19 Viral pneumonia Lung opacity Natural language processing (Computer science) Machine learning
spellingShingle	Optimal Transport(OT) Theory Generative Adversarial Networks (GANs) Unsupervised neural networks Wasserstein distance Maximum Mean Discrepancy(MMD) Chest X-Ray Covid-19 Viral pneumonia Lung opacity Natural language processing (Computer science) Machine learning Siddiki Shan, Md. Abdul Kahhar Quaiyum, Md. Abdul Saha, Sugata Nayer Anik, S. M. Navin Optimal transport theory based GAN for medical image augmentation and classification
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	Rabiul Alam, Dr. Md. Golam
author_facet	Rabiul Alam, Dr. Md. Golam Siddiki Shan, Md. Abdul Kahhar Quaiyum, Md. Abdul Saha, Sugata Nayer Anik, S. M. Navin
format	Thesis
author	Siddiki Shan, Md. Abdul Kahhar Quaiyum, Md. Abdul Saha, Sugata Nayer Anik, S. M. Navin
author_sort	Siddiki Shan, Md. Abdul Kahhar
title	Optimal transport theory based GAN for medical image augmentation and classification
title_short	Optimal transport theory based GAN for medical image augmentation and classification
title_full	Optimal transport theory based GAN for medical image augmentation and classification
title_fullStr	Optimal transport theory based GAN for medical image augmentation and classification
title_full_unstemmed	Optimal transport theory based GAN for medical image augmentation and classification
title_sort	optimal transport theory based gan for medical image augmentation and classification
publisher	Brac University
publishDate	2023
url	http://hdl.handle.net/10361/19232
work_keys_str_mv	AT siddikishanmdabdulkahhar optimaltransporttheorybasedganformedicalimageaugmentationandclassification AT quaiyummdabdul optimaltransporttheorybasedganformedicalimageaugmentationandclassification AT sahasugata optimaltransporttheorybasedganformedicalimageaugmentationandclassification AT nayeraniksmnavin optimaltransporttheorybasedganformedicalimageaugmentationandclassification
_version_	1814308396891897856

Optimal transport theory based GAN for medical image augmentation and classification

Lignende værker