Deep learning based medical X-ray image recognition and classification
This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018.
מחבר ראשי: | |
---|---|
מחברים אחרים: | |
פורמט: | Thesis |
שפה: | English |
יצא לאור: |
BRAC University
2019
|
נושאים: | |
גישה מקוונת: | http://hdl.handle.net/10361/11426 |
id |
10361-11426 |
---|---|
record_format |
dspace |
spelling |
10361-114262022-01-26T10:19:58Z Deep learning based medical X-ray image recognition and classification Khan, Md. Rakib Hossain Amitabha Chakrabarty Department of Computer Science and Engineering, BRAC University Image processing. Pattern recognition systems. Image processing. This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018. Includes bibliographical references (page 25). Cataloged from PDF version of thesis. Analysis of radiology images are mostly being done by medical specialists, as it is a critical sector and people expect highest level of care and service regardless of cost. Though, it is quite limited due to its complexity and subjectivity of the images. Extensive variation exists across different interpreters and fatigue in terms of image interpretation by human experts. Our primary objective is to analyze medical X-ray images using deep learning and exploit images using Pandas, Keras, OpenCV, TensorFlow etc. to achieve classification of diseases like Atelectasis, Consolidation, Cardiomegaly, Edema, Effusion, Emphysema, Fibrosis, Hernia, Infiltration, Mass, Nodule, Pleural, Pneumonia, Pneumothorax, Thickening etc. We have used Convolutional Neural Networks (CNN) algorithm because CNN based deep learning classification approaches have ability to automatically extract the high level representations from big data using little pre-processing compared to other image classification algorithms. Ultimately, our simple and efficient model will lead clinicians towards better diagnostic decisions for patients to provide them solutions with good accuracy for medical imaging. Keywords: Convolutional Neural Networks (CNN), X-ray, Deep Learning, Pandas, Keras, Radiography, TensorFlow, OpenCV and Artificial Intelligence. Md. Rakib Hossain Khan B. Computer Science and Engineering 2019-02-18T03:45:12Z 2019-02-18T03:45:12Z 2018 2018-12 Thesis ID 14301110 http://hdl.handle.net/10361/11426 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. 25 pages application/pdf BRAC University |
institution |
Brac University |
collection |
Institutional Repository |
language |
English |
topic |
Image processing. Pattern recognition systems. Image processing. |
spellingShingle |
Image processing. Pattern recognition systems. Image processing. Khan, Md. Rakib Hossain Deep learning based medical X-ray image recognition and classification |
description |
This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018. |
author2 |
Amitabha Chakrabarty |
author_facet |
Amitabha Chakrabarty Khan, Md. Rakib Hossain |
format |
Thesis |
author |
Khan, Md. Rakib Hossain |
author_sort |
Khan, Md. Rakib Hossain |
title |
Deep learning based medical X-ray image recognition and classification |
title_short |
Deep learning based medical X-ray image recognition and classification |
title_full |
Deep learning based medical X-ray image recognition and classification |
title_fullStr |
Deep learning based medical X-ray image recognition and classification |
title_full_unstemmed |
Deep learning based medical X-ray image recognition and classification |
title_sort |
deep learning based medical x-ray image recognition and classification |
publisher |
BRAC University |
publishDate |
2019 |
url |
http://hdl.handle.net/10361/11426 |
work_keys_str_mv |
AT khanmdrakibhossain deeplearningbasedmedicalxrayimagerecognitionandclassification |
_version_ |
1814309037426081792 |