Improve the Diagnosis on Fundus Photography with Deep Transfer Learning

Improve the Diagnosis on Fundus Photography with Deep Transfer Learning

Bibliographic Details
Main Author: Guo, Chen
Language:English
Published: Case Western Reserve University School of Graduate Studies / OhioLINK 2021
Subjects:
Artificial Intelligence
Computer Science
Bioinformatics
fundus photography
deep Learning
transfer learning
visualization
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=case1621674781655785
id ndltd-OhioLink-oai-etd.ohiolink.edu-case1621674781655785
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-case16216747816557852021-12-01T05:17:24Z Improve the Diagnosis on Fundus Photography with Deep Transfer Learning Guo, Chen Artificial Intelligence Computer Science Bioinformatics fundus photography deep Learning transfer learning visualization Fundus photography-based eye disease prediction attracted great attention since breakthroughs in deep convolutional neuron networks (DCNNs). However, the performance of existing studies focusing on identifying the right disease among several candidates,which is close to clinical diagnosis in practice,is at most mediocre. Moreover, obtaining large labeled dataset is difficult due to privacy concerns, resulting in the infeasibility to train huge DCNNs. Hence, we propose to utilize a lightweight deep learning architecture (MobileNetV2) and transfer learning to distinguish four eye diseases from normal controls using a small dataset. A visualization approach is also applied to highlight the loci for the predicted label, which may give some hints for further fundus image studies. Our experimental results show that our system achieves an average accuracy of 96.2%, sensitivity of 90.4%, and specificity of 97.6% via five independent runs, and outperforms two other deep learning based algorithms both in accuracy and efficiency. 2021-06-21 English text Case Western Reserve University School of Graduate Studies / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=case1621674781655785 http://rave.ohiolink.edu/etdc/view?acc_num=case1621674781655785 unrestricted This thesis or dissertation is protected by copyright: some rights reserved. It is licensed for use under a Creative Commons license. Specific terms and permissions are available from this document's record in the OhioLINK ETD Center.
collection NDLTD
language English
sources NDLTD
topic Artificial Intelligence
Computer Science
Bioinformatics
fundus photography
deep Learning
transfer learning
visualization
spellingShingle Artificial Intelligence
Computer Science
Bioinformatics
fundus photography
deep Learning
transfer learning
visualization
Guo, Chen
Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
author Guo, Chen
author_facet Guo, Chen
author_sort Guo, Chen
title Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
title_short Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
title_full Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
title_fullStr Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
title_full_unstemmed Improve the Diagnosis on Fundus Photography with Deep Transfer Learning
title_sort improve the diagnosis on fundus photography with deep transfer learning
publisher Case Western Reserve University School of Graduate Studies / OhioLINK
publishDate 2021
url http://rave.ohiolink.edu/etdc/view?acc_num=case1621674781655785
work_keys_str_mv AT guochen improvethediagnosisonfundusphotographywithdeeptransferlearning
_version_ 1723963320495505408

Similar Items