RUcore: Rutgers University Community Repository
ResNet + LSTM method for age-related macular degeneration and diabetic retinopathy diagnosis on OCT images
Descriptive
TitleInfo
Title
ResNet + LSTM method for age-related macular degeneration and diabetic retinopathy diagnosis on OCT images
Name
(type = personal)
NamePart
(type = family)
Sun
NamePart
(type = given)
Shichen
DisplayForm
Shichen Sun
Role
RoleTerm
(authority = RULIB)
author
Name
(type = personal)
NamePart
(type = family)
Metaxas
NamePart
(type = given)
Dimitris N.
DisplayForm
Dimitris N. Metaxas
Affiliation
Advisory Committee
Role
RoleTerm
(authority = RULIB)
chair
Name
(type = personal)
NamePart
(type = family)
Michmizos
NamePart
(type = given)
Konstantinos
DisplayForm
Konstantinos Michmizos
Affiliation
Advisory Committee
Role
RoleTerm
(authority = RULIB)
internal member
Name
(type = personal)
NamePart
(type = family)
Melo
NamePart
(type = given)
Gerard de
DisplayForm
Gerard de Melo
Affiliation
Advisory Committee
Role
RoleTerm
(authority = RULIB)
internal member
Name
(type = corporate)
NamePart
Rutgers University
Role
RoleTerm
(authority = RULIB)
degree grantor
Name
(type = corporate)
NamePart
School of Graduate Studies
Role
RoleTerm
(authority = RULIB)
school
TypeOfResource
Text
Genre
(authority = marcgt)
theses
Genre
(authority = ExL-Esploro)
ETD graduate
OriginInfo
DateCreated
(qualifier = exact);
(encoding = w3cdtf);
(keyDate = yes)
2021
DateOther
(type = degree);
(qualifier = exact);
(encoding = w3cdtf)
2021-01
Language
LanguageTerm
(authority = ISO 639-3:2007);
(type = text)
English
Abstract
(type = abstract)
With the fast development of medical image devices and technologies, the amount of medical image data has increased significantly at a unprecedented rate. In many clinical specialities, there can be a shortage of doctors and radiologist experts to give timely diagnosis and referral to patients when facing the large amount of medical images and data. Especially for the ophthalmology, the widespread availability of optical coherence tomography (OCT), which is a novel medical imaging technology that allow acquisition of cross-sectional images of the retina with semihistologic resolution, has not been matched by the availability of human experts to interpret scans and provide appropriate treatments. According to the National Reporting and Learning System (NRLS), there are about 250 cases of sight harm due to the diagnosis delay per year in UK. Hence, how can we improve the efficiency of clinical diagnosis is a urgent problem need to be solved.
In this dissertation, we are going to present a method for classifying normal, diabetic retinopathy (DR) and age-related macular degeneration (AMD) on OCT scan sequences. Different from classic medical image classification problems, OCT is a crosssectional image sequences of eye fundus. The lesions of DR and AMD can be spatial related among OCT slices. To solve this problem and find the feature connection between OCT slices, we proposed a model that contains two neural networks. The first model is a residual neural network, which is used for extract symptom features on each OCT slices. The feature extract from each slices are combined to a series feature as the second model input. The second model is a long short-term memory neural network used for get the predictions based on OCT sequence feature. The model was trained and tested on around 1700 OCT scans, each of them has 25 slice images (Total 36149 slices). We used cross-entropy loss and k-cross validation. The result shows it has a accuracy of 1, 1, 1 on three class, respectively, when choosing the best model.
In this dissertation, we are going to present a method for classifying normal, diabetic retinopathy (DR) and age-related macular degeneration (AMD) on OCT scan sequences. Different from classic medical image classification problems, OCT is a crosssectional image sequences of eye fundus. The lesions of DR and AMD can be spatial related among OCT slices. To solve this problem and find the feature connection between OCT slices, we proposed a model that contains two neural networks. The first model is a residual neural network, which is used for extract symptom features on each OCT slices. The feature extract from each slices are combined to a series feature as the second model input. The second model is a long short-term memory neural network used for get the predictions based on OCT sequence feature. The model was trained and tested on around 1700 OCT scans, each of them has 25 slice images (Total 36149 slices). We used cross-entropy loss and k-cross validation. The result shows it has a accuracy of 1, 1, 1 on three class, respectively, when choosing the best model.
Subject
(authority = local)
Topic
Machine learning
Subject
(authority = LCSH)
Topic
Optical coherence tomography
Subject
(authority = RUETD)
Topic
Computer Science
RelatedItem
(type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Identifier
(type = RULIB)
ETD
Identifier
ETD_10472
PhysicalDescription
Form
(authority = gmd)
InternetMediaType
application/pdf
InternetMediaType
text/xml
Extent
1 online resource (vii, 16 pages) : illustrations
Note
(type = degree)
M.S.
Note
(type = bibliography)
Includes bibliographical references
RelatedItem
(type = host)
TitleInfo
Title
School of Graduate Studies Electronic Theses and Dissertations
Identifier
(type = local)
rucore10001600001
Location
PhysicalLocation
(authority = marcorg);
(displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier
(type = doi)
doi:10.7282/t3-42qf-9750
Back to the top
Rights
RightsDeclaration
(ID = rulibRdec0006)
The author owns the copyright to this work.
RightsHolder
(type = personal)
Name
FamilyName
Sun
GivenName
Shichen
Role
Copyright Holder
RightsEvent
Type
Permission or license
DateTime
(encoding = w3cdtf);
(qualifier = exact);
(point = start)
2019-12-20 13:21:02
AssociatedEntity
Name
Shichen Sun
Role
Copyright holder
Affiliation
Rutgers University. School of Graduate Studies
AssociatedObject
Type
License
Name
Author Agreement License
Detail
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.
RightsEvent
Type
Embargo
DateTime
(encoding = w3cdtf);
(qualifier = exact);
(point = start)
2021-01-31
DateTime
(encoding = w3cdtf);
(qualifier = exact);
(point = end)
2022-01-31
Detail
Access to this PDF has been restricted at the author's request. It will be publicly available after January 31st, 2022.
Copyright
Status
Copyright protected
Availability
Status
Open
Reason
Permission or license
Back to the top
Technical
RULTechMD
(ID = TECHNICAL1)
ContentModel
ETD
OperatingSystem
(VERSION = 5.1)
windows xp
CreatingApplication
Version
1.5
DateCreated
(point = end);
(encoding = w3cdtf);
(qualifier = exact)
2020-01-02T15:35:20
DateCreated
(point = end);
(encoding = w3cdtf);
(qualifier = exact)
2020-01-02T15:35:20
ApplicationName
pdfTeX-1.40.19
Back to the top
Statistical Profile