Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Neural network diagnosis of malignant melanoma from color images
Author (s): Ercal, Fikret
Chawla, A.
Stoecker, W.V.
Hsi-Chieh Lee
Moss, Randy Hays
Department/Lab Affiliations: Computer Science
Electrical and Computer Engineering
Image Processing Laboratory
Keywords: 5 y
United States
artificial neural network classification
automated cancer detection
benign tumors
color images
deadliest skin cancer form
discriminant features
malignant melanoma
medical diagnostic images
medical image processing
neural network diagnosis
patient diagnosis
relative tumor color
skin
skin tumor images
tumor shape
Issue Date: 1994
Publisher: Institute of Electrical and Electronics Engineers
Citation: Ercal, F.; Chawla, A.; Stoecker, W.V.; Hsi-Chieh Lee; Moss, R.H., "Neural network diagnosis of malignant melanoma from color images," IEEE Transactions on Biomedical Engineering, vol.41, no.9 pp.837-845, Sep 1994
Abstract: Malignant melanoma is the deadliest form of all skin cancers. Approximately 32,000 new cases of malignant melanoma were diagnosed in 1991 in the United States, with approximately 80% of patients expected to survive 5 years. Fortunately, if detected early, even malignant melanoma may be treated successfully, Thus, in recent years, there has been rising interest in the automated detection and diagnosis of skin cancer, particularly malignant melanoma. Here, the authors present a novel neural network approach for the automated separation of melanoma from 3 benign categories of tumors which exhibit melanoma-like characteristics. The approach uses discriminant features, based on tumor shape and relative tumor color, that are supplied to an artificial neural network for classification of tumor images as malignant or benign. With this approach, for reasonably balanced training/testing sets, the authors are able to obtain above 80% correct classification of the malignant and benign tumors on real skin tumor images.
Type: Article - Journal
text
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
FULL COPYRIGHT INFORMATION:
http://www.ieee.org/web/publications/rights/policies.html
Publisher URL:
http://ieeexplore.ieee.org/iel1/10/7570/00312091.pdf?arnumber=31209
Link to this page:
http://scholarsmine.mst.edu/post_prints/00312091_09007dcc8030bc07.html
Full Text:
00312091_09007dcc8030bc0c.pdf



titleNeural network diagnosis of malignant melanoma from color images
contributor.authorErcal, Fikret
contributor.authorChawla, A.
contributor.authorStoecker, W.V.
contributor.authorHsi-Chieh Lee
contributor.authorMoss, Randy Hays
contributor.deptlabComputer Science
contributor.deptlabElectrical and Computer Engineering
contributor.deptlabImage Processing Laboratory
subject5 y
subjectUnited States
subjectartificial neural network classification
subjectautomated cancer detection
subjectbenign tumors
subjectcolor images
subjectdeadliest skin cancer form
subjectdiscriminant features
subjectmalignant melanoma
subjectmedical diagnostic images
subjectmedical image processing
subjectneural network diagnosis
subjectpatient diagnosis
subjectrelative tumor color
subjectskin
subjectskin tumor images
subjecttumor shape
date.issued1994
date.submitted2007
publisherInstitute of Electrical and Electronics Engineers
identifier.citationErcal, F.; Chawla, A.; Stoecker, W.V.; Hsi-Chieh Lee; Moss, R.H., "Neural network diagnosis of malignant melanoma from color images," IEEE Transactions on Biomedical Engineering, vol.41, no.9 pp.837-845, Sep 1994
identifier.issn0018-9294
identifier.pub.URI
http://ieeexplore.ieee.org/iel1/10/7570/00312091.pdf?arnumber=31209
description.abstractMalignant melanoma is the deadliest form of all skin cancers. Approximately 32,000 new cases of malignant melanoma were diagnosed in 1991 in the United States, with approximately 80% of patients expected to survive 5 years. Fortunately, if detected early, even malignant melanoma may be treated successfully, Thus, in recent years, there has been rising interest in the automated detection and diagnosis of skin cancer, particularly malignant melanoma. Here, the authors present a novel neural network approach for the automated separation of melanoma from 3 benign categories of tumors which exhibit melanoma-like characteristics. The approach uses discriminant features, based on tumor shape and relative tumor color, that are supplied to an artificial neural network for classification of tumor images as malignant or benign. With this approach, for reasonably balanced training/testing sets, the authors are able to obtain above 80% correct classification of the malignant and benign tumors on real skin tumor images.
typeArticle - Journal
type.DCMITypetext
type.statusFinal version
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
rights.URI
http://www.ieee.org/web/publications/rights/policies.html
date.accessioned2007-04-05T13:58:06Z
date.available2007-04-05T13:58:06Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/00312091_09007dcc8030bc07.html
Full Text
00312091_09007dcc8030bc0c.pdf