Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Performance of AI methods in detecting melanoma
Author (s): Kjoelen, A.
Thompson, M.J.
Umbaugh, S.E.
Moss, Randy Hays
Stoecker, W.V.
Department/Lab Affiliations: Electrical and Computer Engineering
Image Processing Laboratory
Keywords: 35 mm
35 mm color slides
AI methods performance
AIM numeric modeling tool
artificial intelligence
atypical moles
benign tumors
color skin tumor images
computer vision
computer vision methods
feature extraction
lst-Class software
mean success rates
medical diagnostic imaging
medical image processing
melanoma detection
monotonically increasing success ratios
skin
training set size
Issue Date: 1995
Publisher: Institute of Electrical and Electronics Engineers
Citation: Kjoelen, A.; Thompson, M.J.; Umbaugh, S.E.; Moss, R.H.; Stoecker, W.V., "Performance of AI methods in detecting melanoma," Engineering in Medicine and Biology Magazine, IEEE , vol.14, no.4 pp.411-416, JulAug 1995
Abstract: This research has shown that features extracted from color skin tumor images by computer vision methods can be reliable discriminators of malignant tumors from benign ones. Reliability was demonstrated by the monotonically increasing success ratios with increasing training set size and by the small standard deviations from the mean success rates. An average success rate of 70 percent in diagnosing melanoma was attained for a training set size of 60 percent. The presence or absence of atypical moles in the training and test sets was shown to have a dramatic impact on the effectiveness of the generated classification rules. This was the case with both AIM and lst-Class, and indicates a high potential for success if a method can be found for discriminating between atypical moles and melanoma
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/iel1/51/8966/00395323.pdf?arnumber=39532
Link to this page:
http://scholarsmine.mst.edu/post_prints/00395323_09007dcc8030bcea.html
Full Text:
00395323_09007dcc8030bcef.pdf



titlePerformance of AI methods in detecting melanoma
contributor.authorKjoelen, A.
contributor.authorThompson, M.J.
contributor.authorUmbaugh, S.E.
contributor.authorMoss, Randy Hays
contributor.authorStoecker, W.V.
contributor.deptlabElectrical and Computer Engineering
contributor.deptlabImage Processing Laboratory
subject35 mm
subject35 mm color slides
subjectAI methods performance
subjectAIM numeric modeling tool
subjectartificial intelligence
subjectatypical moles
subjectbenign tumors
subjectcolor skin tumor images
subjectcomputer vision
subjectcomputer vision methods
subjectfeature extraction
subjectlst-Class software
subjectmean success rates
subjectmedical diagnostic imaging
subjectmedical image processing
subjectmelanoma detection
subjectmonotonically increasing success ratios
subjectskin
subjecttraining set size
date.issued1995
date.submitted2007
publisherInstitute of Electrical and Electronics Engineers
identifier.citationKjoelen, A.; Thompson, M.J.; Umbaugh, S.E.; Moss, R.H.; Stoecker, W.V., "Performance of AI methods in detecting melanoma," Engineering in Medicine and Biology Magazine, IEEE , vol.14, no.4 pp.411-416, JulAug 1995
identifier.issn0739-5175
identifier.pub.URI
http://ieeexplore.ieee.org/iel1/51/8966/00395323.pdf?arnumber=39532
description.abstractThis research has shown that features extracted from color skin tumor images by computer vision methods can be reliable discriminators of malignant tumors from benign ones. Reliability was demonstrated by the monotonically increasing success ratios with increasing training set size and by the small standard deviations from the mean success rates. An average success rate of 70 percent in diagnosing melanoma was attained for a training set size of 60 percent. The presence or absence of atypical moles in the training and test sets was shown to have a dramatic impact on the effectiveness of the generated classification rules. This was the case with both AIM and lst-Class, and indicates a high potential for success if a method can be found for discriminating between atypical moles and melanoma
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.accessioned2007-04-05T13:59:07Z
date.available2007-04-05T13:59:07Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/00395323_09007dcc8030bcea.html
Full Text
00395323_09007dcc8030bcef.pdf