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
A. Kjoelen et al., "Performance of AI Methods in Detecting Melanoma," IEEE Engineering in Medicine and Biology Magazine, Institute of Electrical and Electronics Engineers (IEEE), Jan 1995.
The definitive version is available at http://dx.doi.org/10.1109/51.395323
Electrical and Computer Engineering
Keywords and Phrases
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
International Standard Serial Number (ISSN)
Article - Journal
© 1995 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.