Open AccessAnalysis of clinical and dermoscopic features for basal cell carcinoma neural network classification
Author(s) -
Cheng Beibei,
Joe Stanley R.,
Stoecker William V.,
Stricklin Sherea M.,
Hinton Kristen A.,
Nguyen Thanh K.,
Rader Ryan K.,
Rabinovitz Harold S.,
Oliviero Margaret,
Moss Randy H.
Publication year - 2013
Publication title -
skin research and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.521
H-Index - 69
eISSN - 1600-0846
pISSN - 0909-752X
DOI - 10.1111/j.1600-0846.2012.00630.x
Subject(s) - artificial intelligence , artificial neural network , pattern recognition (psychology) , computer science , lesion , feature (linguistics) , receiver operating characteristic , basal cell carcinoma , data set , convolutional neural network , basal cell , medicine , machine learning , pathology , linguistics , philosophy
Background Basal cell carcinoma ( BCC ) is the most commonly diagnosed cancer in the USA . In this research, we examine four different feature categories used for diagnostic decisions, including patient personal profile (patient age, gender, etc.), general exam (lesion size and location), common dermoscopic (blue‐gray ovoids, leaf‐structure dirt trails, etc.), and specific dermoscopic lesion (white/pink areas, semitranslucency, etc.). Specific dermoscopic features are more restricted versions of the common dermoscopic features. Methods Combinations of the four feature categories are analyzed over a data set of 700 lesions, with 350 BCC s and 350 benign lesions, for lesion discrimination using neural network‐based techniques, including evolving artificial neural networks ( EANN s) and evolving artificial neural network ensembles. Results Experiment results based on 10‐fold cross validation for training and testing the different neural network‐based techniques yielded an area under the receiver operating characteristic curve as high as 0.981 when all features were combined. The common dermoscopic lesion features generally yielded higher discrimination results than other individual feature categories. Conclusions Experimental results show that combining clinical and image information provides enhanced lesion discrimination capability over either information source separately. This research highlights the potential of data fusion as a model for the diagnostic process.