Analysis of clinical and dermoscopic features for basal cell carcinoma neural network classification

Abstract

Background Basal cell carcinoma (BCC) is the most commonly diagnosed cancer in the United States. 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 BCCs and 350 benign lesions, for lesion discrimination using neural network-based techniques, including Evolving Artificial Neural Networks and Evolving Artificial Neural Network Ensembles. Results Experiment results based on ten-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.

The role of AI classifiers in skin cancer images

“…The implementation of additional algorithms for the optimization of ANN performance in skin cancer classification is also found. Common methods include the use of genetic algorithms (GA) and particle swarm optimization (PSO) …”

“…Common methods include the use of genetic algorithms (GA) 39 and particle swarm optimization (PSO). 40 Additionally, random forests (RF) learning methods have also been applied to dermatoscopy images for both melanoma 41…”

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

“…An increasing number of original studies have also begun classifying non-melanoma skin cancers (also known as keratinocyte carcinomas) vs. benign and pre-malignant lesions (36)(37)(38)(39)(40)(41)(42)(43)(44). For example, Spyridonos et al developed an AI model that could differentiate between actinic keratosis and normal skin with a specificity of 89.8% and a sensitivity of 91.7% (37).…”

Classification of reticular pattern and streaks in dermoscopic images based on texture analysis

“…These techniques also permit the use of automated classification of skin lesions, which is a valuable help to clinical practice. 19,20 In fact, one of the greatest challenges in classification is the higher inter-and intraindividual variability, due to the limited capacity of the human eye (contrast sensitivity, wavelength sensitivity, orientation discrimination, etc.). [21][22][23] The pigmented network or reticular pattern and streaks are important diagnostic clues, representing a dermoscopic hallmark of melanocytic lesions, which is independent of their biologic behavior.…”