Universal in vivo Textural Model for Human Skin based on Optical Coherence Tomograms

Abstract

Currently, diagnosis of skin diseases is based primarily on the visual pattern recognition skills and expertise of the physician observing the lesion. Even though dermatologists are trained to recognize patterns of morphology, it is still a subjective visual assessment. Tools for automated pattern recognition can provide objective information to support clinical decision-making. Noninvasive skin imaging techniques provide complementary information to the clinician. In recent years, optical coherence tomography (OCT) has become a powerful skin imaging technique. According to specific functional needs, skin architecture varies across different parts of the body, as do the textural characteristics in OCT images. There is, therefore, a critical need to systematically analyze OCT images from different body sites, to identify their significant qualitative and quantitative differences. Sixty-three optical and textural features extracted from OCT images of healthy and diseased skin are analyzed and, in conjunction with decision-theoretic approaches, used to create computational models of the diseases. We demonstrate that these models provide objective information to the clinician to assist in the diagnosis of abnormalities of cutaneous microstructure, and hence, aid in the determination of treatment. Specifically, we demonstrate the performance of this methodology on differentiating basal cell carcinoma (BCC) and squamous cell carcinoma (SCC) from healthy tissue.

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Figure 1

The illustration demonstrates the sequential images obtained by OCT (top left), and the 3D OCT representation of the skin (top right). The center illustration demonstrates several skin structures and their corresponding appearance on OCT. The bottom images demonstrate thick skin and thin skin, and annotated structures, their corresponding equivalent histology, and OCT images. The scale bar in OCT images is 400 µm.

Figure 2

OCT images and structure annotation of different sites of body including, (a) nose, (b) preauricular, (c) volar forearm, (d) neck, (e) palm, (f) back, (g) thumb, (h) dorsal forearm, (i) sole and (j) calf. SC: stratum corneum, SL: stratum lucidum, ESD: eccrine sweat ducts, RE: remainder of epidermis (stratum granulosum, stratum spinosum, stratum basale), RD: reticular dermis, DEJ: dermal-epidermal junction showing pronounced dermal papillae, PD: papillary dermis, D: dermis, EP: epidermis, BV: blood vessels, TK: thick skin, and TN: thin skin.

Figure 3

Classification results. (a) Correlation map of 63 features used for differentiating healthy versus BCC samples, (b) correlation map of the six selected features, (c) ROC curve for different subsets of features with LSVM classifier, (d) cross-validation classification error of different classifiers when different subsets of features were used. SRE: short run emphasis, LRE: long run emphasis, GLN: gray-level nonuniformity, RP: run percentage, RLN: run length nonuniformity, LGRE: low gray-level run emphasis, HGRE: high gray-level run emphasis.

Figure 4

Classification results. (a) Correlation map of 63 features used for differentiating healthy versus SCC samples, (b) correlation map of the six selected features, (c) ROC curve for different subsets of features with QSVM classifier, (d) cross-validation classification error of different classifiers when different subsets of features were used. SRE: short run emphasis, LRE: long run emphasis, GLN: gray-level nonuniformity, RP: run percentage, RLN: run length nonuniformity, LGRE: low gray-level run emphasis, HGRE: high gray-level run emphasis.

Figure 5

(a) Block diagram of the proposed computational method, (b) attenuation coefficient measurement procedure.