Multispectral Imaging Algorithm Predicts Breslow Thickness of Melanoma

Abstract

Breslow thickness is a major prognostic factor for melanoma. It is based on histopathological evaluation, and thus it is not available to aid clinical decision making at the time of the initial melanoma diagnosis. In this work, we assessed the efficacy of multispectral imaging (MSI) to predict Breslow thickness and developed a classification algorithm to determine optimal safety margins of the melanoma excision. First, we excluded nevi from the analysis with a novel quantitative parameter. Parameter s’ could differentiate nevi from melanomas with a sensitivity of 89.60% and specificity of 88.11%. Following this step, we have categorized melanomas into three different subgroups based on Breslow thickness (≤1 mm, 1–2 mm and >2 mm) with a sensitivity of 78.00% and specificity of 89.00% and a substantial agreement (κ = 0.67; 95% CI, 0.58–0.76). We compared our results to the performance of dermatologists and dermatology residents who assessed dermoscopic and clinical images of these melanomas, and reached a sensitivity of 60.38% and specificity of 80.86% with a moderate agreement (κ = 0.41; 95% CI, 0.39–0.43). Based on our findings, this novel method may help predict the appropriate safety margins for curative melanoma excision.

Optically Guided High-Frequency Ultrasound Shows Superior Efficacy for Preoperative Estimation of Breslow Thickness in Comparison with Multispectral Imaging: A Single-Center Prospective Validation Study

“…ROIs corresponding to melanomas were recorded using the ROI manager function of the ImageJ software, ensuring that the analyzed area was consistent across all channels (G, R, and IR). Mean gray value (integrated density/area), circularity (4π × area/perimeter 2 ), solidity (area/convex area), and roundness (4 × area/(π × major_axis 2 )) were measured as described in our previous publication [ 26 ]. The entire imaging procedure and subsequent thickness estimation are completed within a few minutes.…”

“…In our previous research [ 26 ], we developed an algorithm to classify melanomas into three clinically relevant subgroups (Breslow thickness < 1 mm, Breslow thickness between 1–2 mm, and Breslow thickness > 2 mm) based on the shape descriptors and intensity values of their MSI images. This modified melanoma classification algorithm ( Figure 1 .)…”

“…Breslow thickness over 2 mm. The algorithm could sort melanomas into these three subgroups with a sensitivity of 78.00% and specificity of 89.00% and a substantial agreement (κ = 0.67; 95% CI, 0.58–0.76) [ 26 ].…”

Multimodal system for optical biopsy of melanoma with integrated ultrasound, optical coherence tomography and Raman spectroscopy

“…As for classification and diagnosis, Raman spectroscopy (RS) has been capable of distinguishing melanoma and benign skin lesions by analyzing lipid and melanin bands, additionally identifying different skin cancer types [18][19][20][21][22][23]. Finally, in the last years, numerous studies have emerged with multi-and hyperspectral imaging systems that are able to rapidly classify and predict benign and malignant lesions from the surface [24][25][26][27].…”

Self-made transparent optoacoustic detector for measurement of skin lesion thickness in vivo

“…For example, Meyer et al have demonstrated good level of agreement of highfrequency ultrasound (HFUS) measurements with histological results, while optical coherence tomography (OCT) was shown to be inappropriate for lesion thicknesses over 0.5 mm [4]. Bozsányi et al have successfully applied multispectral imaging for measuring and classifying the Breslow thickness of melanoma (1 mm, 1-2 mm and >2 mm) [5]. Finally, multiphoton and confocal microscopy were employed for imaging of melanoma; they were however restricted to relatively low penetration depths of 200 μm in pigmented skin [6][7][8].…”