Diagnostic Performance of a Support Vector Machine for Dermatofluoroscopic Melanoma Recognition: The Results of the Retrospective Clinical Study on 214 Pigmented Skin Lesions

Abstract

The need for diagnosing malignant melanoma in its earliest stages results in an increasing number of unnecessary excisions. Objective criteria beyond the visual inspection are needed to distinguish between benign and malignant melanocytic tumors in vivo. Fluorescence spectra collected during the prospective, multicenter observational study (“FLIMMA”) were retrospectively analyzed by the newly developed machine learning algorithm. The formalin-fixed paraffin-embedded (FFPE) tissue samples of 214 pigmented skin lesions (PSLs) from 144 patients were examined by two independent pathologists in addition to the first diagnosis from the FLIMMA study, resulting in three histopathological results per sample. The support vector machine classifier was trained on 17,918 fluorescence spectra from 49 lesions labeled as malignant (1) and benign (0) by three histopathologists. A scoring system that scales linearly with the number of the “malignant spectra” was designed to classify the lesion as malignant melanoma (score > 28) or non-melanoma (score ≤ 28). Finally, the scoring algorithm was validated on 165 lesions to ensure model prediction power and to estimate the diagnostic accuracy of dermatofluoroscopy in melanoma detection. The scoring algorithm revealed a sensitivity of 91.7% and a specificity of 83.0% in diagnosing malignant melanoma. Using additionally the image segmentation for normalization of lesions’ region of interest, a further improvement of sensitivity of 95.8% was achieved, with a corresponding specificity of 80.9%.

Investigating Serum and Tissue Expression Identified a Cytokine/Chemokine Signature as a Highly Effective Melanoma Marker

“…We therefore analyzed the entire panel of 27 cytokines/chemokines with the SVM machine learning algorithm, to investigate simultaneously all molecules as predictors of melanoma state. In other studies, SVM effectively discriminated melanoma on the basis of dermoscopic images [44], ultrasonic and spectrophotometric images [45], BRAF status [46], or dermo-fluorescence spectra [47], with a reported accuracy up to 90%. SVM was previously used for prognostic purposes in melanoma patients [48] but, to our knowledge, the present study is the first applying the SVM analysis to cytokine/chemokine-expression values to discriminate melanoma from controls, both in serum and in tissue, in a large group of controls and patients.…”

Artificial Intelligence in Dermatology: A Primer

“…AI coupled with hardwarebased methods such as spectroscopy, multispectral imaging, or other specialized imaging modalities may augment dermatologists' capabilities (Dick et al, 2019;Ferrante di Ruffano et al, 2018;Szyc et al, 2019). For example, early melanomas may not present morphologic differences detectable by conventional photography, but computerassisted techniques like dermatofluoroscopy may provide additional information for early diagnosis.…”

The role of technology in melanoma screening and diagnosis

“…Most recently, deep learning models have achieved sensitivity and specificity for the diagnosis of melanoma from images on par with, or exceeding, medical experts. Importantly, deep learning may accelerate the adoption of specialized imaging modalities through automated analysis of acquired images (Szyc, Hillen, Scharlach, Kauer, & Garbe, 2019; Wodzinski, Skalski, Witkowski, Pellacani, & Ludzik, 2019), thus reducing the need for advanced training. Deep learning is already being used to help triage the large number of images collected using TBP or SDDI and to retrieve the most similar annotated images, although they are not yet clinically used for diagnosis which would subject them to the need for regulatory approval.…”