Hyperspectral Imaging for Non-invasive Diagnostics of Melanocytic Lesions

• DOI: 10.2340/actadv.v102.2045
• Publication Date: 2022-10-25T09:30:07Z
• Authors: John Paoli; Ilkka Pölönen; Mari Salmivuori; Janne Räsänen; Oscar Zaar; Sam Polesie; Sari Koskenmies; Sari Pitkänen; Meri Övermark; Kirsi Isoherranen; Susanna Juteau; Annamari Ranki; Mari Grönroos; Noora Neittaanmäki
• Keywords: Skin Neoplasms; hyperspectral imaging; malignant melanoma; 610; Dermatology; 3121 Internal medicine; Sensitivity and Specificity; Computational Science; 3121; ihosyöpä; 03 medical and health sciences; Melanoma, Cutaneous Malignant; 0302 clinical medicine; Humans; melanooma; Melanoma; hyperspektrikuvantaminen; ta217; ta113; Nevus, Pigmented; Hyperspectral Imaging; diagnostiikka; ta3122; General medicine, internal medicine and other clinical medicine; 3. Good health; machine learning; koneoppiminen; RL1-803; Original Article; Laskennallinen tiede; non-invasive diagnostic

Malignant melanoma poses a clinical diagnostic problem, since a large number of benign lesions are excised to find a single melanoma. This study assessed the accuracy of a novel non-invasive diagnostic technology, hyperspectral imaging, for melanoma detection. Lesions were imaged prior to excision and histopathological analysis. A deep neural network algorithm was trained twice to distinguish between histopathologically verified malignant and benign melanocytic lesions and to classify the separate subgroups. Furthermore, 2 different approaches were used: a majority vote classification and a pixel-wise classification. The study included 325 lesions from 285 patients. Of these, 74 were invasive melanoma, 88 melanoma in situ, 115 dysplastic naevi, and 48 non-dysplastic naevi. The study included a training set of 358,800 pixels and a validation set of 7,313 pixels, which was then tested with a training set of 24,375 pixels. The majority vote classification achieved high overall sensitivity of 95% and a specificity of 92% (95% confidence interval (95% CI) 0.024–0.029) in differentiating malignant from benign lesions. In the pixel-wise classification, the overall sensitivity and specificity were both 82% (95% CI 0.005–0.005). When divided into 4 subgroups, the diagnostic accuracy was lower. Hyperspectral imaging provides high sensitivity and specificity in distinguishing between naevi and melanoma. This novel method still needs further validation.