Hyperspectral Imaging for Non-invasive Diagnostics of Melanocytic Lesions

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 a...

Full description

Saved in:
Bibliographic Details
Published in:Acta dermato-venereologica 2022-11, Vol.102, p.adv00815-adv00815
Main Authors: Paoli, John, Pölönen, Ilkka, Salmivuori, Mari, Räsänen, Janne, Zaar, Oscar, Polesie, Sam, Koskenmies, Sari, Pitkänen, Sari, Övermark, Meri, Isoherranen, Kirsi, Juteau, Susanna, Ranki, Annamari, Grönroos, Mari, Neittaanmäki, Noora
Format: Article
Language:English
Subjects:
Clinical Medicine
Humans
Hyperspectral Imaging
Klinisk medicin
machine learning
malignant melanoma
Melanoma
Melanoma - pathology
Melanoma, Cutaneous Malignant
Nevus
Nevus, Pigmented - pathology
non-invasive diagnostic
Original
pathology
Pigmented
Sensitivity and Specificity
Skin Neoplasms
Skin Neoplasms - pathology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0001-5555
1651-2057
1651-2057
DOI:10.2340/actadv.v102.2045