A1 Journal article (refereed)
Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours : A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and Convolutional Neural Networks (2022)

Lindholm, V., Raita-Hakola, A.-M., Annala, L., Salmivuori, M., Jeskanen, L., Saari, H., Koskenmies, S., Pitkänen, S., Pölönen, I., Isoherranen, K., & Ranki, A. (2022). Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours : A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and Convolutional Neural Networks. Journal of Clinical Medicine, 11(7), Article 1914. https://doi.org/10.3390/jcm11071914

JYU authors or editors

Publication details

All authors or editors: Lindholm, Vivian; Raita-Hakola, Anna-Maria; Annala, Leevi; Salmivuori, Mari; Jeskanen, Leila; Saari, Heikki; Koskenmies, Sari; Pitkänen, Sari; Pölönen, Ilkka; Isoherranen, Kirsi; et al.

Journal or series: Journal of Clinical Medicine

eISSN: 2077-0383

Publication year: 2022

Publication date: 30/03/2022

Volume: 11

Issue number: 7

Article number: 1914

Publisher: MDPI AG

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.3390/jcm11071914

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/81969

Publication is parallel published: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8999463/

Abstract

Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. In this second part of a three-phase pilot study, we used a novel hand-held SICSURFIS Spectral Imager with an adaptable field of view and target-wise selectable wavelength channels to provide detailed spectral and spatial data for lesions on complex surfaces. The hyperspectral images (33 wavelengths, 477–891 nm) provided photometric data through individually controlled illumination modules, enabling convolutional networks to utilise spectral, spatial, and skin-surface models for the analyses. In total, 42 lesions were studied: 7 melanomas, 13 pigmented and 7 intradermal nevi, 10 basal cell carcinomas, and 5 squamous cell carcinomas. All lesions were excised for histological analyses. A pixel-wise analysis provided map-like images and classified pigmented lesions with a sensitivity of 87% and a specificity of 93%, and 79% and 91%, respectively, for non-pigmented lesions. A majority voting analysis, which provided the most probable lesion diagnosis, diagnosed 41 of 42 lesions correctly. This pilot study indicates that our non-invasive hyperspectral imaging system, which involves shape and depth data analysed by convolutional neural networks, is feasible for differentiating between malignant and benign pigmented and non-pigmented skin tumours, even on complex skin surfaces.

Keywords: skin cancer; melanoma; carcinomas; hyperspectral imaging; diagnostics; machine learning; neural networks (information technology)

Free keywords: biomedical optical imaging; convolutional neural networks; hyperspectral imaging; non-invasive imaging; optical modelling; photometric stereo; skin cancer; skin imaging

Contributing organizations

Related projects

Ministry reporting: Yes

Reporting Year: 2022

JUFO rating: 1