Hyperspectral Imaging System in the Delineation of Ill-defined Basal Cell Carcinomas : A Pilot Study
Salmivuori, M., Neittaanmäki, N., Pölönen, I., Jeskanen, L., Snellman, E., & Grönroos, M. (2019). Hyperspectral Imaging System in the Delineation of Ill-defined Basal Cell Carcinomas : A Pilot Study. Journal of the European Academy of Dermatology and Venereology, 33(1), 71-78. https://doi.org/10.1111/jdv.15102
Authors
Date
2019Copyright
© 2018 European Academy of Dermatology and Venereology
Background
Basal cell carcinoma (BCC) is the most common skin cancer in the Caucasian population. Eighty per cent of BCCs are located on the head and neck area. Clinically ill‐defined BCCs often represent histologically aggressive subtypes, and they can have subtle subclinical extensions leading to recurrence and the need for re‐excisions.
Objectives
The aim of this pilot study was to test the feasibility of a hyperspectral imaging system (HIS) in vivo in delineating the preoperatively lateral margins of ill‐defined BCCs on the head and neck area.
Methods
Ill‐defined BCCs were assessed clinically with a dermatoscope, photographed and imaged with HIS. This was followed by surgical procedures where the BCCs were excised at the clinical border and the marginal strip separately. HIS, with a 12‐cm2 field of view and fast data processing, records a hyperspectral graph for every pixel in the imaged area, thus creating a data cube. With automated computational modelling, the spectral data are converted into localization maps showing the tumour borders. Interpretation of these maps was compared to the histologically verified tumour borders.
Results
Sixteen BCCs were included. Of these cases, 10 of 16 were the aggressive subtype of BCC and 6 of 16 were nodular, superficial or a mixed type. HIS delineated the lesions more accurately in 12 of 16 of the BCCs compared to the clinical evaluation (4 of 16 wider and 8 of 16 smaller by HIS). In 2 of 16 cases, the HIS‐delineated lesion was wider without histopathological confirmation. In 2 of 16 cases, HIS did not detect the histopathologically confirmed subclinical extension.
Conclusions
HIS has the potential to be an easy and fast aid in the preoperative delineation of ill‐defined BCCs, but further adjustment and larger studies are warranted for an optimal outcome.
...
Publisher
Wiley-Blackwell Publishing Ltd.ISSN Search the Publication Forum
0926-9959Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/28076663
Metadata
Show full item recordCollections
License
Related items
Showing items with similar title or keywords.
-
Hyperspectral Imaging Reveals Spectral Differences and Can Distinguish Malignant Melanoma from Pigmented Basal Cell Carcinomas : A Pilot Study
Räsänen, Janne; Salmivuori, Mari; Pölönen, Ilkka; Grönroos, Mari; Neittaanmäki, Noora (Society for Publication of Acta Dermato-Venereologica, 2021)Pigmented basal cell carcinomas can be difficult to distinguish from melanocytic tumours. Hyperspectral imaging is a non-invasive imaging technique that measures the reflectance spectra of skin in vivo. The aim of this ... -
Discriminating Basal Cell Carcinoma and Bowen’s Disease with Novel Hyperspectral Imaging System and Convolutional Neural Networks
Salmivuori, Mari; Lindholm, Vivian; Annala, Leevi; Raita-Hakola, Anna-Maria; Jeskanen, Leila; Pölönen, Ilkka; Koskenmies, Sari; Pitkänen, Sari; Isoherranen, Kirsi; Ranki, Annamari (Society for Publication of Acta Dermato-Venereologica, 2022) -
Discriminating basal cell carcinoma and Bowen's disease from benign skin lesions with a 3D hyperspectral imaging system and convolutional neural networks
Lindholm, Vivian; Annala, Leevi; Koskenmies, Sari; Pitkänen, Sari; Isoherranen, Kirsi; Järvinen, Anna; Jeskanen, Leila; Pölönen, Ilkka; Ranki, Annamari; Raita‐Hakola, Anna‐Maria; Salmivuori, Mari (Wiley-Blackwell, 2024) -
Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network
Annala, Leevi; Neittaanmäki, Noora; Paoli, John; Zaar, Oscar; Pölönen, Ilkka (IEEE, 2020)In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural ... -
Discovering knowledge in various applications with a novel hyperspectral imager
Pölönen, Ilkka (University of Jyväskylä, 2013)