Hyperspectral imaging reveals spectral differences and can distinguish malignant melanoma from pigmented basal cell carcinomas : A pilot study
| Autor: | Ilkka Pölönen, Noora Neittaanmäki, Mari Grönroos, Mari Salmivuori, J.E. Räsänen |
|---|---|
| Přispěvatelé: | Tampere University, Clinical Medicine, Department of Respiratory medicine, Dermatology and Allergology, HYKS erva, Päijät-Häme Welfare Consortium, HUS Inflammation Center, Department of Dermatology, Allergology and Venereology, University of Helsinki, Helsinki University Hospital Area |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Pathology
medicine.medical_specialty Skin Neoplasms 010504 meteorology & atmospheric sciences neural network 3122 Cancers 0211 other engineering and technologies malignant melanoma Pilot Projects 02 engineering and technology neuroverkot Dermatology tyvisolusyöpä 3121 Internal medicine 01 natural sciences Sensitivity and Specificity Lesion ihosyöpä Diagnosis Differential basal cell carcinoma medicine Humans Basal cell carcinoma Basal cell Prospective Studies Melanoma 021101 geological & geomatics engineering 0105 earth and related environmental sciences business.industry spektrikuvaus Hyperspectral imaging deep learning General Medicine Hyperspectral Imaging diagnostiikka medicine.disease 3126 Surgery anesthesiology intensive care radiology Reflectivity Confidence interval 3. Good health koneoppiminen Carcinoma Basal Cell RL1-803 3121 General medicine internal medicine and other clinical medicine medicine.symptom Differential diagnosis business |
| Zdroj: | Acta Dermato-Venereologica, Vol 101, Iss 2, p adv00405 (2021) |
| Popis: | 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 prospective pilot study was to use a convolutional neural network classifier in hyperspectral images for differential diagnosis between pigmented basal cell carcinomas and melanoma. A total of 26 pigmented lesions (10 pigmented basal cell carcinomas, 12 melanomas in situ, 4 invasive melanomas) were imaged with hyperspectral imaging and excised for histopathological diagnosis. For 2-class classifier (melanocytic tumours vs pigmented basal cell carcinomas) using the majority of the pixels to predict the class of the whole lesion, the results showed a sensitivity of 100% (95% confidence interval 81-100%), specificity of 90% (95% confidence interval 60-98%) and positive predictive value of 94% (95% confidence interval 73-99%). These results indicate that a convolutional neural network classifier can differentiate melanocytic tumours from pigmented basal cell carcinomas in hyperspectral images. Further studies are warranted in order to confirm these preliminary results, using larger samples and multiple tumour types, including all types of melanocytic lesions. publishedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|