Automatic detection of basal cell carcinoma by hyperspectral imaging

• Published in: Journal of biophotonics Vol. 15; no. 1; pp. e202100231 - n/a
• Main Authors: Calin, Mihaela Antonina, Parasca, Sorin Viorel
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.01.2022; Wiley Subscription Services, Inc
• Subjects: Algorithms; Anomalies; anomaly detector; automated detection; Basal cell carcinoma; cancer; Carcinoma, Basal Cell - diagnostic imaging; Cell differentiation; Detectors; Female; Humans; Hyperspectral Imaging; reflectance spectra; ROC Curve; Sensors; Skin; Skin cancer; Skin Neoplasms - diagnostic imaging; reflectance spectra; anomaly detector; skin; cancer; automated detection; hyperspectral imaging
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.202100231

The purpose of this study was to test the ability of hyperspectral imaging (HSI) combined with unsupervised anomaly detectors to automatically differentiate basal cell carcinoma (BCC) from normal skin. Hyperspectral images of the face of a female patient with a BCC of the lower lip were acquired using a visible/near‐infrared HSI system and two anomaly detection algorithms (Reed‐Xiaoli and Reed‐Xiaoli/Uniform Target hybrid anomaly detectors) were used to detect pathological tissue from normal skin. The results revealed that the receiver operating characteristic curve of the Reed‐Xiaoli/Uniform Target hybrid detector was higher than that of the Reed‐Xiaoli detector in the range of false positive rates between 0 and 0.8. The area under curve values were good (0.7074 and 0.8607, respectively) with Reed‐Xiaoli/Uniform Target hybrid detector performing better. In conclusion, HSI combined with either of two anomaly detectors can play a promising role in the automated screening of BCC. The aim of the study was to test the ability of hyperspectral imaging combined with two anomaly detectors (Reed‐Xiaoli and Reed‐Xiaoli/ Uniform Target Detector) to automatically differentiate basal cell carcinoma (BCC) from normal skin. This combined method proved that either of the two anomaly detectors could discriminate BCC from normal tissue well enough, and could play a promising role in the automated screening of BCC.