6533b836fe1ef96bd12a1211

RESEARCH PRODUCT

Towards to deep neural network application with limited training data: synthesis of melanoma's diffuse reflectance spectral images

Katrina BolochkoDilshat UteshevYuriy ChizhovAlexey LihachevIlze LihacovaDmitrijs BliznuksAndrey Bondarenko

subject

Training setLed illuminationArtificial neural networkbusiness.industryComputer scienceMelanomaMultispectral imagePattern recognitionmedicine.diseasemedicineNevusBenign nevusArtificial intelligenceSkin cancerbusiness

description

The goal of our study is to train artificial neural networks (ANN) using multispectral images of melanoma. Since the number of multispectral images of melanomas is limited, we offer to synthesize them from multispectral images of benign skin lesions. We used the previously created melanoma diagnostic criterion p'. This criterion is calculated from multispectral images of skin lesions captured under 526nm, 663nm, and 964nm LED illumination. We synthesize these three images from multispectral images of nevus so that the p' map matches the melanoma criteria (the values in the lesion area is >1, respectively). Demonstrated results show that by transforming multispectral images of benign nevus is possible to get a reliable multispectral images of melanoma usable for ANN training.

yearjournalcountryeditionlanguage
2019-07-11Diffuse Optical Spectroscopy and Imaging VII
https://doi.org/10.1117/12.2527173