Abstract
The paper presents results of using a neural network classifier to analyze images of malignant skin lesions obtained using a hyper-spectral camera. Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin. The sufficiency of the inclusion in the training set of two-dimensional images of a limited spectral range is analyzed. The results obtained show significant prospects of using neural network algorithms for processing hyperspectral data for the classification of skin pathologies. With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %.
Highlights
Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin
With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %
On the spectral signature of melanoma: a nonparametric classification framework for cancer detection in hyperspectral imaging of melanocytic lesions / A
Summary
Для регистрации спектральных изображений использовался акустооптический видеоспектрометр, позволяющий получать изображение исследуемого участка на произвольно-задаваемой длине волны в диапазоне 440 – 750 нм. При этом спектральное разрешение составляет δλ = 2,5 нм (при λ = 633 нм), а пространственное разрешение – 0,14 мм. Она обеспечивает практически полную компенсацию спектральных и пространственных искажений изображения в одиночной ячейке, вызываемых дифракцией Брэгга, обычно приводящих к изменению спектров в отдельных точках [32]. Результатом фиксации гиперспектральных данных является гиперкуб из 151 изображения
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
