دورية أكاديمية

Curve‐based classification approach for hyperspectral dermatologic data processing

التفاصيل البيبلوغرافية
العنوان: Curve‐based classification approach for hyperspectral dermatologic data processing
المؤلفون: Uteng, Stig, Quevedo Gutiérrez, Eduardo Gregorio, Marrero Callicó, Gustavo Iván, Castaño González, Irene, Carretero Hernández, Gregorio, Almeida Martín, Pablo, Garcia del Toro, Aday, Hernández Santana, Javier A., Godtliebsen, Fred
المساهمون: 57216457386, 55845740700, 56006321500, 57214689598, 6506191408, 8524503900, 55452183800, 57214748954, 55974798000, BU-TEL
المصدر: Sensors (Switzerland) [ISSN 1424-8220], v. 21 (3), p. 1-13
سنة النشر: 2021
المجموعة: Universidad de Las Palmas de Gran Canaria: Acceda
مصطلحات موضوعية: 3314 Tecnología médica, 320106 Dermatología, Hyperspectral, Curve fit, Statistical discrimination, Melanoma, Benign, Malignant
الوصف: This paper shows new contributions in the detection of skin cancer, where we present the use of a customized hyperspectral system that captures images in the spectral range from 450 to 950 nm. By choosing a 7 × 7 sub-image of each channel in the hyperspectral image (HSI) and then taking the mean and standard deviation of these sub-images, we were able to make fits of the resulting curves. These fitted curves had certain characteristics, which then served as a basis of classification. The most distinct fit was for the melanoma pigmented skin lesions (PSLs), which is also the most aggressive malignant cancer. Furthermore, we were able to classify the other PSLs in malignant and benign classes. This gives us a rather complete classification method for PSLs with a novel perspective of the classification procedure by exploiting the variability of each channel in the HSI. ; 13
نوع الوثيقة: article in journal/newspaper
اللغة: English
تدمد: 1424-8220
العلاقة: Sensors (Switzerland); 21; Scopus; http://hdl.handle.net/10553/77331Test; 85099677035; Sí
DOI: 10.3390/s21030680
الإتاحة: https://doi.org/10.3390/s21030680Test
http://hdl.handle.net/10553/77331Test
رقم الانضمام: edsbas.302D60F2
قاعدة البيانات: BASE
الوصف
تدمد:14248220
DOI:10.3390/s21030680