Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing
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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/680 |
| _version_ | 1797409331922075648 |
|---|---|
| author | Stig Uteng Eduardo Quevedo Gustavo M. Callico Irene Castaño Gregorio Carretero Pablo Almeida Aday Garcia Javier A. Hernandez Fred Godtliebsen |
| author_facet | Stig Uteng Eduardo Quevedo Gustavo M. Callico Irene Castaño Gregorio Carretero Pablo Almeida Aday Garcia Javier A. Hernandez Fred Godtliebsen |
| author_sort | Stig Uteng |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T04:12:48Z |
| format | Article |
| id | doaj.art-6395062b9ed34e21bdc7e3b704179783 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:12:48Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6395062b9ed34e21bdc7e3b7041797832023-12-03T13:58:18ZengMDPI AGSensors1424-82202021-01-0121368010.3390/s21030680Curve-Based Classification Approach for Hyperspectral Dermatologic Data ProcessingStig Uteng0Eduardo Quevedo1Gustavo M. Callico2Irene Castaño3Gregorio Carretero4Pablo Almeida5Aday Garcia6Javier A. Hernandez7Fred Godtliebsen8Department of Education and Pedagogy, UiT the Arctic University of Norway, 9019 Tromsø, NorwayInstitute for Applied Microelectronics, Universidad de Las Palmas de Gran Canaria, 35016 Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics, Universidad de Las Palmas de Gran Canaria, 35016 Las Palmas de Gran Canaria, SpainDepartment of Dermatology, Hospital Universitario de Gran Canaria Doctor Negrín, 35016 Las Palmas de Gran Canaria, SpainDepartment of Dermatology, Hospital Universitario de Gran Canaria Doctor Negrín, 35016 Las Palmas de Gran Canaria, SpainDepartment of Dermatology, Complejo Hospitalario Universitario Insular-Materno Infantil, 35016 Las Palmas de Gran Canaria, SpainDepartment of Electromedicine, Complejo Hospitalario Universitario Insular-Materno Infantil, 35016 Las Palmas de Gran Canaria, SpainDepartment of Dermatology, Complejo Hospitalario Universitario Insular-Materno Infantil, 35016 Las Palmas de Gran Canaria, SpainDepartment of Mathematics and Statistics, UiT the Arctic University of Norway, 9019 Tromsø, NorwayThis 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.https://www.mdpi.com/1424-8220/21/3/680hyperspectralcurve fitstatistical discriminationmelanomabenignmalignant |
| spellingShingle | Stig Uteng Eduardo Quevedo Gustavo M. Callico Irene Castaño Gregorio Carretero Pablo Almeida Aday Garcia Javier A. Hernandez Fred Godtliebsen Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing Sensors hyperspectral curve fit statistical discrimination melanoma benign malignant |
| title | Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing |
| title_full | Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing |
| title_fullStr | Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing |
| title_full_unstemmed | Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing |
| title_short | Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing |
| title_sort | curve based classification approach for hyperspectral dermatologic data processing |
| topic | hyperspectral curve fit statistical discrimination melanoma benign malignant |
| url | https://www.mdpi.com/1424-8220/21/3/680 |
| work_keys_str_mv | AT stiguteng curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT eduardoquevedo curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT gustavomcallico curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT irenecastano curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT gregoriocarretero curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT pabloalmeida curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT adaygarcia curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT javierahernandez curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing AT fredgodtliebsen curvebasedclassificationapproachforhyperspectraldermatologicdataprocessing |