Segmentation Approaches for Diabetic Foot Disorders
Thermography enables non-invasive, accessible, and easily repeated foot temperature measurements for diabetic patients, promoting early detection and regular monitoring protocols, that limit the incidence of disabling conditions associated with diabetic foot disorders. The establishment of this appl...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/934 |
| _version_ | 1827596788038631424 |
|---|---|
| author | Natalia Arteaga-Marrero Abián Hernández Enrique Villa Sara González-Pérez Carlos Luque Juan Ruiz-Alzola |
| author_facet | Natalia Arteaga-Marrero Abián Hernández Enrique Villa Sara González-Pérez Carlos Luque Juan Ruiz-Alzola |
| author_sort | Natalia Arteaga-Marrero |
| collection | DOAJ |
| description | Thermography enables non-invasive, accessible, and easily repeated foot temperature measurements for diabetic patients, promoting early detection and regular monitoring protocols, that limit the incidence of disabling conditions associated with diabetic foot disorders. The establishment of this application into standard diabetic care protocols requires to overcome technical issues, particularly the foot sole segmentation. In this work we implemented and evaluated several segmentation approaches which include conventional and Deep Learning methods. Multimodal images, constituted by registered visual-light, infrared and depth images, were acquired for 37 healthy subjects. The segmentation methods explored were based on both visual-light as well as infrared images, and optimization was achieved using the spatial information provided by the depth images. Furthermore, a ground truth was established from the manual segmentation performed by two independent researchers. Overall, the performance level of all the implemented approaches was satisfactory. Although the best performance, in terms of spatial overlap, accuracy, and precision, was found for the Skin and U-Net approaches optimized by the spatial information. However, the robustness of the U-Net approach is preferred. |
| first_indexed | 2024-03-09T03:15:26Z |
| format | Article |
| id | doaj.art-e57fdcfb3294485d909cb79eb78ff491 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:15:26Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e57fdcfb3294485d909cb79eb78ff4912023-12-03T15:23:26ZengMDPI AGSensors1424-82202021-01-0121393410.3390/s21030934Segmentation Approaches for Diabetic Foot DisordersNatalia Arteaga-Marrero0Abián Hernández1Enrique Villa2Sara González-Pérez3Carlos Luque4Juan Ruiz-Alzola5IACTEC Medical Technology Group, Instituto de Astrofísica de Canarias (IAC), 38205 San Cristóbal de La Laguna, SpainResearch Institute of Biomedical and Health Sciences (IUIBS), Universidad de Las Palmas de Gran Canaria, 35016 Las Palmas de Gran Canaria, SpainIACTEC Medical Technology Group, Instituto de Astrofísica de Canarias (IAC), 38205 San Cristóbal de La Laguna, SpainIACTEC Medical Technology Group, Instituto de Astrofísica de Canarias (IAC), 38205 San Cristóbal de La Laguna, SpainIACTEC Medical Technology Group, Instituto de Astrofísica de Canarias (IAC), 38205 San Cristóbal de La Laguna, SpainIACTEC Medical Technology Group, Instituto de Astrofísica de Canarias (IAC), 38205 San Cristóbal de La Laguna, SpainThermography enables non-invasive, accessible, and easily repeated foot temperature measurements for diabetic patients, promoting early detection and regular monitoring protocols, that limit the incidence of disabling conditions associated with diabetic foot disorders. The establishment of this application into standard diabetic care protocols requires to overcome technical issues, particularly the foot sole segmentation. In this work we implemented and evaluated several segmentation approaches which include conventional and Deep Learning methods. Multimodal images, constituted by registered visual-light, infrared and depth images, were acquired for 37 healthy subjects. The segmentation methods explored were based on both visual-light as well as infrared images, and optimization was achieved using the spatial information provided by the depth images. Furthermore, a ground truth was established from the manual segmentation performed by two independent researchers. Overall, the performance level of all the implemented approaches was satisfactory. Although the best performance, in terms of spatial overlap, accuracy, and precision, was found for the Skin and U-Net approaches optimized by the spatial information. However, the robustness of the U-Net approach is preferred.https://www.mdpi.com/1424-8220/21/3/934segmentationthermography (D013817)diabetic foot (D017719)diabetic neuropathy (D003929)supervised and unsupervised algorithms |
| spellingShingle | Natalia Arteaga-Marrero Abián Hernández Enrique Villa Sara González-Pérez Carlos Luque Juan Ruiz-Alzola Segmentation Approaches for Diabetic Foot Disorders Sensors segmentation thermography (D013817) diabetic foot (D017719) diabetic neuropathy (D003929) supervised and unsupervised algorithms |
| title | Segmentation Approaches for Diabetic Foot Disorders |
| title_full | Segmentation Approaches for Diabetic Foot Disorders |
| title_fullStr | Segmentation Approaches for Diabetic Foot Disorders |
| title_full_unstemmed | Segmentation Approaches for Diabetic Foot Disorders |
| title_short | Segmentation Approaches for Diabetic Foot Disorders |
| title_sort | segmentation approaches for diabetic foot disorders |
| topic | segmentation thermography (D013817) diabetic foot (D017719) diabetic neuropathy (D003929) supervised and unsupervised algorithms |
| url | https://www.mdpi.com/1424-8220/21/3/934 |
| work_keys_str_mv | AT nataliaarteagamarrero segmentationapproachesfordiabeticfootdisorders AT abianhernandez segmentationapproachesfordiabeticfootdisorders AT enriquevilla segmentationapproachesfordiabeticfootdisorders AT saragonzalezperez segmentationapproachesfordiabeticfootdisorders AT carlosluque segmentationapproachesfordiabeticfootdisorders AT juanruizalzola segmentationapproachesfordiabeticfootdisorders |