Segmentation of Plantar Foot Thermal Images Using Prior Information
Diabetic foot (DF) complications are associated with temperature variations. The occurrence of DF ulceration could be reduced by using a contactless thermal camera. The aim of our study is to provide a decision support tool for the prevention of DF ulcers. Thus, the segmentation of the plantar foot...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/10/3835 |
| _version_ | 1797495662961491968 |
|---|---|
| author | Asma Bougrine Rachid Harba Raphael Canals Roger Ledee Meryem Jabloun Alain Villeneuve |
| author_facet | Asma Bougrine Rachid Harba Raphael Canals Roger Ledee Meryem Jabloun Alain Villeneuve |
| author_sort | Asma Bougrine |
| collection | DOAJ |
| description | Diabetic foot (DF) complications are associated with temperature variations. The occurrence of DF ulceration could be reduced by using a contactless thermal camera. The aim of our study is to provide a decision support tool for the prevention of DF ulcers. Thus, the segmentation of the plantar foot in thermal images is a challenging step for a non-constraining acquisition protocol. This paper presents a new segmentation method for plantar foot thermal images. This method is designed to include five pieces of prior information regarding the aforementioned images. First, a new energy term is added to the snake of Kass et al. in order to force its curvature to match that of the prior shape, which has a known form. Second, we defined the initial contour as the downsized prior-shape contour, which is placed inside the plantar foot surface in a vertical orientation. This choice makes the snake avoid strong false boundaries present outside the plantar region when evolving. As a result, the snake produces a smooth contour that rapidly converges to the true boundaries of the foot. The proposed method is compared to two classical prior-shape snake methods, that of Ahmed et al. and that of Chen et al. A database of 50 plantar foot thermal images was processed. The results show that the proposed method outperforms the previous two methods with a root-mean-square error of 5.12 pixels and a dice similarity coefficient of 94%. The segmentation of the plantar foot regions in the thermal images helped us to assess the point-to-point temperature differences between the two feet in order to detect hyperthermia regions. The presence of such regions is the pre-sign of ulcers in the diabetic foot. Furthermore, our method was applied to hyperthermia detection to illustrate the promising potential of thermography in the case of the diabetic foot. Associated with a friendly acquisition protocol, the proposed segmentation method is the first step for a future mobile smartphone-based plantar foot thermal analysis for diabetic foot patients. |
| first_indexed | 2024-03-10T01:52:51Z |
| format | Article |
| id | doaj.art-5490aff82980441c81088575735e6465 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:52:51Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5490aff82980441c81088575735e64652023-11-23T13:02:02ZengMDPI AGSensors1424-82202022-05-012210383510.3390/s22103835Segmentation of Plantar Foot Thermal Images Using Prior InformationAsma Bougrine0Rachid Harba1Raphael Canals2Roger Ledee3Meryem Jabloun4Alain Villeneuve5Multidisciplinary Research Laboratory in Systems Engineering, Mechanics and Energy (PRISME), University of Orleans, 12 rue de Blois, 45067 Orleans, FranceMultidisciplinary Research Laboratory in Systems Engineering, Mechanics and Energy (PRISME), University of Orleans, 12 rue de Blois, 45067 Orleans, FranceMultidisciplinary Research Laboratory in Systems Engineering, Mechanics and Energy (PRISME), University of Orleans, 12 rue de Blois, 45067 Orleans, FranceMultidisciplinary Research Laboratory in Systems Engineering, Mechanics and Energy (PRISME), University of Orleans, 12 rue de Blois, 45067 Orleans, FranceMultidisciplinary Research Laboratory in Systems Engineering, Mechanics and Energy (PRISME), University of Orleans, 12 rue de Blois, 45067 Orleans, FranceThe Diabetic Foot Service, Regional Hospital of Orleans, 45100 Orleans, FranceDiabetic foot (DF) complications are associated with temperature variations. The occurrence of DF ulceration could be reduced by using a contactless thermal camera. The aim of our study is to provide a decision support tool for the prevention of DF ulcers. Thus, the segmentation of the plantar foot in thermal images is a challenging step for a non-constraining acquisition protocol. This paper presents a new segmentation method for plantar foot thermal images. This method is designed to include five pieces of prior information regarding the aforementioned images. First, a new energy term is added to the snake of Kass et al. in order to force its curvature to match that of the prior shape, which has a known form. Second, we defined the initial contour as the downsized prior-shape contour, which is placed inside the plantar foot surface in a vertical orientation. This choice makes the snake avoid strong false boundaries present outside the plantar region when evolving. As a result, the snake produces a smooth contour that rapidly converges to the true boundaries of the foot. The proposed method is compared to two classical prior-shape snake methods, that of Ahmed et al. and that of Chen et al. A database of 50 plantar foot thermal images was processed. The results show that the proposed method outperforms the previous two methods with a root-mean-square error of 5.12 pixels and a dice similarity coefficient of 94%. The segmentation of the plantar foot regions in the thermal images helped us to assess the point-to-point temperature differences between the two feet in order to detect hyperthermia regions. The presence of such regions is the pre-sign of ulcers in the diabetic foot. Furthermore, our method was applied to hyperthermia detection to illustrate the promising potential of thermography in the case of the diabetic foot. Associated with a friendly acquisition protocol, the proposed segmentation method is the first step for a future mobile smartphone-based plantar foot thermal analysis for diabetic foot patients.https://www.mdpi.com/1424-8220/22/10/3835prior-shape-based segmentationactive contoursplantar foot thermal imagesinfrared cameradiabetic foothyperthermia |
| spellingShingle | Asma Bougrine Rachid Harba Raphael Canals Roger Ledee Meryem Jabloun Alain Villeneuve Segmentation of Plantar Foot Thermal Images Using Prior Information Sensors prior-shape-based segmentation active contours plantar foot thermal images infrared camera diabetic foot hyperthermia |
| title | Segmentation of Plantar Foot Thermal Images Using Prior Information |
| title_full | Segmentation of Plantar Foot Thermal Images Using Prior Information |
| title_fullStr | Segmentation of Plantar Foot Thermal Images Using Prior Information |
| title_full_unstemmed | Segmentation of Plantar Foot Thermal Images Using Prior Information |
| title_short | Segmentation of Plantar Foot Thermal Images Using Prior Information |
| title_sort | segmentation of plantar foot thermal images using prior information |
| topic | prior-shape-based segmentation active contours plantar foot thermal images infrared camera diabetic foot hyperthermia |
| url | https://www.mdpi.com/1424-8220/22/10/3835 |
| work_keys_str_mv | AT asmabougrine segmentationofplantarfootthermalimagesusingpriorinformation AT rachidharba segmentationofplantarfootthermalimagesusingpriorinformation AT raphaelcanals segmentationofplantarfootthermalimagesusingpriorinformation AT rogerledee segmentationofplantarfootthermalimagesusingpriorinformation AT meryemjabloun segmentationofplantarfootthermalimagesusingpriorinformation AT alainvilleneuve segmentationofplantarfootthermalimagesusingpriorinformation |