@InProceedings{8902691,
  author = {A. Bougrine and R. Harba and R. Canals and R. Ledee and M. Jabloun},
  booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},
  title = {On the segmentation of plantar foot thermal images with Deep Learning},
  year = {2019},
  pages = {1-5},
  abstract = {Foot ulceration can be prevented by using thermal information of the plantar foot surface. Indeed, important indicators can be provided with a thermal infrared image. As part of a non-constraining acquisition protocol, these images are freehandedly taken with a smartphone equipped by a dedicated thermal camera. A total of 248 images have been obtained from an acquisition campaign composed of control and pathological subjects. Our aim is the segmentation of these plantar foot thermal images. To that end, we compare three different deep learning methods namely, the Fully Convolutional Networks (FCN), SegNet, U-Net, and the previously proposed prior shape active contour-based method. 80% of our database serves to train the 3 deep learning networks and 20% are used for the test. When applied to our data, results show that the SegNet method outperforms the three other methods with a Dice Similarity Coefficient (DSC) equal to 97.26%. This method also shows efficiency in segmenting both feet simultaneously with a DSC equal to 96.8% for a smartphone based plantar foot thermal analysis for diabetic patients.},
  keywords = {diseases;image classification;image segmentation;learning (artificial intelligence);medical image processing;patient monitoring;smart phones;foot ulceration;thermal information;plantar foot surface;thermal infrared image;nonconstraining acquisition protocol;thermal camera;plantar foot thermal images;smartphone based plantar foot thermal analysis;deep learning networks;shape active contour-based method;deep learning methods;Dice similarity coefficient;SegNet method;Foot;Image segmentation;Shape;Convolution;Deep learning;Databases;Diabetes;Plantar foot thermal images;Deep Learning;prior shape active contour;image segmentation.},
  doi = {10.23919/EUSIPCO.2019.8902691},
  issn = {2076-1465},
  month = {Sep.},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533332.pdf},
}

{"_id":"cQ2XEmr3oY6z7xiLP","bibbaseid":"bougrine-harba-canals-ledee-jabloun-onthesegmentationofplantarfootthermalimageswithdeeplearning-2019","authorIDs":[],"author_short":["Bougrine, A.","Harba, R.","Canals, R.","Ledee, R.","Jabloun, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["A."],"propositions":[],"lastnames":["Bougrine"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Harba"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Canals"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Ledee"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Jabloun"],"suffixes":[]}],"booktitle":"2019 27th European Signal Processing Conference (EUSIPCO)","title":"On the segmentation of plantar foot thermal images with Deep Learning","year":"2019","pages":"1-5","abstract":"Foot ulceration can be prevented by using thermal information of the plantar foot surface. Indeed, important indicators can be provided with a thermal infrared image. As part of a non-constraining acquisition protocol, these images are freehandedly taken with a smartphone equipped by a dedicated thermal camera. A total of 248 images have been obtained from an acquisition campaign composed of control and pathological subjects. Our aim is the segmentation of these plantar foot thermal images. To that end, we compare three different deep learning methods namely, the Fully Convolutional Networks (FCN), SegNet, U-Net, and the previously proposed prior shape active contour-based method. 80% of our database serves to train the 3 deep learning networks and 20% are used for the test. When applied to our data, results show that the SegNet method outperforms the three other methods with a Dice Similarity Coefficient (DSC) equal to 97.26%. This method also shows efficiency in segmenting both feet simultaneously with a DSC equal to 96.8% for a smartphone based plantar foot thermal analysis for diabetic patients.","keywords":"diseases;image classification;image segmentation;learning (artificial intelligence);medical image processing;patient monitoring;smart phones;foot ulceration;thermal information;plantar foot surface;thermal infrared image;nonconstraining acquisition protocol;thermal camera;plantar foot thermal images;smartphone based plantar foot thermal analysis;deep learning networks;shape active contour-based method;deep learning methods;Dice similarity coefficient;SegNet method;Foot;Image segmentation;Shape;Convolution;Deep learning;Databases;Diabetes;Plantar foot thermal images;Deep Learning;prior shape active contour;image segmentation.","doi":"10.23919/EUSIPCO.2019.8902691","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533332.pdf","bibtex":"@InProceedings{8902691,\n author = {A. Bougrine and R. Harba and R. Canals and R. Ledee and M. Jabloun},\n booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},\n title = {On the segmentation of plantar foot thermal images with Deep Learning},\n year = {2019},\n pages = {1-5},\n abstract = {Foot ulceration can be prevented by using thermal information of the plantar foot surface. Indeed, important indicators can be provided with a thermal infrared image. As part of a non-constraining acquisition protocol, these images are freehandedly taken with a smartphone equipped by a dedicated thermal camera. A total of 248 images have been obtained from an acquisition campaign composed of control and pathological subjects. Our aim is the segmentation of these plantar foot thermal images. To that end, we compare three different deep learning methods namely, the Fully Convolutional Networks (FCN), SegNet, U-Net, and the previously proposed prior shape active contour-based method. 80% of our database serves to train the 3 deep learning networks and 20% are used for the test. When applied to our data, results show that the SegNet method outperforms the three other methods with a Dice Similarity Coefficient (DSC) equal to 97.26%. This method also shows efficiency in segmenting both feet simultaneously with a DSC equal to 96.8% for a smartphone based plantar foot thermal analysis for diabetic patients.},\n keywords = {diseases;image classification;image segmentation;learning (artificial intelligence);medical image processing;patient monitoring;smart phones;foot ulceration;thermal information;plantar foot surface;thermal infrared image;nonconstraining acquisition protocol;thermal camera;plantar foot thermal images;smartphone based plantar foot thermal analysis;deep learning networks;shape active contour-based method;deep learning methods;Dice similarity coefficient;SegNet method;Foot;Image segmentation;Shape;Convolution;Deep learning;Databases;Diabetes;Plantar foot thermal images;Deep Learning;prior shape active contour;image segmentation.},\n doi = {10.23919/EUSIPCO.2019.8902691},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533332.pdf},\n}\n\n","author_short":["Bougrine, A.","Harba, R.","Canals, R.","Ledee, R.","Jabloun, M."],"key":"8902691","id":"8902691","bibbaseid":"bougrine-harba-canals-ledee-jabloun-onthesegmentationofplantarfootthermalimageswithdeeplearning-2019","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570533332.pdf"},"keyword":["diseases;image classification;image segmentation;learning (artificial intelligence);medical image processing;patient monitoring;smart phones;foot ulceration;thermal information;plantar foot surface;thermal infrared image;nonconstraining acquisition protocol;thermal camera;plantar foot thermal images;smartphone based plantar foot thermal analysis;deep learning networks;shape active contour-based method;deep learning methods;Dice similarity coefficient;SegNet method;Foot;Image segmentation;Shape;Convolution;Deep learning;Databases;Diabetes;Plantar foot thermal images;Deep Learning;prior shape active contour;image segmentation."],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2019url.bib","creationDate":"2021-02-11T19:15:21.973Z","downloads":0,"keywords":["diseases;image classification;image segmentation;learning (artificial intelligence);medical image processing;patient monitoring;smart phones;foot ulceration;thermal information;plantar foot surface;thermal infrared image;nonconstraining acquisition protocol;thermal camera;plantar foot thermal images;smartphone based plantar foot thermal analysis;deep learning networks;shape active contour-based method;deep learning methods;dice similarity coefficient;segnet method;foot;image segmentation;shape;convolution;deep learning;databases;diabetes;plantar foot thermal images;deep learning;prior shape active contour;image segmentation."],"search_terms":["segmentation","plantar","foot","thermal","images","deep","learning","bougrine","harba","canals","ledee","jabloun"],"title":"On the segmentation of plantar foot thermal images with Deep Learning","year":2019,"dataSources":["NqWTiMfRR56v86wRs","r6oz3cMyC99QfiuHW"]}