Home > Research > Publications & Outputs > Deep learning in diabetic foot ulcers detection

Links

Text available via DOI:

View graph of relations

Deep learning in diabetic foot ulcers detection: A comprehensive evaluation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Deep learning in diabetic foot ulcers detection: A comprehensive evaluation. / Yap, Moi Hoon; Hachiuma, R; Alavi, A et al.
In: Computers in biology and medicine, Vol. 135, 104596, 31.08.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Yap, MH, Hachiuma, R, Alavi, A, Brüngel, R, Cassidy, B, Goyal, M, Zhu, H, Rückert, J, Olshansky, M, Huang, X, Saito, H, Hassanpour, S, Friedrich, CM, Ascher, DB, Song, A, Kajita, H, Gillespie, D, Reeves, N, Pappachan, JM, O'Shea, C & Frank, E 2021, 'Deep learning in diabetic foot ulcers detection: A comprehensive evaluation', Computers in biology and medicine, vol. 135, 104596. https://doi.org/10.1016/j.compbiomed.2021.104596

APA

Yap, M. H., Hachiuma, R., Alavi, A., Brüngel, R., Cassidy, B., Goyal, M., Zhu, H., Rückert, J., Olshansky, M., Huang, X., Saito, H., Hassanpour, S., Friedrich, C. M., Ascher, D. B., Song, A., Kajita, H., Gillespie, D., Reeves, N., Pappachan, J. M., ... Frank, E. (2021). Deep learning in diabetic foot ulcers detection: A comprehensive evaluation. Computers in biology and medicine, 135, Article 104596. https://doi.org/10.1016/j.compbiomed.2021.104596

Vancouver

Yap MH, Hachiuma R, Alavi A, Brüngel R, Cassidy B, Goyal M et al. Deep learning in diabetic foot ulcers detection: A comprehensive evaluation. Computers in biology and medicine. 2021 Aug 31;135:104596. Epub 2021 Jul 8. doi: 10.1016/j.compbiomed.2021.104596

Author

Yap, Moi Hoon ; Hachiuma, R ; Alavi, A et al. / Deep learning in diabetic foot ulcers detection : A comprehensive evaluation. In: Computers in biology and medicine. 2021 ; Vol. 135.

Bibtex

@article{17f4e84a6bcb4c84a00230e93d5d1eb9,
title = "Deep learning in diabetic foot ulcers detection: A comprehensive evaluation",
abstract = "There has been a substantial amount of research involving computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training and 2,000 images for testing. This paper summarizes the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R–CNN, three variants of Faster R–CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance was obtained from Deformable Convolution, a variant of Faster R–CNN, with a mean average precision (mAP) of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhance the F1-Score but not the mAP.",
author = "Yap, {Moi Hoon} and R Hachiuma and A Alavi and R Br{\"u}ngel and Bill Cassidy and M Goyal and H Zhu and J R{\"u}ckert and M Olshansky and X Huang and H Saito and S Hassanpour and Friedrich, {C M} and Ascher, {D B} and A Song and H Kajita and David Gillespie and Neil Reeves and Pappachan, {J M} and C O'Shea and E Frank",
year = "2021",
month = aug,
day = "31",
doi = "10.1016/j.compbiomed.2021.104596",
language = "English",
volume = "135",
journal = "Computers in biology and medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

RIS

TY - JOUR

T1 - Deep learning in diabetic foot ulcers detection

T2 - A comprehensive evaluation

AU - Yap, Moi Hoon

AU - Hachiuma, R

AU - Alavi, A

AU - Brüngel, R

AU - Cassidy, Bill

AU - Goyal, M

AU - Zhu, H

AU - Rückert, J

AU - Olshansky, M

AU - Huang, X

AU - Saito, H

AU - Hassanpour, S

AU - Friedrich, C M

AU - Ascher, D B

AU - Song, A

AU - Kajita, H

AU - Gillespie, David

AU - Reeves, Neil

AU - Pappachan, J M

AU - O'Shea, C

AU - Frank, E

PY - 2021/8/31

Y1 - 2021/8/31

N2 - There has been a substantial amount of research involving computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training and 2,000 images for testing. This paper summarizes the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R–CNN, three variants of Faster R–CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance was obtained from Deformable Convolution, a variant of Faster R–CNN, with a mean average precision (mAP) of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhance the F1-Score but not the mAP.

AB - There has been a substantial amount of research involving computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training and 2,000 images for testing. This paper summarizes the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R–CNN, three variants of Faster R–CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance was obtained from Deformable Convolution, a variant of Faster R–CNN, with a mean average precision (mAP) of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhance the F1-Score but not the mAP.

U2 - 10.1016/j.compbiomed.2021.104596

DO - 10.1016/j.compbiomed.2021.104596

M3 - Journal article

C2 - 34247133

VL - 135

JO - Computers in biology and medicine

JF - Computers in biology and medicine

SN - 0010-4825

M1 - 104596

ER -