Your browser doesn't support javascript.
loading
Deep learning in diabetic foot ulcers detection: A comprehensive evaluation.
Yap, Moi Hoon; Hachiuma, Ryo; Alavi, Azadeh; Brüngel, Raphael; Cassidy, Bill; Goyal, Manu; Zhu, Hongtao; Rückert, Johannes; Olshansky, Moshe; Huang, Xiao; Saito, Hideo; Hassanpour, Saeed; Friedrich, Christoph M; Ascher, David B; Song, Anping; Kajita, Hiroki; Gillespie, David; Reeves, Neil D; Pappachan, Joseph M; O'Shea, Claire; Frank, Eibe.
Afiliação
  • Yap MH; Faculty of Science and Engineering, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester, M1 5GD, UK. Electronic address: m.yap@mmu.ac.uk.
  • Hachiuma R; Keio University, Yokohama, Kanagawa, Japan.
  • Alavi A; Baker Heart and Diabetes Institute, 20 Commercial Road, Melbourne, VIC, 3000, Australia.
  • Brüngel R; Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Str. 42, 44227 Dortmund, Germany; Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen, Hufelandstr. 55, 45122, Essen, Germany.
  • Cassidy B; Faculty of Science and Engineering, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester, M1 5GD, UK.
  • Goyal M; Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA.
  • Zhu H; Shanghai University, Shanghai, 200444, China.
  • Rückert J; Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Str. 42, 44227 Dortmund, Germany.
  • Olshansky M; Baker Heart and Diabetes Institute, 20 Commercial Road, Melbourne, VIC, 3000, Australia.
  • Huang X; Shanghai University, Shanghai, 200444, China.
  • Saito H; Keio University, Yokohama, Kanagawa, Japan.
  • Hassanpour S; Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA.
  • Friedrich CM; Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Str. 42, 44227 Dortmund, Germany; Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen, Hufelandstr. 55, 45122, Essen, Germany.
  • Ascher DB; Baker Heart and Diabetes Institute, 20 Commercial Road, Melbourne, VIC, 3000, Australia.
  • Song A; Shanghai University, Shanghai, 200444, China.
  • Kajita H; Keio University School of Medicine, Shinanomachi, Tokyo, Japan.
  • Gillespie D; Faculty of Science and Engineering, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester, M1 5GD, UK.
  • Reeves ND; Faculty of Science and Engineering, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester, M1 5GD, UK.
  • Pappachan JM; Lancashire Teaching Hospitals, Chorley, UK.
  • O'Shea C; Waikato Diabetes Health Board, Hamilton, New Zealand.
  • Frank E; Department of Computer Science, University of Waikato, Hamilton, New Zealand.
Comput Biol Med ; 135: 104596, 2021 08.
Article em En | MEDLINE | ID: mdl-34247133
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.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Pé Diabético / Diabetes Mellitus / Aprendizado Profundo Tipo de estudo: Diagnostic_studies / Prognostic_studies Limite: Humans Idioma: En Ano de publicação: 2021 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Pé Diabético / Diabetes Mellitus / Aprendizado Profundo Tipo de estudo: Diagnostic_studies / Prognostic_studies Limite: Humans Idioma: En Ano de publicação: 2021 Tipo de documento: Article