Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation
Manchester Metropolitan University（曼彻斯特城市大学）；Keio University（庆应义塾大学）；Baker Heart and Diabetes Institute（贝克心脏与糖尿病研究所）；University of Applied Sciences and Arts Dortmund (FH Dortmund)（多特蒙德应用科学与艺术大学）；Dartmouth College（达特茅斯学院）；Shanghai University（上海大学）
Moi Hoon Yap, Ryo Hachiuma, Azadeh Alavi, Raphael Brungel, Bill Cassidy, Manu Goyal, Hongtao Zhu, Johannes Ruckert, Moshe Olshansky, Xiao Huang, Hideo Saito, Sa… 展开作者
Moi Hoon Yap, Ryo Hachiuma, Azadeh Alavi, Raphael Brungel, Bill Cassidy, Manu Goyal, Hongtao Zhu, Johannes Ruckert, Moshe Olshansky, Xiao Huang, Hideo Saito, Saeed Hassanpour, Christoph M. Friedrich, David Ascher, Anping Song, Hiroki Kajita, David Gillespie, Neil D. Reeves, Joseph Pappachan, Claire O'Shea, Eibe Frank
备注：
19 pages, 18 figures, 10 tables
发表信息：
Computers in Biology and Medicine, Volume 135, 2021, 104596, ISSN 0010-4825,
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 summarises 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 enhanced the F1-Score but not the mAP.
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospitals NHS Foundation Trust（兰开夏教学医院NHS基金会信托）；Waikato District Health Board（怀卡托地区卫生委员会）
DFUNet: Convolutional Neural Networks for Diabetic Foot Ulcer Classification
Manchester Metropolitan University（曼彻斯特城市大学）；University of Manchester（曼彻斯特大学）；Lancashire Teaching Hospital（兰开夏教学医院）；Lancashire Care NHS Foundation Trust（兰开夏护理NHS基金会信托）
Diabetic Foot Ulcer Grand Challenge 2021: Evaluation and Summary
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospitals NHS Foundation Trust（兰开夏教学医院NHS基金会信托）；Waikato District Health Board（怀卡托地区卫生局）；University of Southern California（南加利福尼亚大学）
A Cloud-based Deep Learning Framework for Remote Detection of Diabetic Foot Ulcers
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospitals NHS Foundation Trust（兰开夏教学医院NHS基金会信托）；The University of Manchester（曼彻斯特大学）；Manchester University NHS Foundation Trust（曼彻斯特大学NHS基金会信托）；Salford Royal NHS Foundation Trust（索尔福德皇家NHS基金会信托）
Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers
Faculty of Science and Engineering, Manchester Metropolitan University（曼彻斯特城市大学科学与工程学院）；Lanchashire Teaching Hospitals（兰开夏教学医院）；Waikato District Health Board（怀卡托地区卫生局）
Translating Clinical Delineation of Diabetic Foot Ulcers into Machine Interpretable Segmentation
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospitals NHS Foundation Trust（兰开夏教学医院NHS基金会信托）；Waikato District Health Board（怀卡托地区卫生委员会）；United Lincolnshire Hospitals NHS Trust（联合林肯郡医院NHS信托）；Jersey General Hospital（泽西总医院）；Eastbourne District General Hospital（伊斯特本地区综合医院）
A quantitative comparison of plantar soft tissue strainability distribution and homogeneity between ulcerated and non-ulcerated patients using strain elastography
Staffordshire University（斯塔福德郡大学）；AR Diabetes Hospitals（AR糖尿病医院）；Technische Universität München（慕尼黑工业大学）
DFUC2020: Analysis Towards Diabetic Foot Ulcer Detection
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospital（兰开夏教学医院）；Waikato District Health Board（怀卡托地区卫生委员会）；Manipal College of Health Professions（马尼帕尔健康专业学院）；University of Waikato（怀卡托大学）；University of Manchester（曼彻斯特大学）；University of Southern California（南加州大学）；Baylor College of Medicine（贝勒医学院）
UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription
KITE Research Institute（凯特研究所）；University Health Network（大学健康网络）；Institute of Biomedical Engineering, University of Toronto（多伦多大学生物医学工程研究所）；University of Toronto Mississauga（多伦多大学密西沙加分校）
Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers
University of Applied Sciences and Arts Dortmund (FH Dortmund)（多特蒙德应用科学与艺术大学）；University Hospital Essen（埃森大学医院）
ConMatFormer: A Multi-attention and Transformer Integrated ConvNext based Deep Learning Model for Enhanced Diabetic Foot Ulcer Classification
Department of Information Technology（信息科技系）；Charles Darwin University（查尔斯·达尔文大学）；Department of Computer Science and Engineering（计算机科学与工程系）；University of Liberal Arts Bangladesh（孟加拉自由大学）；BRAC University（BRAC大学）；Center for Advanced Analytics (CAA), COE for Artificial Intelligence, Faculty of Engineering & Technology (FET)（高级分析中心（CAA）、人工智能学院、工程与技术学院）；Multimedia University Melaka（马六甲多媒体大学）；American International University-Bangladesh（美国国际大学-孟加拉）
Domain-Specific Deep Learning Feature Extractor for Diabetic Foot Ulcer Detection
Institute of Biomedical Engineering, University of Toronto（多伦多大学生物医学工程研究所）；KITE, Toronto Rehabilitation Institute, University Health Network（大学健康网络多伦多康复研究所KITE部门）
Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques
Manchester Metropolitan University（曼彻斯特城市大学）；Lancashire Teaching Hospital（兰开夏教学医院）；University of Manchester（曼彻斯特大学）；Manchester Royal Infirmary（曼彻斯特皇家医院）；Sun Yat-sen University（中山大学）
Synthesizing Diabetic Foot Ulcer Images with Diffusion Model
Institute of Biomedical Engineering, University of Toronto（多伦多大学生物医学工程研究所）；University Health Network（多伦多大学健康网络）；Zivot Limb Preservation Centre, Peter Lougheed Centre（齐沃特肢体保护中心（彼得·劳埃德中心））；Cumming School of Medicine, University of Calgary（卡尔加里大学卡明医学院）
WoundNet-Ensemble: A Novel IoMT System Integrating Self-Supervised Deep Learning and Multi-Model Fusion for Automated, High-Accuracy Wound Classification and Healing Progression Monitoring
The Catholic University of America（美国天主教大学）；Center for Advanced Research in Computer Engineering（计算机工程高级研究中心）
Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification
Department of Mechanical and Aerospace Engineering, Missouri University of Science and Technology（密苏里科技大学机械与航空航天工程系）；Intelligent System Center, Missouri University of Science and Technology（密苏里科技大学智能系统中心）；Center for Biomedical Research, Missouri University of Science and Technology（密苏里科技大学生物医学研究中心）；Wound Care Department, Charles George Department of Veterans Affairs Medical Center（查尔斯·乔治退伍军人事务医疗中心伤口护理部）
University of Wisconsin-Milwaukee（威斯康星大学密尔沃基分校）；Institute for Pathophysiology and Allergy Research, Medical University of Vienna（维也纳医科大学病理生理学与过敏研究所）；Bournemouth University（伯恩茅斯大学）；Advancing the Zenith of Healthcare (AZH) Wound and Vascular Center（AZH伤口与血管中心）
Explainable Continuous-Time Mask Refinement with Local Self-Similarity Priors for Medical Image Segmentation
School of Computer Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, India（计算机工程学院，印度克里希纳加尔工业技术学院，布巴内斯瓦尔，印度）；AmygdalaAI-India Lab, Bhubaneswar, India（AmygdalaAI-印度实验室，布巴内斯瓦尔，印度）
Robust and Annotation-Free Wound Segmentation on Noisy Real-World Pressure Ulcer Images: Towards Automated DESIGN-R\textsuperscript{\textregistered} Assessment
Fully Automatic Wound Segmentation with Deep Convolutional Neural Networks
University of Wisconsin-Milwaukee（威斯康星大学密尔沃基分校）；Advancing the Zenith of Healthcare (AZH) Wound and Vascular Center（医疗保健提升巅峰伤口与血管中心）；College of Nursing, University of Wisconsin Milwaukee（威斯康星大学密尔沃基分校护理学院）
CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Prompting
University of Exeter（埃克塞特大学）；University of Liverpool（利物浦大学）；Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences（中国科学院宁波材料技术与工程研究所）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）
Integrating Vision and Location with Transformers: A Multimodal Deep Learning Framework for Medical Wound Analysis
University of Zanjan（赞詹大学）；Islamic Azad University Science and Research Branch（伊斯兰阿扎德大学科学与研究分支）；Samarkand State University named after Sharof Rashidov（沙罗夫·拉希多夫命名的撒马尔罕州立大学）；Kimyo International University In Tashkent（塔什干基莫国际大学）；University of Tehran（德黑兰大学）；Drexel University（德雷塞尔大学）
Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach
University of Wisconsin-Milwaukee（威斯康星大学密尔沃基分校）；Advancing the Zenith of Healthcare (AZH) Wound and Vascular Center（医疗保健提升巅峰伤口与血管中心）；University of Wisconsin Milwaukee（威斯康星大学密尔沃基分校）
