期刊
COMPUTERS IN BIOLOGY AND MEDICINE
卷 135, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2021.104596
关键词
Diabetic foot ulcers; Object detection; Machine learning; Deep learning; DFUC2020
类别
资金
- NVIDIA Corporation
- National Health and Medical Research Council [GNT1174405]
- Victorian Government's OIS Program
- University of Applied Sciences and Arts Dortmund, Dortmund, Germany
This paper summarized the results of DFUC2020 by comparing various deep learning algorithms for the detection of diabetic foot ulcers, highlighting the best performance achieved by Deformable Convolution method. The study showed that ensemble methods based on different deep learning techniques can enhance F1-Score but not mAP.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据