针对糖尿病足辅助诊断问题，提出了一种有效的具有两级集成卷积神经网络的深度学习方法。利用加载预训练权重的121层密集卷积网络DenseNet121和EfficientNet-B0网络作为集成卷积神经网络训练时特征提取的初始参数；再使用数据集Diabetic Foot UlcersGrand Challenge 2021进行整个网络的训练，从而实现糖尿病足伤口感染和缺血特征的TEXAS自动分期。使用5折交叉验证获得的该方法受试者工作特征曲线下面积值为0.989，准确率为0.954，查全率为0.944，查准率为0.954，F1-score为0.956。结果显示该方法性能良好，在临床辅助诊断中具有较好的应用潜力。
In order to solve the problem of diabetic foot auxiliary diagnosis, an efficient deep learning method with two-level ensemble convolutional neural network was proposed. This paper proposes an efficient deep learning method featured with two-level ensemble convolutional neural networks. The approach utilizes DenseNet121 and EfficientNet-B0 networks with pre-training weight as initial parameters for feature extraction during network training. The Diabetic Foot Ulcers Grand Challenge 2021 dataset is used to train the parameters of whole network, so as to realize the automatic staging of diabetic foot in terms of wound infection and ischemia. 5-fold cross-validation was used to verify the proposed trained network. The proposed method achieves high accuracy, with AUC (area under the receiver operating characteristic curve) value, accuracy, recall, precision, and F1-score of the network measured as 0.989, 0.954, 0.944, 0.954, 0.956, respectively. The method demonstrates promising potential for assisting the staging of diabetic foot in clinical.
[1] Shen D G, Wu G R, Suk H I. Deep learning in medical image analysis [J]. Annual Review of Biomedical Engineering, 2017, 19: 221-248.
[2] Cho N H, Shaw J E, Karuranga S, et al. IDF diabetes atlas: global estimates of diabetes prevalence for 2017 and projections for 2045[J]. Diabetes Research and Clinical Practice, 2018, 138: 271-281.
[3] Liu C J, Netten J, Ba Al J, et al. Automatic detection of diabetic foot complications with infrared thermography by asymmetric analysis [J]. Journal of Biomedical Optics, 2015, 20(2): 026003.
[4] Armstrong D G, Boulton A J M, Bus S A. Diabetic foot ulcers and their recurrence [J]. The New England Journal of Medicine, 2017, 376(24): 2367-2375.
[5] Albers M, Fratezi A C, De Luccia N. Assessment of quality of life of patients with severe ischemia as a result of infrainguinal arterial occlusive disease [J]. Journal of Vascular Surgery, 1992, 16(1): 54-59.
[6] 李志红, 郭淑芹, 李亭亭, 等. 糖尿病足Wagner分级方法和TEXAS大学分类法临床应用价值比较 [J]. 中华糖尿病杂志, 2012, 4(8): 469-473. Li Z H, Guo S Q, Li T T, et al. Comparison of the clinical value of the Wagner grading and the University of TEXAS diabetic wound classification system [J]. Chinese Journal of Diabetes Mellitus, 2012, 4(8): 469-473. (in Chinese)
[7] Patel S, Patel R, Desai D. Diabetic foot ulcer wound tissue detection and classification [C]//2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), 2017: 1-5.
[8] Wang L, Pedersen P C, Strong D M, et al. An automatic assessment system of diabetic foot ulcers based on wound area determination, color segmentation, and healing score evaluation [J]. Journal of Diabetes Science and Technology, 2015, 10(2): 421-428.
[9] Han A, Zhang Y, Li A, et al. Efficient refinements on YOLOv3 for real-time detection and assessment of diabetic foot Wagner grades [DB/OL]. 2006[2021-09-29]. https://arxiv.org/abs/2006.02322.
[10] Goyal M, Reeves N D, Davison A K, et al. DFUNet: convolutional neural networks for diabetic foot ulcer classification [J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2020, 4(5): 728-739.
[11] Goyal M, Reeves N D, Rajbhandari S, et al. Robust methods for real-time diabetic foot ulcer detection and localization on mobile devices [J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(4): 1730-1741.
[12] Goyal M, Reeves N D, Rajbhandari S, et al. Recognition of ischaemia and infection in diabetic foot ulcers: dataset and techniques [J]. Computers in Biology and Medicine, 2020, 117: 103616.
[13] Tan M, Le Q V. EfficientNet: rethinking model scaling for convolutional neural networks [C]//International Conference on Machine Learning, 2019: 1-12.
[14] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 2261-2269.
[15] Yap M H, Cassidy B, Pappachan J M, et al. Analysis towards classification of infection and ischaemia of diabetic foot ulcers [C]//2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), 2021: 1-4.
[16] Hu J, Shen L, Sun G. Squeeze-and-excitation networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[17] Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database [C]//2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009: 248- 255.
