Abstract
Diabetic foot ulcers (DFU) are one of the most common and severe complications of diabetes. More than one million diabetics face amputation due to failure to recognize and treat DFU properly every year, and it is very important to early recognize the condition of DFU. As deep learning has achieved outstanding results in computer vision tasks, some deep learning methods have been used for diabetic foot ulcer image classification. However, these models do not pay attention to the learning of color information in images and may not effectively learn the characteristics of hard examples, which are difficult to recognize by models trained by common loss functions. In addition, they may be time-consuming or not suitable for small datasets. According to DFU medical classification systems, the presence of infection and ischemia has important clinical implications for DFU assessment. In our work, based on the characteristics of gangrene and wound, which are significantly different from the surrounding skin and the background, we use the K-Means algorithm to segment the features and further build the classification model with the segmentation module. Next, we use focal loss to train EfficientNet B3, which can make this model better learn the characteristics of hard examples. We finally use the two powerful networks for testing. The experimental results demonstrate that compared with other excellent classification models, our model has better performance with a macro-average F1-score of 0.6334, which has great potential in medical assisted diagnosis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aguiree, F., et al.: IDF diabetes atlas (2013)
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. Vasc. Surg. 16(1), 54–59 (1992)
Alzubaidi, L., Fadhel, M.A., Oleiwi, S.R., Al-Shamma, O., Zhang, J.: DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimedia Tools Appl. 79(21), 15655–15677 (2020)
Armstrong, D.G., Boulton, A.J., Bus, S.A.: Diabetic foot ulcers and their recurrence. New England J. Med. 376(24), 2367–2375 (2017)
Armstrong, D.G., Lavery, L.A., Harkless, L.B.: Validation of a diabetic wound classification system: the contribution of depth, infection, and ischemia to risk of amputation. Diabetes Care 21(5), 855–859 (1998)
Bloch, L., Brüngel, R., Friedrich, C.M.: Boosting efficientnets ensemble performance via pseudo-labels and synthetic images by pix2pixHD for infection and ischaemia classification in diabetic foot ulcers. arXiv preprint arXiv:2112.00065 (2021). https://doi.org/10.1007/978-3-030-94907-5_3
Cassidy, B., et al.: Diabetic foot ulcer grand challenge 2021: evaluation and summary. arXiv preprint arXiv:2111.10376 (2021). https://doi.org/10.1007/978-3-030-94907-5_7
Cassidy, B., et al.: DFUC 2020: analysis towards diabetic foot ulcer detection. arXiv abs/2004.11853 (2021)
Cassidy, B., et al.: The DFUC 2020 dataset: analysis towards diabetic foot ulcer detection. TouchREV. Endocrinol. 17(1), 5–11 (2021)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Dosovitskiy, A., et al.: An image is worth 16\(\,\times \,\)16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412 (2020)
Galdran, A., Carneiro, G., Ballester, M.A.G.: Convolutional nets versus vision transformers for diabetic foot ulcer classification. arXiv preprint arXiv:2111.06894 (2021)
Goyal, M., Reeves, N.D., Davison, A.K., Rajbhandari, S., Spragg, J., Yap, M.H.: DFUNet: convolutional neural networks for diabetic foot ulcer classification. IEEE Trans. Emerg. Top. Comput. Intell. 4(5), 728–739 (2018)
Goyal, M., Reeves, N.D., Rajbhandari, S., Ahmad, N., Wang, C., Yap, M.H.: Recognition of ischaemia and infection in diabetic foot ulcers: dataset and techniques. Comput. Biol. Med. 117, 103616 (2020)
Goyal, M., Reeves, N.D., Rajbhandari, S., Yap, M.H.: Robust methods for real-time diabetic foot ulcer detection and localization on mobile devices. IEEE J. Biomed. Health Inform. 23(4), 1730–1741 (2018)
Goyal, M., Yap, M.H., Reeves, N.D., Rajbhandari, S., Spragg, J.: Fully convolutional networks for diabetic foot ulcer segmentation. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 618–623. IEEE (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Korpelevich, G.M.: The extragradient method for finding saddle points and other problems. Matecon 12, 747–756 (1976)
Lavery, L.A., Armstrong, D.G., Wunderlich, R.P., Tredwell, J., Boulton, A.J.: Diabetic foot syndrome: evaluating the prevalence and incidence of foot pathology in Mexican Americans and non-Hispanic whites from a diabetes disease management cohort. Diabetes Care 26(5), 1435–1438 (2003)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Lipsky, B.A., et al.: 2012 infectious diseases society of America clinical practice guideline for the diagnosis and treatment of diabetic foot infections. Clin. Infect. Dis. 54(12), e132–e173 (2012)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Mills Sr, J.L., et al.: Society for Vascular Surgery Lower Extremity Guidelines Committee. The society for vascular surgery lower extremity threatened limb classification system: risk stratification based on wound, ischemia, and foot infection (WIfI). J. Vasc. Surg. 59(1), 220–234 (2014)
Patel, S., Patel, R., Desai, D.: Diabetic foot ulcer wound tissue detection and classification. In: 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS). pp. 1–5. IEEE (2017)
Prompers, L., et al.: High prevalence of ischaemia, infection and serious comorbidity in patients with diabetic foot disease in Europe. Baseline results from the Eurodiale study. Diabetologia 50(1), 18–25 (2007)
Rania, N., Douzi, H., Yves, L., Sylvie, T.: Semantic segmentation of diabetic foot ulcer images: dealing with small dataset in DL approaches. In: El Moataz, A., Mammass, D., Mansouri, A., Nouboud, F. (eds.) ICISP 2020. LNCS, vol. 12119, pp. 162–169. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-51935-3_17
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2016)
Roglic, G., et al.: WHO Global report on diabetes: a summary. Int. J. Noncommun. Dis. 1(1), 3 (2016)
Saeedi, P., et al.: Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the international diabetes federation diabetes atlas. Diabetes Res. Clin. Pract. 157, 107843 (2019)
Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Vardasca, R., Magalhaes, C., Seixas, A., Carvalho, R., Mendes, J.: Diabetic foot monitoring using dynamic thermography and AI classifiers. In: Proceedings of the 3rd Quantitative InfraRed Thermography Asia Conference (QIRT Asia 2019), Tokyo, Japan. pp. 1–5 (2019)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Xu, Y., Han, K., Zhou, Y., Wu, J., Xie, X., Xiang, W.: Classification of diabetic foot ulcers using class knowledge banks. Front. Bioeng. Biotechnol. 9 (2021)
Yap, M.H., Cassidy, B., Pappachan, J.M., O’Shea, C., Gillespie, D., Reeves, N.: Analysis towards classification of infection and ischaemia of diabetic foot ulcers. arXiv preprint arXiv:2104.03068 (2021)
Acknowledgements
We have obtained the authorization of the organizers of DFUC 2021 for research, who have received approval from the UK National Health Service (NHS) Research Ethics Committee (REC). The computation is supported by the School of Computer Engineering and Science of Shanghai University. This work is supported by the NSFCs of China (No. 61902234).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xie, C. (2023). FCFNet: A Network Fusing Color Features and Focal Loss for Diabetic Foot Ulcer Image Classification. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1793. Springer, Singapore. https://doi.org/10.1007/978-981-99-1645-0_36
Download citation
DOI: https://doi.org/10.1007/978-981-99-1645-0_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1644-3
Online ISBN: 978-981-99-1645-0
eBook Packages: Computer ScienceComputer Science (R0)