Abstract
Most existing image classification methods have achieved significant progress in the field of natural images. However, in the field of diabetic foot ulcer (DFU) where data is scarce and complex, the accurate classification of data is still a thorny problem. In this paper, we propose an Asymmetric Convolutional Transformer Network (ACTNet) for the multi-class (4-class) classification task of DFU. Specifically, in order to strengthen the expressive ability of the network, we design an asymmetric convolutional module in the front part of the network to model the relationship between local pixels, extract the underlying features of the image, and guide the network to focus on the central region in the image that contains more information. Furthermore, a novel pooling layer is added between the encoder and the classification head in the Transformer, which weights the data sequence generated by the encoder to better correlate the features between the input data. Finally, to fully exploit the performance of the model, we pretrained our model on ImageNet and fine-tune it on DFU images. The model is validated on the DFUC2021 test set, and the F1-score and AUC value are 0.593 and 0.824, respectively. The experiments show that our model has excellent performance even in the case of a small dataset.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Armstrong DG, Lavery LA, Harkless LB (1998) Validation of a diabetic wound classification system. the contribution of depth, infection, and ischemia to risk of amputation. Diabetes Care 21(5):855–859
Ingelfinger JR, Armstrong DG, Boulton A et al (2017) Diabetic foot ulcers and their recurrence. N Engl J Med 376:2367–2375
Ince P, Abbas ZG, Lutale JK, Basit A, Ali SM, Chohan F, Morbach S, Mollenberg J, Game FL, Jeffcoate WJ (2008) Use of the SINBAD classification system and score in comparing outcome of foot ulcer management on three continents. Diabetes Care 31(5):964–967
Lavery LA, Armstrong DG, Harkless LB (1996) Classification of diabetic foot wounds. J Foot Ankle Surg 35(6):528–31
Wagner FW (1987) The diabetic foot. Orthopedics 10(1):163–172
Andrew J, Gunne R, Jan A (2005) The global burden of diabetic foot disease. Lancet 366(9498):1719–1724
Schaper NC, Apelqvist J, Bakker K (2003) The international consensus and practical guidelines on the management and prevention of the diabetic foot. Curr Diabetes Rep 3(6):475–479
Zimmet PZ, Magliano DJ, Herman WH et al (2014) Diabetes: a 21st century challenge. Lancet Diabetes Endocrinol 2(1):56–64
Das D, Mahanta LB (2021) A comparative assessment of different approaches of segmentation and classification methods on childhood medulloblastoma images. J Med Biol Eng 41:379–392. https://doi.org/10.1007/s40846-021-00612-4
Muruganantham P, Balakrishnan SM (2022) Attention aware deep learning model for wireless capsule endoscopy lesion classification and localization. J Med Biol Eng 42:157–168. https://doi.org/10.1007/s40846-022-00686-8
Vinicor F (1998) The public health burden of diabetes and the reality of limits. Diabetes Care 21(Suppl 3):C15–C18
Alqudah AM, Qazan S, Masad IS (2021) Artificial intelligence framework for efficient detection and classification of pneumonia using chest radiography images. J Med Biol Eng 41:599–609. https://doi.org/10.1007/s40846-021-00631-1
Goyal M, Reeves ND, Davison AK et al (2020) Dfunet: convolutional neural networks for diabetic foot ulcer classification. IEEE Trans Emerg Top Comput Intell 4(5):728–739. https://doi.org/10.1109/TETCI.2018.2866254
Alzubaidi L, Fadhel MA, Oleiwi SR et al (2020) Dfu_qutnet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimed Tools Appl 79(21):15655–15677. https://doi.org/10.1007/s11042-019-07820-w
Güley O, Pati S, Bakas S (2022) Classification of infection and ischemia in diabetic foot ulcers using vgg architectures. In: Yap MH, Cassidy B, Kendrick C (eds) Diabetic foot ulcers grand challenge, vol 13183. Springer, pp 76–89. https://doi.org/10.1007/978-3-030-94907-5_6
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations
Ag A, Re B, Afha A et al (2021) Diabetic foot ulcer classification using mapped binary patterns and convolutional neural networks. Comput Biol Med 140(105):055. https://doi.org/10.1016/j.compbiomed.2021.105055
Qayyum A, Benzinou A, Mazher M, et al (2022) Efficient multi-model vision transformer based on feature fusion for classification of dfuc2021 challenge. In: Yap MH, Cassidy B, Kendrick C (eds) Diabetic foot ulcers grand challenge, vol 13183. Springer, Cham, pp 62–75. https://doi.org/10.1007/978-3-030-94907-5_5
Dosovitskiy A, Beyer L, Kolesnikov A, et al (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations
Jia D, Wei D, Socher R, et al (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 248–255. https://doi.org/10.1109/CVPR.2009.5206848
Jaderberg M, Vedaldi A, Zisserman A (2014) Speeding up convolutional neural networks with low rank expansions. In: British Machine Vision Conference
Goyal M, Reeves ND, Rajbhandari S et al (2019) Robust methods for real-time diabetic foot ulcer detection and localization on mobile devices. IEEE J Biomed Health Inform 23(4):1730–1741. https://doi.org/10.1109/JBHI.2018.2868656
Goyal M, Reeves ND, Rajbhandari S et al (2020) Recognition of ischaemia and infection in diabetic foot ulcers: dataset and techniques. Comput Biol Med 117(103):616. https://doi.org/10.1016/j.compbiomed.2020.103616
Hassani A, Walton S, Shah N et al (2021) Escaping the big data paradigm with compact transformers. In: CVPR LLID Workshop 2021. https://arxiv.org/pdf/2104.05704.pdf
Yap MH, Cassidy B, Pappachan JM, et al (2021) Analysis towards classification of infection and ischaemia of diabetic foot ulcers. In: 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), pp 1–4. https://doi.org/10.1109/BHI50953.2021.9508563
Cassidy B, Reeves ND, Pappachan JM et al (2021) The dfuc 2020 dataset: analysis towards diabetic foot ulcer detection. Eur Endocrinol 1(1):5
Funding
This work was supported in part by National Natural Science Foundations of China under Grants 62271297, 61672021 and 61872227, and in part by the Major Project of the Science and Technology Ministry in China under Grant 2020YFB0204500.
Author information
Authors and Affiliations
Contributions
LA: supervision, funding acquisition, conceptualization, methodology, participation in writing. MY: software, writing-original draft, visualization, investigation. ZX: formal analysis.
Corresponding author
Ethics declarations
Competing interests
The authors have no relevant financial or non-financial interests to disclose.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ai, L., Yang, M. & Xie, Z. ACTNet: asymmetric convolutional transformer network for diabetic foot ulcers classification. Phys Eng Sci Med 45, 1175–1181 (2022). https://doi.org/10.1007/s13246-022-01185-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-022-01185-5