Abstract
Diabetic foot ulcer (DFU) is a potentially fatal complication of diabetes. Traditional techniques of DFU analysis and therapy are more time-consuming and costly. Artificial intelligence (AI), particularly deep neural networks, has demonstrated remarkable effectiveness in medical applications. Despite this, the lack of explainability of deep learning models is currently viewed as a key hurdle to using these approaches in actual clinical settings. In this research, we present the DFU_XAI framework for assessing the interpretability of explainable-driven deep learning (DL) models. DFU_XAI evaluates five DL models (Xception, DenseNet121, ResNet50, InceptionV3, and MobileNetV2) to establish a transparent DL framework using three state-of-the-art explanation methods: Shapley additive explanation (SHAP), local interpretable model-agnostic explanations (LIME), and gradient-weighted class activation mapping (Grad-CAM). ResNet50 outperformed the other four models with remarkable results: 98.75% accuracy, 99.2% precision, 97.6% recall, 98.4% F1-score, and 98.5% AUC. For the most part, it can locate diabetic foot ulcers precisely on a diabetic foot and discriminate between diabetic foot ulcers and healthy feet in the DFU dataset. A heat map will indicate the precise location of the ulcer that needs care.
Similar content being viewed by others
Data Availability
The works used publicly available datasets mentioned in reference [19].
References
R. Mostafiz, Diagnosis of diabetes: a machine learning paradigm using optimized features. Netw. Biol. 11(3), 222 (2021)
Diabetes. https://www.who.int/news-room/fact-sheets/detail/diabetes. Accessed 12 May 2023
A.J. Boulton, L. Vileikyte, G. Ragnarson-Tennvall, J. Apelqvist, The global burden of diabetic foot disease. Lancet 366(9498), 1719–1724 (2005)
C. Liu, J.J. van Netten, J.G. Van Baal, S.A. Bus, F. van Der Heijden, Automatic detection of diabetic foot complications with infrared thermography by asymmetric analysis. J. Biomed. Opt. 20(2), 026003 (2015)
D.G. Armstrong, L.A. Lavery, L.B. Harkless, 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)
P. Cavanagh, C. Attinger, Z. Abbas, A. Bal, N. Rojas, Z.-R. Xu, Cost of treating diabetic foot ulcers in five different countries. Diabetes Metab. Res. Rev. 28, 107–111 (2012)
F. Aguiree et al., IDF diabetes atlas, 6th edn., ed. L. Guariguata, T. Nolan, J. Beagley, U. Linnenkamp, O. Jacqmain (International Diabetes Federation, Brussels, 2013)
G. Litjens et al., A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
F.J. Veredas, R.M. Luque-Baena, F.J. Martín-Santos, J.C. Morilla-Herrera, L. Morente, Wound image evaluation with machine learning. Neurocomputing 164, 112–122 (2015)
L. Alzubaidi, M.A. Fadhel, O. Al-Shamma, J. Zhang, J. Santamaría, Y. Duan, Robust application of new deep learning tools: an experimental study in medical imaging. Multimed. Tools Appl. 81(10), 13289–13317 (2022)
B. Najafi, H. Mohseni, G.S. Grewal, T.K. Talal, R.A. Menzies, D.G. Armstrong, An optical-fiber-based smart textile (smart socks) to manage biomechanical risk factors associated with diabetic foot amputation. J. Diabetes Sci. Technol. 11(4), 668–677 (2017)
M. Kaselimi, E. Protopapadakis, A. Doulamis, N. Doulamis, A review of non-invasive sensors and artificial intelligence models for diabetic foot monitoring. Front. Physiol. 13, 924546 (2022)
S.K. Das, P. Roy, A.K. Mishra, DFU_SPNet: a stacked parallel convolution layers based CNN to improve diabetic foot ulcer classification. ICT Express 8(2), 271–275 (2022)
L. Alzubaidi, A.A. Abbood, M.A. Fadhel, O. Al-Shamma, J. Zhang, Comparison of hybrid convolutional neural networks models for diabetic foot ulcer classification. 16 (2021)
L. Alzubaidi, M.A. Fadhel, S.R. Oleiwi, O. Al-Shamma, J. Zhang, DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimed. Tools Appl. 79(21–22), 15655–15677 (2020)
M. Goyal, N.D. Reeves, A.K. Davison, S. Rajbhandari, J. Spragg, M.H. Yap, Dfunet: convolutional neural networks for diabetic foot ulcer classification. IEEE Trans. Emerg. Top. Comput. Intell. 4(5), 728–739 (2018)
L. Wang, P.C. Pedersen, E. Agu, D.M. Strong, B. Tulu, Area determination of diabetic foot ulcer images using a cascaded two-stage SVM-based classification. IEEE Trans. Biomed. Eng. 64(9), 2098–2109 (2017). https://doi.org/10.1109/TBME.2016.2632522
M. Goyal, M.H. Yap, N.D. Reeves, S. Rajbhandari, J. Spragg, Fully convolutional networks for diabetic foot ulcer segmentation, in 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (IEEE, 2017), pp. 618–623
Dataset: diabetic foot ulcer (DFU), Available link: https://www.kaggle.com/laithjj/diabetic-foot-ulcer-dfu
L. Alzubaidi et al., Towards a better understanding of transfer learning for medical imaging: a case study. Appl. Sci. 10(13), 4523 (2020)
N.V. Chawla, K.W. Bowyer, L.O. Hall, W.P. Kegelmeyer, SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res.Artif. Intell. Res. 16, 321–357 (2002)
S.J. Pan, Q. Yang, A survey on transfer learning IEEE transactions on knowledge and data engineering. 22(10), 1345 (2009)
J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, G. Zhang, Transfer learning using computational intelligence: a survey. Knowl.-Based Syst..-Based Syst. 80, 14–23 (2015)
Z. Huang, Z. Pan, B. Lei, Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data. Remote Sens. 9(9), 907 (2017)
G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Honolulu, 2017), pp. 2261–2269
Z. Wu, C. Shen, A. Van Den Hengel, Wider or deeper: revisiting the resnet model for visual recognition. Pattern Recogn.Recogn. 90, 119–133 (2019)
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Las Vegas, NV, 2016) pp. 2818–2826
F. Chollet, Xception: deep learning with depthwise separable convolutions, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Honolulu, HI, 2017) pp. 1800–1807
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, MobileNetV2: inverted residuals and linear bottlenecks, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, Salt Lake City, UT, 2018) pp. 4510–4520
G. Battineni, G.G. Sagaro, N. Chinatalapudi, F. Amenta, Applications of machine learning predictive models in the chronic disease diagnosis. JPM 10(2), 21 (2020)
E.J. Topol, High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25(1), 44–56 (2019)
A.M. Antoniadi et al., Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Appl. Sci. 11(11), 5088 (2021)
M.T. Ribeiro, S. Singh, C. Guestrin, ‘Why should I trust you?’ Explaining the predictions of any classifier, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016), pp. 1135–1144
R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: visual explanations from deep networks via gradient-based localization, in Proceedings of the IEEE International Conference on Computer Vision (2017), pp. 618–626
S.M. Lundberg, S.-I. Lee, A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30 (2017)
N. Ketkar, Deep Learning with Python (Apress, Berkeley, 2017). https://doi.org/10.1007/978-1-4842-2766-4
O. Russakovsky et al., ImageNet large scale visual recognition challenge (2015). Accessed 23 Sep 2023. Preprint at http://arxiv.org/abs/1409.0575
A. Alqahtani, X. Xie, M.W. Jones, Literature review of deep network compression. Informatics 8(4), 77 (2021)
D.P. Kingma, J. Ba, Adam: a method for stochastic optimization (2014). Preprint at http://arxiv.org/abs/1412.6980
M.S. Santos, J.P. Soares, P.H. Abreu, H. Araujo, J. Santos, Cross-validation for imbalanced datasets: avoiding overoptimistic and overfitting approaches [Research Frontier]. IEEE Comput. Intell. Mag.Comput. Intell. Mag. 13(4), 59–76 (2018). https://doi.org/10.1109/MCI.2018.2866730
S. Biswas, R. Mostafiz, B.K. Paul, K.M. Mohi Uddin, M.M. Rahman, F.N.U. Shariful, DFU_MultiNet: a deep neural network approach for detecting diabetic foot ulcers through multi-scale feature fusion using the DFU dataset. Intell.-Based Med. 8, 100128 (2023)
Funding
There is no funding for this research work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
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
Biswas, S., Mostafiz, R., Paul, B.K. et al. DFU_XAI: A Deep Learning-Based Approach to Diabetic Foot Ulcer Detection Using Feature Explainability. Biomedical Materials & Devices (2024). https://doi.org/10.1007/s44174-024-00165-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s44174-024-00165-5