Skip to main content
SpringerLink
Log in

Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. J. C. Baker, J. L. Demertzis, N. G. Rhodes, D. E. Wessell and D. A. Rubin, "Diabetic musculoskeletal complications and their imaging mimics," Radiographics, vol. 32, no. 7, pp. 1959-74, 2012.

    Article  PubMed  Google Scholar 

  2. P. D. Brash, J. Foster, W. Vennart, P. Anthony, J. E. Tooke, "Magnetic resonance imaging techniques demonstrate soft tissue damage in the diabetic foot," Diabetic Medicine, 16(1), 55-61, 1999.

    Article  CAS  PubMed  Google Scholar 

  3. F. B. Ergen, S. E. Sanverdi and A. Oznur, "Charcot foot in diabetes and an update on imaging," Diabet Foot Ankle, vol. 20, no. 4, pp. 124-127, 2013.

    Google Scholar 

  4. L. C. Rogers and N. J. Bevilacqua, "Imaging of the Charcot foot," Clinics in Podiatric Medicine and Surgery, vol. 25, p. 263–74, 2008.

    Article  PubMed  Google Scholar 

  5. T. Martín Noguerol, A. Luna Alcalá, L. S. Beltrán, M. Gómez Cabrera, J. Broncano Cabrero and J. C. Vilanova, "Advanced MR Imaging Techniques for Differentiation of Neuropathic Arthropathy and Osteomyelitis in the Diabetic Foot," Radiographics, vol. 37, no. 4, pp. 1161–1180, 2017.

  6. S. Iqbal, A. N. Qureshi, J. Li and T. Mahmood, "On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks," Archives of Computational Methods in Engineering, 2023.

  7. A. Han, Y. Zhang, A. Li, C. Li, F. Zhao, Q. Dong, Y. Liu, X. Shen, S. Yan, S. Zhou, "Deep Learning Methods for Real-time Detection and Analysis of Wagner Ulcer Classification System," 2022 International Conference on Computer Applications Technology (CCAT) IEEE, pp. 11–21, 2022.

  8. K. Bousabarah, M. Ruge, J. S. Brand, M. Hoevels, D. Rueß, J. Borggrefe, N. G. Hokamp, V. Visser-Vandewalle, D. Maintz, H. Treuer and M. Kocher, "Deep convolutional neural networks for automated segmentation of brain metastases trained on clinical data," Radiation Oncology, 2020.

  9. M. Goyal, N. Reeves, A. Davison, S. Rajbhandari, J. Spragg and M. Yap, "Dfunet: Convolutional neural networks for diabetic foot ulcer classification," arXiv, 2017.

  10. I. Cruz-Vega, D. Hernandez-Contreras, H. Peregrina-Barreto, J. Rangel-Magdaleno and J. Ramirez-Cortes, "Deep learning classification for diabetic foot thermograms," Sensors, 2020.

  11. K. Munadi, K. Saddami, M. Oktiana, R. Roslidar, K. Muchtar, M. Melinda, R. Muharar, M. Syukri, T. Abidin and F. Arnia, "A Deep Learning Method for Early Detection of Diabetic Foot Using Decision Fusion and Thermal Images," Applied Sciences, 2022.

  12. A. I. G. Diez, D. Fuster, L. Morata, F. Torres, R. Garcia, D. Poggio, S. Sotes, M. Del Amo, J. Isern-Kebschull, J. Pomes, A. Soriano, L. Brugnara and X. Tomas, "Comparison of the diagnostic accuracy of diffusion-weighted and dynamic contrast-enhanced MRI with 18F-FDG PET/CT to differentiate osteomyelitis from Charcot neuro-osteoarthropathy in diabetic foot," European Journal of Radiology, 2020.

  13. M. Goyal, N. D. Reeves, S. Rajbhandari, N. Ahmad, C. Wang and M. H. Yap, "Recognition of ischaemia and infection in diabetic foot ulcers: Dataset and techniques," Computers in Biology and Medicine, vol. 117, 2020.

  14. M. H. Yap, R. Hachiuma, A. Alavi, C. R. B. Brüngel, M. Goyal, H. Zhu, J. Rückert, M. Olshansky, X. Huang, H. Saito, S. Hassanpour, C. M. Friedrich, D. B. Ascher, A. Song, H. Kajita and D. Gill, "Deep learning in diabetic foot ulcers detection: A comprehensive evaluation," Computers in Biology and Medicine, vol. 135, 2021.

  15. B. Cassidy, N. D. Reeves, J. M. Pappachan, D. Gillespie, C. O'Shea, S. Rajbhandari, A. G. Maiya, E. Frank, A. J. Boulton, D. G. Armstrong, B. Najafi, J. Wu, R. S. Kochhar and M. H. Yap, "The DFUC 2020 Dataset: Analysis Towards Diabetic Foot Ulcer Detection," TouchREVIEWS in endocrinology, vol. 17, no. 1, pp. 5-11, 2021.

    Article  PubMed  PubMed Central  Google Scholar 

  16. M. Goyal and S. Hassanpour, "A Refined Deep Learning Architecture for Diabetic Foot Ulcers Detection," Computer Science, 2020.

  17. A. Hernandez-Guedes, I. Santana-Perez, N. Arteaga-Marrero, H. Fabelo, G. M. Callico and J. Ruiz-Alzola, "Performance Evaluation of Deep Learning Models for Image Classification Over Small Datasets: Diabetic Foot Case Study," IEEE Access, vol. 10, pp. 124373-124386, 2022.

    Article  Google Scholar 

  18. S. Muralidhara, A. Lucieri, A. Dengel and S. Ahmed, "Holistic multi-class classifcation & grading of diabetic foot ulcerations from plantar thermal images using deep learning," Health Information Science and Systems, vol. 10, no. 21, 2022.

  19. M. Ahsan, S. Naz, R. Ahmad, H. Ehsan and A. Sikandar, "A Deep Learning Approach for Diabetic Foot Ulcer Classification and Recognition," Information, vol. 14, no. 1, p. 36, 2023.

    Article  Google Scholar 

  20. L. Alzubaidi, M. A. Fadhel, S. R. Oleiwi, O. Al-Shamma and J. Zhang, "DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network," Multimedia Tools and Applications, vol. 79, pp. 15655-15677, 2019.

    Article  Google Scholar 

  21. P. N. Thotad, G. R. Bharamagoudar and B. S. Anami, "Diabetic foot ulcer detection using deep learning approaches," Sensors International, vol. 4, 2023.

  22. A. Anaya-Isaza and M. Zequera-Diaz, "Detection of Diabetes Mellitus With Deep Learning and Data Augmentation Techniques on Foot Thermography," IEEE Access, vol. 10, pp. 59564-59591, 2022.

    Article  Google Scholar 

  23. T. K. Chuah, E. Van Reeth, K. Sheah, C. L. Poh, "Texture analysis of bone marrow in knee MRI for classification of subjects with bone marrow lesion—data from the Osteoarthritis Initiative," Magnetic Resonance Imaging, 31(6), 930-938, 2013.

    Article  PubMed  Google Scholar 

  24. J. Li, S. Fu, Z. Gong, Z. Zhu, D. Zeng, P. Cao, T. Lin, T. Chen, X. Wang, R. Lartey, C. K. Kwoh, A. Guermazi, F. W. Roemer, D. J. Hunter, J. Ma, C. Ding, "MRI-based texture analysis of infrapatellar fat pad to predict knee osteoarthritis incidence, " Radiology, 304(3), 611-621, 2022.

    Article  PubMed  Google Scholar 

  25. S. Kostopoulos, N. Boci, D. Cavouras, A. Tsagkalis, M. Papaioannou, A. Tsikrika, D. Glotsos, P. Asvestas, E. Lavdas, "Radiomics Texture Analysis of Bone Marrow Alterations in MRI Knee Examinations," Journal of Imaging, 9(11), 252, 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  26. F. Cuce, G. Tulum, K. B. Yilmaz, O. Osman and A. Aralasmak, "Radiomics method in the differential diagnosis of diabetic foot osteomyelitis and charcot neuroarthropathy," The British Journal of Radiology, 2023.

  27. K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.

  28. M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," International Conference on Machine Learning, 2019.

  29. G. Tulum, "GitHub," [Online]. Available: https://github.com/DrGokalpTulum/deep_learning_classification_CNO_OM_TR/tree/main. [Accessed 16 8 2023].

  30. B. A. Lipsky, É. Senneville, Z. G. Abbas, J. Aragón-Sánchez, M. Diggle, J. M. Embil, S. Kono, L. A. Lavery, M. Malone, S. A. Van Asten, V. Urbančič-Rovan, E. J. G. Peters, "Guidelines on the diagnosis and treatment of foot infection in persons with diabetes (IWGDF 2019 update)," Diabetes/metabolism research and reviews, 2020.

  31. K. T. Low, W. C. Peh, "Magnetic resonance imaging of diabetic foot complications, " Singapore medical journal, 56(1), 23, 2015.

  32. H. P. Ledermann, W. B. Morrison and M. E. Schweitzer, "MR image analysis of pedal osteomyelitis: distribution, patterns of spread, and frequency of associated ulceration and septic arthritis," Radiology, vol. 223, no. 3, pp. 747-755, 2002.

    Article  PubMed  Google Scholar 

  33. C. Yang and A. Tandon, "A Pictorial Review of Diabetic foot Manifestations," The Medical journal of Malaysia, vol. 68, no. 3, p. 279–289, 2013.

    CAS  PubMed  Google Scholar 

  34. R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2013.

  35. R. Girshick, "Fast R-CNN," 2015 IEEE International Conference on Computer Vision, pp. 1440–1448, 2015.

  36. J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified, real-time object detection," 2016 IEEE conference on computer vision and pattern recognition, pp. 779–788, 2016.

  37. R. Sujatha, S. L. Aarthy and R. R. Vettriselvan, "Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics," CRC Press, 2021.

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Faculty of Engineering and Natural Sciences, Bandirma Onyedi Eylul University, Balikesir, Turkey

    Maide Cakir

  2. Department of Electrical and Electronics Engineering, Istanbul Topkapi University, Engineering Faculty, Istanbul, Turkey

    Gökalp Tulum

  3. Department of Radiology, Health Science University, Gulhane Training, and Research Hospital, Ankara, Turkey

    Ferhat Cuce

  4. Department of General Surgery, Health Science University, Gulhane Training and Research, Ankara, Turkey

    Kerim Bora Yilmaz

  5. Department of Radiology, Liv Hospital Vadi, Istanbul, Turkey

    Ayse Aralasmak

  6. Department of Radiology, Health Sciences University, Gulhane Training and Research Hospital, Ankara, Turkey

    Muhammet İkbal Isik

  7. Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Ankara Yildirim Beyazit University, Ankara, Turkey

    Hüseyin Canbolat

Authors
  1. Maide Cakir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gökalp Tulum
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ferhat Cuce
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kerim Bora Yilmaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ayse Aralasmak
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Muhammet İkbal Isik
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hüseyin Canbolat
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conception and design, or acquisition of data, or analysis and interpretation of data: MC, GT, HC. Drafting the article or revising it critically for important intellectual content: All authors. Final approval of the version to be published: FC, KBY, AA, MII. Agree to be accountable for all aspects of the work if questions arise related to its accuracy or integrity: FC, KBY, AA, MII.

Corresponding author

Correspondence to Maide Cakir.

Ethics declarations

Conflict of Interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 8114 KB)

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cakir, M., Tulum, G., Cuce, F. et al. Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods. J Digit Imaging. Inform. med. (2024). https://doi.org/10.1007/s10278-024-01067-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10278-024-01067-0

Keywords

Search

Navigation