Abstract
Automated image segmentation technology for Diabetic foot ulcer (DFU) management is pivotal in alleviating the healthcare system’s workload, considering the severity of DFU as a complication for diabetics. Due to the constraints of annotation costs and privacy, the scale of the publicly available DFU image segmentation datasets is relatively small, which greatly limits the performance improvement of deep learning models. We explore the potential of synthetic image technology in enhancing the performance of DFU image segmentation. We use the FreestyleNet model to generate high-quality synthetic images and employ an error pixel filtering strategy to handle the discrepancies between the synthetic images and masks. To improve the effectiveness and diversity of the synthetic dataset, we specifically designed a mask difficulty calculation method for DFU synthetic images and proposed two innovative resampling strategies based on it. The efficacy of the novel resampling strategies has been demonstrated through comparative experiments conducted against the average sampling method. Furthermore, integrating synthetic image technology with ensemble learning strategies elevates model performance even higher. Our approach achieved a Dice of 73.72% in the Diabetic Foot Ulcer Challenge 2022 on MICCAI 2022, better than the 72.87% Dice that ranked first in the testing phase, ranking second on the Live Leaderboard (as of July 5, 2024). Our code will be released at https://github.com/xupin262/Synthetic_DFU.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Armstrong, D.G., Boulton, A.J., Bus, S.A.: Diabetic foot ulcers and their recurrence. N. Engl. J. Med. 376(24), 2367–2375 (2017)
Breiman, L.: Bagging predictors. Machine learning 24, 123–140 (1996)
Brüngel, R., Koitka, S., Friedrich, C.M.: Unconditionally generated and pseudo-labeled synthetic images for diabetic foot ulcer segmentation dataset extension. In: Yap, M.H., Kendrick, C., Cassidy, B. (eds.) Diabetic Foot Ulcers Grand Challenge, vol. 13797, pp. 65–79. Springer International Publishing, Cham (2023)
Chae, H.J., Lee, S., Son, H., Han, S., Lim, T.: Generating 3d bio-printable patches using wound segmentation and reconstruction to treat diabetic foot ulcers. In: Computer Vision and Pattern Recognition (CVPR). pp. 2539–2549. IEEE (2022)
Chen, C., Xiong, Z., Tian, X., Zha, Z.J., Wu, F.: Real-world image denoising with deep boosting. IEEE Trans. Pattern Anal. Mach. Intell. 42(12), 3071–3087 (2019)
Edmonds, M., Manu, C., Vas, P.: The current burden of diabetic foot disease. Clinical Orthopaedics and Trauma 17, 88–93 (2021)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: International Conference on Machine Learning (ICML). pp. 148–156. Citeseer, Bari, Italy (1996)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Hassib, M., Ali, M., Mohamed, A., Torki, M., Hussein, M.: Diabetic foot ulcer segmentation using convolutional and transformer-based models. In: Diabetic Foot Ulcers Grand Challenge, vol. 13797, pp. 83–91. Springer, Cham (2023)
Kataoka, H., Hayamizu, R., Yamada, R., Nakashima, K., Takashima, S., Zhang, X., Martinez-Noriega, E.J., Inoue, N., Yokota, R.: Replacing labeled real-image datasets with auto-generated contours. In: Computer Vision and Pattern Recognition (CVPR). pp. 21232–21241. IEEE, New Orleans, Louisiana, USA (2022)
Kendrick, C., Cassidy, B., Pappachan, J.M., O’Shea, C., Fernandez, C.J., Chacko, E., Jacob, K., Reeves, N.D., Yap, M.H.: Translating clinical delineation of diabetic foot ulcers into machine interpretable segmentation. arXiv:2204.11618 (2022)
Kim, H.C., Pang, S., Je, H.M., Kim, D., Bang, S.Y.: Support vector machine ensemble with bagging. In: Pattern Recognition with Support Vector Machines, vol. 2388, pp. 397–408. Springer Berlin Heidelberg, Berlin, Heidelberg (2002)
Kingma, D.P., Welling, M.: Auto-Encoding variational bayes (2022)
Li, J., Chang, H., Yang, J.: Sparse deep stacking network for image classification. In: AAAI Conference on Artificial Intelligence (AAAI). vol. 29. AAAI, Austin, Texas USA (2015)
Li, K., Yin, J., Lu, Z., Kong, X., Zhang, R., Liu, W.: Multiclass boosting svm using different texture features in hep-2 cell staining pattern classification. In: International Conference on Pattern Recognition (ICPR). pp. 170–173. IEEE (2012)
Lo, Z.J., Surendra, N.K., Saxena, A., Car, J.: Clinical and economic burden of diabetic foot ulcers: a 5-year longitudinal multi-ethnic cohort study from the tropics. Int. Wound J. 18(3), 375–386 (2021)
Mohammed, A., Kora, R.: A comprehensive review on ensemble deep learning: Opportunities and challenges. Journal of King Saud University-Computer and Information Sciences 35(2), 757–774 (2023)
Odegua, R.: An empirical study of ensemble techniques (bagging, boosting and stacking). In: Deep Learning IndabaX. pp. 1–10. University of Lagos, Abuja, Nigeria (2019)
Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Computer Vision and Pattern Recognition (CVPR). pp. 2337–2346. IEEE, Long Beach, CA, USA (2019)
Ploderer, B., Clark, D., Brown, R., Harman, J., Lazzarini, P.A., Van Netten, J.J.: Self-monitoring diabetes-related foot ulcers with the myfootcare app: A mixed methods study. Sensors 23(5), 2547 (2023)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: Ground truth from computer games. In: European Conference on Computer Vision (ECCV). pp. 102–118. Springer, Amsterdam, Netherlands (2016)
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T.: Photorealistic text-to-image diffusion models with deep language understanding. In: Neural Information Processing Systems (NeurIPS). pp. 36479–36494. MIT, New Orleans, USA (2022)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)
Smyth, P., Wolpert, D.: Stacked density estimation. In: Neural Information Processing Systems (NeurIPS). pp. 668–674. MIT, Denver, USA (1997)
Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (ICML). pp. 2256–2265. ACM, Lille, France (2015)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR). pp. 1–9. IEEE, Boston, MA, USA (2015)
Tan, Z., Chai, M., Chen, D., Liao, J., Chu, Q., Liu, B., Hua, G., Yu, N.: Diverse semantic image synthesis via probability distribution modeling. In: Computer Vision and Pattern Recognition (CVPR). pp. 7962–7971. IEEE, Virtual (2021)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Neural Information Processing Systems (NeurIPS). pp. 5998–6008. MIT, Long Beach, USA (2017)
Wang, C., Mahbod, A., Ellinger, I., Galdran, A., Gopalakrishnan, S., Niezgoda, J., Yu, Z.: FUSeg: The foot ulcer segmentation challenge (2022)
Xue, H., Huang, Z., Sun, Q., Song, L., Zhang, W.: Freestyle layout-to-image synthesis (2023)
Yang, L., Xu, X., Kang, B., Shi, Y., Zhao, H.: FreeMask: Synthetic images with dense annotations make stronger segmentation models. In: Neural Information Processing Systems (NeurIPS). pp. 1–17. MIT (2023)
Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE/CVF International Conference on Computer Vision (ICCV). pp. 3836–3847. IEEE, Paris, France (2023)
Zhou, Z.H.: Ensemble Methods: Foundations and Algorithms. Chapman and Hall/CRC, Boca Raton, FL (2012)
Acknowledgements
This work was supported in part by the National Key Research and Development Program of China under Grant 2022YFF0606303, the National Natural Science Foundation of China under Grant 62206054, Research Capacity Enhancement Project of Key Construction Discipline in Guangdong Province under Grant 2022ZDJS028, and the Guangdong Basic and Applied Basic Research Foundation (No.2023B1515120058).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, P., Xiao, X., Yuen, W., Li, Y., Li, K., Yin, J. (2025). Synthetic Images with Dense Annotations and Ensemble Learning for DFU Segmentation. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15327. Springer, Cham. https://doi.org/10.1007/978-3-031-78398-2_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-78398-2_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78397-5
Online ISBN: 978-3-031-78398-2
eBook Packages: Computer ScienceComputer Science (R0)