Abstract
For the Diabetic Foot Ulcer Challenge 2022 (DFUC2022) hosted by MICCAI 2022, we built a machine learning model based on the architecture of TransFuse [20] to accomplish the segmentation task. The TransFuse model combines Transformers and convolutional neural networks (CNNs), taking advantage of both local and global features. In this paper, we propose a modification to the data flow in encoder necks for decoding features in the higher resolution level, and in fusion modules for more efficient attention. Furthermore, to minimize the information loss as a result of resizing, we propose new techniques in both training and testing algorithms. Firstly, a region proposal network (RPN) is introduced from object detection methods and is used at the image pre-processing phase. It crops fixed size images from origin images, so that the high resolution input can be fed into TransFuse. We also applied test-time augmentation following a similar concept to RPN. We crop fixed size images at each corner and use edge pooling to ensemble them properly.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cassidy, B., et al.: DFUC 2020: Analysis Towards Diabetic Foot Ulcers Detection (2020). arXiv:2004.11853
Chao, P., Kao, C.Y., Ruan, Y.S., Huang, C.H., Lin, Y.L.: Hardnet: a low memory traffic network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3552–3561 (2019)
Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124–12134 (2022)
Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929
Fan, D.-P., et al.: PraNet: parallel reverse attention network for polyp segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 263–273. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59725-2_26
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
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. Topics Comput. Intell. 4(5), 728–739 (2018)
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 Inf. 23(4), 1730–1741 (2018)
Goyal, M., Reeves, N., 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 (2019)
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)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Kendrick, C., et al.: Translating Clinical Delineation of Diabetic Foot Ulcers into Machine Interpretable Segmentation (2022). arXiv:2204.11618
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)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, pp. 10347–10357. PMLR (2021)
Yap, M.H. et al.: 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. IEEE (2021)
Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using convolutional neural networks with test-time augmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 61–72. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11726-9_6
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision, (ECCV), pp. 3–19 (2018)
Zhang, Y., Liu, H., Hu, Q.: TransFuse: fusing transformers and CNNs for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 14–24. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_2
Acknowledgments
Supported by TWCC, and MOST.
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 Switzerland AG
About this paper
Cite this paper
Chen, YH., Ju, YJ., Huang, JD. (2023). Capture the Devil in the Details via Partition-then-Ensemble on Higher Resolution Images. In: Yap, M.H., Kendrick, C., Cassidy, B. (eds) Diabetic Foot Ulcers Grand Challenge. DFUC 2022. Lecture Notes in Computer Science, vol 13797. Springer, Cham. https://doi.org/10.1007/978-3-031-26354-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-26354-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26353-8
Online ISBN: 978-3-031-26354-5
eBook Packages: Computer ScienceComputer Science (R0)
