Hybrid-Structure-Oriented Transformer for Arm Musculoskeletal Ultrasound Segmentation
Authors: 
Lingyu Chen, Yue Wang, Zhe Zhao, Hongen Liao, Daoqiang Zhang, Haojie Han, Fang ChenAuthors Info & Claims
Pages 621 - 631
Abstract
Segmenting complex layer structures, including subcutaneous fat, skeletal muscle, and bone in arm musculoskeletal ultrasound (MSKUS), is vital for diagnosing and monitoring the progression of Breast-Cancer-Related Lymphedema (BCRL). Nevertheless, previous researches primarily focus on individual muscle or bone segmentation in MSKUS, overlooking the intricate and hybrid-layer morphology that characterizes these structures. To address this limitation, we propose a novel approach called the hybrid structure-oriented Transformer (HSformer), which effectively captures hierarchical structures with diverse morphology in MSKUS. Specifically, HSformer combines a hierarchical-consistency relative position encoding and a structure-biased constraint for hierarchical structure attention. Our experiments on arm MSKUS datasets demonstrate that HSformer achieves state-of-the-art performance in segmenting subcutaneous fat, skeletal muscle and bone. The code of our implementation is: https://github.com/Swecamellia/HSformer.
References
[1]
Chen, J., et al.: TransuNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)
[2]
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
[3]
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)
[4]
Goudarzi, S., Whyte, J., Boily, M., Towers, A., Kilgour, R.D., Rivaz, H.: Segmentation of arm ultrasound images in breast cancer-related lymphedema: a database and deep learning algorithm. IEEE Trans. Biomed. Eng. (2023)
[5]
Hashemi HS, Fallone S, Boily M, Towers A, Kilgour RD, and Rivaz H Assessment of mechanical properties of tissue in breast cancer-related lymphedema using ultrasound elastography IEEE Trans. Ultrason. Ferroelectr. Freq. Control 2018 66 3 541-550
[6]
Hidding JT et al. Measurement properties of instruments for measuring of lymphedema: systematic review Phys. Ther. 2016 96 12 1965-1981
[7]
Katakis S, Barotsis N, Kakotaritis A, Economou G, Panagiotopoulos E, and Panayiotakis G Automatic extraction of muscle parameters with attention unet in ultrasonography Sensors 2022 22 14 5230
[8]
Katakis S, Barotsis N, Kakotaritis A, Tsiganos P, and Economou G Muscle cross-sectional area segmentation in transverse ultrasound images using vision transformers Diagnostics 2023 13 2 217
[9]
Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)
[10]
Liu H, Wei D, Lu D, Tang X, Wang L, and Zheng Y Simultaneous alignment and surface regression using hybrid 2D–3D networks for 3d coherent layer segmentation of retinal oct images with full and sparse annotations Med. Image Anal. 2024 91
[11]
Liu R et al. NHBS-Net: a feature fusion attention network for ultrasound neonatal hip bone segmentation IEEE Trans. Med. Imaging 2021 40 12 3446-3458
[12]
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
[13]
International Society of Lymphology: The diagnosis and treatment of peripheral lymphedema. Consensus document of the international society of lymphology. Lymphology 36(2), 84–91 (2003)
[14]
Marzola F, van Alfen N, Doorduin J, and Meiburger KM Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment Comput. Biol. Med. 2021 135
[15]
Mishra Z, Ganegoda A, Selicha J, Wang Z, Sadda SR, and Hu Z Automated retinal layer segmentation using graph-based algorithm incorporating deep-learning-derived information Sci. Rep. 2020 10 1 9541
[16]
Rasti, R., Biglari, A., Rezapourian, M., Yang, Z., Farsiu, S.: RetiFluidNet: a self-adaptive and multi-attention deep convolutional network for retinal OCT fluid segmentation. IEEE Trans. Med. Imaging (2022)
[17]
Ronneberger O, Fischer P, and Brox T Navab N, Hornegger J, Wells WM, and Frangi AF U-Net: convolutional networks for biomedical image segmentation Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 2015 Cham Springer 234-241
[18]
Seward C, Skolny M, Brunelle C, Asdourian M, Salama L, and Taghian AG A comprehensive review of bioimpedance spectroscopy as a diagnostic tool for the detection and measurement of breast cancer-related lymphedema J. Surg. Oncol. 2016 114 5 537-542
[19]
Tan, Y., et al.: Retinal layer segmentation in OCT images with boundary regression and feature polarization. IEEE Trans. Med. Imaging (2023)
[20]
Van der Veen P, Vermeiren K, Von Kemp K, Lamote J, Sacre R, and Lievens P A key to understanding postoperative lymphoedema: a study on the evolution and consistency of oedema of the arm using ultrasound imaging Breast 2001 10 3 225-230
[21]
Wan, Q., Huang, Z., Lu, J., Yu, G., Zhang, L.: SeaFormer: squeeze-enhanced axial transformer for mobile semantic segmentation. arXiv preprint arXiv:2301.13156 (2023)
[22]
Yun, I., Shin, C., Lee, H., Lee, H.J., Rhee, C.E.: EGFormer: equirectangular geometry-biased transformer for 360 depth estimation. arXiv preprint arXiv:2304.07803 (2023)
[23]
Zeng B, Chen L, Zheng Y, Kikinis R, Chen X, et al. Greenspan H et al. Fine-grained hand bone segmentation via adaptive multi-dimensional convolutional network and anatomy-constraint loss MICCAI 2023 2023 Cham Springer 395-404
[24]
Zhao, R., et al.: Structure-enhanced attentive learning for spine segmentation from ultrasound volume projection images. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1195–1199. IEEE (2021)
Index Terms
- Hybrid-Structure-Oriented Transformer for Arm Musculoskeletal Ultrasound Segmentation
Index terms have been assigned to the content through auto-classification.
Recommendations
Fisher–Tippett Region-Merging Approach to Transrectal Ultrasound Prostate Lesion Segmentation
In this paper, a computerized approach to segmenting prostate lesions in transrectal ultrasound (TRUS) images is presented. The segmentation of prostate lesions from TRUS images is very challenging due to issues, such as poor contrast, low SNRs, and ...
IFCM Based Segmentation Method for Liver Ultrasound Images
In this paper we have proposed an iterative Fuzzy C-Mean (IFCM) method which divides the pixels present in the image into a set of clusters. This set of clusters is then used to segment a focal liver lesion from a liver ultrasound image. Advantage of ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Oct 2024
822 pages
ISBN:978-3-031-72377-3
DOI:10.1007/978-3-031-72378-0
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 07 October 2024
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Dec 2024