|
|
基于MCTUnet的双模态超声图像的颈动脉斑块分割
|
Abstract:
超声检查(US)和对比增强超声(CEUS)是分析病变的空间和时间特征，以及诊断或预测疾病的重要成像工具。然而，超声图像通常存在边界模糊和噪声干扰强等特点，因此，逐帧评估斑块并描绘病变是一项繁琐且耗时的任务，这对利用深度学习技术分析超声视频提出了挑战。尽管如此，现有的超声和对比增强超声图像分割方法中，能够有效融合这两种不同类型图像的特征信息的仍较为稀缺，且这些方法在全局上下文信息的提取能力上需优化。为此，本文提出了一种基于改进Transformer的混合卷积自注意力(MCT)U形结构双分支网络模型，并在跳跃连接处引入卷积注意力模块。MCT的设计旨在结合卷积和自注意力的优势，不仅增强了全局上下文信息的捕捉能力，同时也保留了卷积方法的良好归纳偏置。实验结果表明，所设计的网络在颈动脉数据集上的表现优于临床医生的诊断结果。
Ultrasound (US) and contrast-enhanced ultrasound (CEUS) are essential imaging tools for analyzing the spatial and temporal characteristics of lesions, as well as for diagnosing or predicting diseases. However, ultrasound images are often characterized by blurred boundaries and significant noise interference, making the task of frame-by-frame plaque assessment and lesion depiction labor-intensive and time-consuming. This presents a challenge for using deep learning techniques to analyze ultrasound videos. Despite advancements, there are still few segmentation methods capable of effectively integrating feature information from both types of images, and existing approaches require further optimization in their ability to capture global contextual information. To address this, we propose a U-shaped dual-branch network model based on a hybrid Convolutional Self-Attention (MCT) framework with an improved Transformer, incorporating convolutional attention modules in the skip connections. The MCT framework is designed to leverage the strengths of both convolution and self-attention, enhancing the ability to capture global contextual information while retaining the beneficial inductive biases of convolution. Experimental results demonstrate that our designed network outperforms clinical experts on the carotid artery dataset.
| [1] | Naghavi, M., Libby, P., Falk, E., Casscells, S.W., Litovsky, S., Rumberger, J., et al. (2003) From Vulnerable Plaque to Vulnerable Patient: A Call for New Definitions and Risk Assessment Strategies: Part I. Circulation, 108, 1664-1672. https://doi.org/10.1161/01.cir.0000087480.94275.97 |
| [2] | Benjamin, E.J., Muntner, P., Alonso, A., et al. (2019) Heart Disease and Stroke Statistics-2019 Update: A Report from the American Heart Association. Circulation, 139, e56-e528. |
| [3] | He, K., Lian, C., Zhang, B., Zhang, X., Cao, X., Nie, D., et al. (2021) HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation in CT Images. IEEE Transactions on Medical Imaging, 40, 2118-2128. https://doi.org/10.1109/tmi.2021.3072956 |
| [4] | European Carotid Plaque Study Group (1995) Carotid Artery Plaque Composition-Relationship to Clinical Presentation and Ultra-Sound B-Mode Imaging. European Journal of Vascular and Endovascular Surgery, 10, 23-30. |
| [5] | Lee, W. (2013) General Principles of Carotid Doppler Ultrasonography. Ultrasonography, 33, 11-17. https://doi.org/10.14366/usg.13018 |
| [6] | ten Kate, G.L., van Dijk, A.C., van den Oord, S.C.H., Hussain, B., Verhagen, H.J.M., Sijbrands, E.J.G., et al. (2013) Usefulness of Contrast-Enhanced Ultrasound for Detection of Carotid Plaque Ulceration in Patients with Symptomatic Carotid Atherosclerosis. The American Journal of Cardiology, 112, 292-298. https://doi.org/10.1016/j.amjcard.2013.03.028 |
| [7] | Feinstein, S.B. (2004) The Powerful Microbubble: From Bench to Bedside, from Intravascular Indicator to Therapeutic Delivery System, and Beyond. American Journal of Physiology-Heart and Circulatory Physiology, 287, H450-H457. https://doi.org/10.1152/ajpheart.00134.2004 |
| [8] | ten Kate, G.L., Renaud, G.G.J., Akkus, Z., van den Oord, S.C.H., ten Cate, F.J., Shamdasani, V., et al. (2012) Far-Wall Pseudoenhancement during Contrast-Enhanced Ultrasound of the Carotid Arteries: Clinical Description and in Vitro Reproduction. Ultrasound in Medicine & Biology, 38, 593-600. https://doi.org/10.1016/j.ultrasmedbio.2011.12.019 |
| [9] | Loizou, C.P., Pattichis, C.S., Pantziaris, M. and Nicolaides, A. (2007) An Integrated System for the Segmentation of Atherosclerotic Carotid Plaque. IEEE Transactions on Information Technology in Biomedicine, 11, 661-667. https://doi.org/10.1109/titb.2006.890019 |
| [10] | Loizou, C.P., Petroudi, S., Pattichis, C.S., Pantziaris, M., Kasparis, T. and Nicolaides, A. (2012) Segmentation of Atherosclerotic Carotid Plaque in Ultrasound Video. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, 28 August-1 September 2012, 53-56. https://doi.org/10.1109/embc.2012.6345869 |
| [11] | Chung, Y.E. and Kim, K.W. (2014) Contrast-Enhanced Ultrasonography: Advance and Current Status in Abdominal Imaging. Ultrasonography, 34, 3-18. https://doi.org/10.14366/usg.14034 |
| [12] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, 5-9 October 2015, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [13] | Devlin, J., Chang, M.W., Lee, K., et al. (2018) Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding. |
| [14] | Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al. (2020) An Image Is Worth 16 x 16 Words: Transformers for Image Recognition at Scale. |
| [15] | Chen, C.R., Fan, Q. and Panda, R. (2021) CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 10-17 October 2021, 357-366. https://doi.org/10.1109/iccv48922.2021.00041 |
| [16] | Woo, S., Park, J., Lee, J. and Kweon, I.S. (2018) CBAM: Convolutional Block Attention Module. Computer Vision—ECCV 2018 15th European Conference, Munich, 8-14 September 2018, 3-19. https://doi.org/10.1007/978-3-030-01234-2_1 |
| [17] | Semih Kayhan, O. and van Gemert, J.C. (2020) On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 14262-14273. https://doi.org/10.1109/cvpr42600.2020.01428 |
| [18] | Chu, X.X., Zhang, B., Tian, Z., Wei, X.L. and Xia, H.X. (2021) Conditional Positional Encodings for Vision Trans-formers. |
| [19] | Lowe, D.G. (1999) Object Recognition from Local Scale-Invariant Features. Proceedings of the 7th IEEE International Conference on Computer Vision, Kerkyra, 20-27 September 1999, 1150-1157. https://doi.org/10.1109/iccv.1999.790410 |
| [20] | Lin, T.-Y., Goyal, P., Girshick, R., He, K.M. and Dollar, P. (2017) Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 318-327. |
| [21] | Chen, J., Lu, Y., Yu, Q., et al. (2021) TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. |
| [22] | Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., et al. (2023) Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation. Computer Vision—ECCV 2022 Workshops, Tel Aviv, 23-27 October 2022, 205-218. https://doi.org/10.1007/978-3-031-25066-8_9 |
| [23] | Yurtkulu, S.C., Şahin, Y.H. and Unal, G. (2019) Semantic Segmentation with Extended DeepLabv3 Architecture. 2019 27th Signal Processing and Communications Applications Conference (SIU), Sivas, 24-26 April 2019, 1-4. https://doi.org/10.1109/siu.2019.8806244 |
| [24] | Guo, M.H., Lu, C.Z., Hou, Q., et al. (2022) SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation. 2022 Conference on Neural Information Processing Systems, New Orleans, 28 November-9 December 2022, 1140-1156. |
| [25] | Zhang, B., Tian, Z., Tang, Q., et al. (2022) SegViT: Semantic Segmentation with Plain Vision Transformers. 2022 Conference on Neural Information Processing Systems, New Orleans, 28 November-9 December 2022, 4971-4982. |
| [26] | Meng, Z., Zhu, Y., Fan, X., Tian, J., Nie, F. and Wang, K. (2022) CEUSegNet: A Cross-Modality Lesion Segmentation Network for Contrast-Enhanced Ultrasound. 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), Kolkata, 28-31 March 2022, 1-5. https://doi.org/10.1109/isbi52829.2022.9761594 |
