深度学习在主动脉影像自动分割中的研究进展

doi:10.6040/j.issn.1671-7554.0.2024.0317

摘要/Abstract

摘要： 在医学图像处理领域,准确的图像分割对于主动脉疾病的诊断和治疗规划至关重要。深度学习技术,尤其是卷积神经网络近年来在医学图像分割任务中取得了显著的进展。本文基于深度学习模型应用于主动脉病变图像自动化分割的研究进行综述,总结了目前这些技术对于提高分割精度和效率方面的贡献,探讨了现有方法所面临的挑战和未来研究更多的可能性以及方向。

关键词: 深度学习, 主动脉图像分割, 卷积神经网络, 主动脉疾病, 计算机视觉

Abstract: In the field of medical image processing, accurate image segmentation is crucial for the diagnosis and treatment planning of aortic diseases. Deep learning techniques, especially convolutional neural networks, have made significant progress in medical image segmentation tasks in recent years. This article reviewed the research on the application of deep learning models to the automatic segmentation of aortic lesion images, summarized the contributions of these current techniques to improving the segmentation accuracy and efficiency, and discussed the challenges faced by existing methods and more possibilities and directions for future research.

Key words: Deep learning, Aortic image segmentation, Convolutional neural networks, Aortic disease, Computer vision

中图分类号:

R543.1

唐玉宁,潘天岳,董智慧,符伟国. 深度学习在主动脉影像自动分割中的研究进展[J]. 山东大学学报 (医学版), 2024, 62(9): 66-73.

TANG Yuning, PAN Tianyue, DONG Zhihui, FU Weiguo. Research progress of deep learning in automatic segmentation of aortic images[J]. Journal of Shandong University (Health Sciences), 2024, 62(9): 66-73.

参考文献

[1] 《中国心血管健康与疾病报告》编写组. 《中国心血管健康与疾病报告2022》要点解读[J]. 中国心血管杂志, 2023, 28(4): 297-312. Committee of the Report on Cardiovascular Health and Diseases in China. Interpretation of report on cardiovascular health and diseases in China 2022[J]. Chinese Journal of Cardiovascular Medicine, 2023, 28(4): 297-312.
[2] 高新海, 徐仲卿, 张晓明, 等. 主动脉夹层患者临床特征及导致死亡相关危险因素分析[J]. 实用临床医药杂志, 2015, 19(13): 130-131. GAO Xinhai, XU Zhongqing, ZHANG Xiaoming, et al. Analysis of clinical characteristics and related risk factors of death in patients with aortic dissection[J]. Journal of Clinical Medicine in Practice, 2015, 19(13): 130-131.
[3] de Bruijne M, van Ginneken B, Viergever MA, et al. Interactive segmentation of abdominal aortic aneurysms in CTA images[J]. Med Image Anal, 2004, 8(2): 127-138.
[4] Ravì D, Wong C, Deligianni F, et al. Deep learning for health informatics[J]. IEEE J Biomed Health Inform, 2017, 21(1): 4-21.
[5] Shen DG, Wu GR, Suk HI. Deep learning in medical image analysis[J]. Annu Rev Biomed Eng, 2017, 19: 221-248. doi:10.1146/annurev-bioeng-071516-044442.
[6] Slomka PJ, Dey D, Sitek A, et al. Cardiac imaging: working towards fully-automated machine analysis & interpretation[J]. Expert Rev Med Devices, 2017, 14(3): 197-212.
[7] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42: 60-88. doi:10.1016/j.media.2017.07.005.
[8] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[9] Wang R, Zhou YQ, Zhao CY, et al. A hybrid flower pollination algorithm based modified randomized location for multi-threshold medical image segmentation[J]. Biomed Mater Eng, 2015, 26(Suppl 1): S1345-S1351.
[10] Patil DD, Deore SG. Medical image segmentation: a review[J]. International Journal of Computer Science and Mobile Computing, 2013, 2(1): 22-27.
[11] Huang BS, Tian JR, Zhang HY, et al. Deep semantic segmentation feature-based radiomics for the classification tasks in medical image analysis[J]. IEEE J Biomed Health Inform, 2021, 25(7): 2655-2664.
[12] Sevastopolsky A. Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network[J]. Pattern Recognit Image Anal, 2017, 27(3): 618-624.
[13] Yu Z, Jiang XD, Zhou F, et al. Melanoma recognition in dermoscopy images via aggregated deep convolutional features[J]. IEEE Trans Biomed Eng, 2019, 66(4): 1006-1016.
[14] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[C] //IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE, 2017: 640-651. doi:10.1109/TPAMI.2016.2572683.
[15] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C] //Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany. Springer International Publishing, 2015: 234-241.
[16] Yu QH, Xie LX, Wang Y, et al. Recurrent saliency transformation network: incorporating multi-stage visual cues for small organ segmentation[C] //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 8280-8289. doi:10.1109/CVPR.2018.00864.
[17] Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12): 2481-2495.
[18] Huang HM, Lin LF, Tong RF, et al. UNet 3: a full-scale connected UNet for medical image segmentation[C] //ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). Barcelona, Spain. IEEE, 2020: 1055-1059. doi:10.1109/ICASSP40776.2020.9053405.
[19] Milletari F, Navab N, Ahmadi SA. V-net: fully convolutional neural networks for volumetric medical image segmentation[C] //2016 Fourth International Conference on 3D Vision(3DV). Stanford, CA, USA. IEEE, 2016: 565-571. doi:10.1109/3DV.2016.79.
[20] Fu J, Liu J, Tian HJ, et al. Dual attention network for scene segmentation[C] //2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach, CA, USA. IEEE, 2019: 3141-3149. doi:10.1109/CVPR.2019.00326.
[21] Alom MZ, Hasan M, Yakopcic C, et al. Recurrent residual convolutional neural network based on U-Net(R2U-Net)for medical image segmentation[EB/OL]. 2018: arXiv: 1802.06955.(2018-05-29)[2024-03-20]. http://arxiv.org/abs/1802.06955.
[22] Ibtehaz N, Rahman MS. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Netw, 2020, 121: 74-87. doi:10.1016/j.neunet.2019.08.025.
[23] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[EB/OL]. 2017: arXiv: 1706.03762.(2023-08-02)[2024-03-20]. http://arxiv.org/abs/1706.03762.
[24] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale[EB/OL]. 2020: arXiv: 2010.11929.(2021-06-03)[2024-03-20]. http://arxiv.org/abs/2010.11929.
[25] Zheng SX, Lu JC, Zhao HS, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C] //2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Nashville, TN, USA. IEEE, 2021: 6877-6886. doi:10.1109/CVPR46437.2021.00681.
[26] Chen JN, Lu YY, Yu QH, et al. TransUNet: transformers make strong encoders for medical image segmentation[EB/OL]. 2021: arXiv: 2102.04306.(2021-02-08)[2024-03-20]. http://arxiv.org/abs/2102.04306.
[27] Tang H, Chen YB, Wang T, et al. HTC-Net: a hybrid CNN-transformer framework for medical image segmentation[J]. Biomed Signal Process Contr, 2024, 88: 105605. doi:10.1016/j.bspc.2023.105605.
[28] 苏炎洲. 基于深度学习的结直肠息肉图像分割方法研究[D]. 成都: 电子科技大学, 2023.
[29] Yao Z, Xie W, Zhang J, et al. Imagetbad: A 3D computed tomography angiography image dataset for automatic segmentation of type-b aortic dissection[J]. Front Physiol, 2021, 12: 732711. doi: 10.3389/fphys.2021.732711.
[30] Gharleghi R, Adikari D, Ellenberger K, et al. Annotated computed tomography coronary angiogram images and associated data of normal and diseased arteries[J]. Sci Data, 2023, 10(1): 128.
[31] Su Z, Jia Y, Liao W, et al. 3D attention U-Net with pretraining: a solution to CADA-aneurysm segmentation challenge[C] // Hennemuth A, Goubergrits L, Ivantsits M, et al. Cerebral aneurysm detection and analysis. AG, Switzerland: Springer, 2021: 58-67.
[32] Ji Y, Bai H, Ge C, et al. AMOS: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation[C] // 36th Conference on Neural Information Processing Systems(NeurIPS 2022). Advances in Neural Information Processing Systems 35. New Orleans, USA: Curran Associates, Inc., 2022: 36722-36732.
[33] Cao L, Shi RQ, Ge YY, et al. Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning[J]. Eur J Radiol, 2019, 121: 108713. doi:10.1016/j.ejrad.2019.108713.
[34] Cheng JL, Tian SW, Yu L, et al. A deep learning algorithm using contrast-enhanced computed tomography(CT)images for segmentation and rapid automatic detection of aortic dissection[J]. Biomed Signal Process Contr, 2020, 62: 102145. doi:10.1016/j.bspc.2020.102145.
[35] Hahn LD, Mistelbauer G, Higashigaito K, et al. CT-based true- and false-lumen segmentation in type B aortic dissection using machine learning[J]. Radiol Cardiothorac Imaging, 2020, 2(3): e190179. doi:10.1148/ryct.2020190179.
[36] Jung JH, Oh HM, Jeong GJ, et al. ZOZI-Seg: a transformer and UNet cascade network with Zoom-Out and Zoom-In scheme for aortic dissection segmentation in enhanced CT images[J]. Comput Biol Med, 2024, 175: 108494. doi:10.1016/j.compbiomed.2024.108494.
[37] Kumar Y, Hooda K, Li S, et al. Abdominal aortic aneurysm: pictorial review of common appearances and complications[J]. Ann Transl Med, 2017, 5(12): 256.
[38] Duquette AA, Jodoin PM, Bouchot O, et al. 3D segmentation of abdominal aorta from CT-scan and MR images[J]. Comput Med Imaging Graph, 2012, 36(4): 294-303.
[39] Siriapisith T, Kusakunniran W, Haddawy P. Outer wall segmentation of abdominal aortic aneurysm by variable neighborhood search through intensity and gradient spaces[J]. J Digit Imaging, 2018, 31(4): 490-504.
[40] Siriapisith T, Kusakunniran W, Haddawy P. 3D segmentation of exterior wall surface of abdominal aortic aneurysm from CT images using variable neighborhood search[J]. Comput Biol Med, 2019, 107: 73-85. doi:10.1016/j.compbiomed.2019.01.027.
[41] López-Linares K, Aranjuelo N, Kabongo L, et al. Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks[J]. Med Image Anal, 2018, 46: 202-214. doi:10.1016/j.media.2018.03.010.
[42] Zohios C, Kossioris G, Papaharilaou Y. Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation[J]. Comput Methods Programs Biomed, 2012, 107(2): 202-217.
[43] Drapikowski P, Domagaa Z. Semi-automatic segmentation of ct/MRI images based on active contour method for 3D reconstruction of abdominal aortic aneurysms[J]. Image Process Commun, 2014, 19(1): 13-19.
[44] Hwang B, Kim J, Lee S, et al. Automatic detection and segmentation of thrombi in abdominal aortic aneurysms using a mask region-based convolutional neural network with optimized loss functions[J]. Sensors, 2022, 22(10): 3643.
[45] Brutti F, Fantazzini A, Finotello A, et al. Deep learning to automatically segment and analyze abdominal aortic aneurysm from computed tomography angiography[J]. Cardiovasc Eng Technol, 2022, 13(4): 535-547.
[46] Abdolmanafi A, Forneris A, Moore RD, et al. Deep-learning method for fully automatic segmentation of the abdominal aortic aneurysm from computed tomography imaging[J]. Front Cardiovasc Med, 2022, 9: 1040053. doi:10.3389/fcvm.2022.1040053.
[47] Kim T, On S, Gwon JG, et al. Computed tomography-based automated measurement of abdominal aortic aneurysm using semantic segmentation with active learning[J]. Sci Rep, 2024, 14(1): 8924.
[48] Rouhollahi A, Willi JN, Haltmeier S, et al. CardioVision: a fully automated deep learning package for medical image segmentation and reconstruction generating digital twins for patients with aortic stenosis[J]. Comput Med Imaging Graph, 2023, 109: 102289. doi:10.1016/j.compmedimag.2023.102289.
[49] Ramirez P, Uus A, van Poppel MPM, et al. Multi-task learning for joint weakly-supervised segmentation and aortic arch anomaly classification in fetal cardiac MRI[J]. Melba, 2023, 2(PIPPI 2022): 406-446. doi:10.59275/j.melba.2023-b7bc.
[50] Imran M, Krebs JR, Gopu VRR, et al. CIS-UNet: multi-class segmentation of the aorta in computed tomography angiography via context-aware shifted window self-attention[EB/OL]. 2024: arXiv: 2401.13049.(2024-01-23)[2024-03-20]. http://arxiv.org/abs/2401.13049.
[51] Manokaran J, Garcia Flores J, Ukwatta E. Fully automated aortic segmentation of 3D phase-contrast magnetic resonance angiography images using deep learning techniques[C] //Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging. February 19-24, 2023. San Diego, USA. SPIE, 2023. doi:10.1117/12.2653344.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed