深度学习在脊柱影像及诊疗中的应用进展

吐逊江·帕哈提; 杨来红; 常玉山; 何雄; 郭辉

doi:10.12122/j.issn.1674-4500.2023.03.32

深度学习在脊柱影像及诊疗中的应用进展

doi: 10.12122/j.issn.1674-4500.2023.03.32

新疆医科大学第一附属医院影像中心，新疆乌鲁木齐 830054

基金项目:

省部共建中亚高发病成因与防治国家重点实验室开放课题基金资助项目 SKL-HIDCA-2021-22

详细信息

作者简介:
吐逊江·帕哈提：帕哈提·吐逊江，在读硕士研究生，E-mail: 3414397179@qq.com

通讯作者:
郭辉，硕士，主任医师，E-mail: guohui9804@126.com

计量
- 文章访问数: 316
- HTML全文浏览量: 320
- PDF下载量: 62
- 被引次数: 0
出版历程
- 收稿日期: 2022-11-04
- 网络出版日期: 2023-06-15
- 刊出日期: 2023-05-20

Application progress of deep learning in spinal imaging and diagnosis and treatment

Medical Imaging Center, Affiliated First Hospital of Xinjiang Medical University, Urumqi 830054, China

摘要

摘要: 近年来，我国人口老龄化正加速推进，脊柱疾病的患病风险呈上升趋势。随着人工智能与脊柱医学的交叉融合，以深度学习为代表的人工智能技术逐渐成为脊柱影像及诊疗领域热门研究方法。然而，深度学习在脊柱方面的研究相对较少并仍处于起步阶段，未来具有广阔的发展潜力及进步空间。本文将从深度学习在脊柱图像识别、分割及测量，脊柱疾病的诊断及脊柱手术预后评估3个方面中的应用及研究进展进行归纳综述，助力脊柱影像及脊柱诊疗研究的更深入、更高水平发展。
- 脊柱 /
- 深度学习 /
- 人工智能 /
- 卷积神经网络 /
- 影像
Abstract: In recent years, the aging of our population is accelerating. The risk of spinal diseases is on the rise. With the cross integration of artificial intelligence and spinal medicine, deep learning has gradually become a popular research method in the field of spinal imaging and diagnosis and treatment. However, the research of deep learning in spine is relatively few and still in the initial stage, which has roomily great development potential and progress space in the future. This article reviews the application and research progress of deep learning in spinal image recognition, segmentation and measurement, spinal disease diagnosis and prognosis, and spinal surgery evaluation, to power deeper and higher level development of spine imaging and spine clinical research.
- spine /
- deep learning /
- artificial intelligence /
- convolutional neural network /
- imaging

HTML全文

参考文献(41)

[1]	Bican O, Minagar A, Pruitt AA. The spinal cord: a review of functional neuroanatomy[J]. Neurol Clin, 2013, 31(1): 1-18. doi: 10.1016/j.ncl.2012.09.009
[2]	Bartynski WS. Clinical, anatomic, and imaging correlation in spinerelated pain: the essential elements[J]. Tech Vasc Interv Radiol, 2009, 12(1): 2-10. doi: 10.1053/j.tvir.2009.06.002
[3]	Cui YY, Zhu J, Duan ZL, et al. Artificial intelligence in spinal imaging: current status and future directions[J]. Int J Environ Res Public Health, 2022, 19(18): 11708. doi: 10.3390/ijerph191811708
[4]	Benzakour A, Altsitzioglou P, Lemée JM, et al. Artificial intelligence in spine surgery[J]. Int Orthop, 2023, 47(2): 457-65. doi: 10.1007/s00264-022-05517-8
[5]	Cheng PM, Montagnon E, Yamashita R, et al. Deep learning: an update for radiologists[J]. RadioGraphics, 2021, 41(5): 1427-45. doi: 10.1148/rg.2021200210
[6]	Choi RY, Coyner AS, Kalpathy-Cramer J, et al. Introduction to machine learning, neural networks, and deep learning[J]. Transl Vis Sci Technol, 2020, 9(2): 14
[7]	Kriegeskorte N, Golan T. Neural network models and deep learning [J]. Curr Biol, 2019, 29(7): R231-6. doi: 10.1016/j.cub.2019.02.034
[8]	Currie G, Hawk KE, Rohren E, et al. Machine learning and deep learning in medical imaging: intelligent imaging[J]. J Med Imaging Radiat Sci, 2019, 50(4): 477-87. doi: 10.1016/j.jmir.2019.09.005
[9]	Soffer S, Ben-Cohen A, Shimon O, et al. Convolutional neural networks for radiologic images: a radiologist's guide[J]. Radiology, 2019, 290(3): 590-606. doi: 10.1148/radiol.2018180547
[10]	Al Arif SMMR, Knapp K, Slabaugh G. Fully automatic cervical vertebrae segmentation framework for X- ray images[J]. Comput Methods Programs Biomed, 2018, 157: 95-111. doi: 10.1016/j.cmpb.2018.01.006
[11]	Kónya S, Natarajan TS, Allouch H, et al. Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray[J]. J Craniovertebr Junction Spine, 2021, 12(2): 136- 43. doi: 10.4103/jcvjs.jcvjs_186_20
[12]	Yang HS, Kim KR, Kim S, et al. Deep learning application in spinal implant identification[J]. Spine, 2021, 46(5): E318-24. doi: 10.1097/BRS.0000000000003844
[13]	Alukaev D, Kiselev S, Mustafaev T, et al. A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation[J]. Eur Spine J, 2022, 31(8): 2115-24. doi: 10.1007/s00586-022-07245-4
[14]	Das P, Pal C, Acharyya A, et al. Deep neural network for automated simultaneous intervertebral disc (IVDs) identification and segmentation of multi- modal MR images[J]. Comput Methods Programs Biomed, 2021, 205: 106074. doi: 10.1016/j.cmpb.2021.106074
[15]	Zhang QF, Du Y, Wei ZQ, et al. Spine medical image segmentation based on deep learning[J]. J Healthc Eng, 2021, 2021: 1917946.
[16]	Ouyang HQ, Meng FY, Liu JF, et al. Evaluation of deep learningbased automated detection of primary spine tumors on MRI using the Turing test[J]. Front Oncol, 2022, 12: 814667. doi: 10.3389/fonc.2022.814667
[17]	Liu H, Jiao ML, Yuan Y, et al. Benign and malignant diagnosis of spinal tumors based on deep learning and weighted fusion framework on MRI[J]. Insights Imaging, 2022, 13(1): 87. doi: 10.1186/s13244-022-01227-2
[18]	Bhattacharyya S, Bradshaw MJ. Infections of the spine and spinal cord[J]. Continuum (Minneap Minn), 2021, 27(4): 887-920.
[19]	Babic M, Simpfendorfer CS. Infections of the spine[J]. Infect Dis Clin North Am, 2017, 31(2): 279-97. doi: 10.1016/j.idc.2017.01.003
[20]	Kim K, Kim S, Lee YH, et al. Performance of the deep convolutional neural network based magnetic resonance image scoring algorithm for differentiating between tuberculous and pyogenic spondylitis[J]. Sci Rep, 2018, 8(1): 13124. doi: 10.1038/s41598-018-31486-3
[21]	Li Z, Wu F, Hong F, et al. Computer-Aided Diagnosis of Spinal Tuberculosis From CT Images Based on Deep Learning With Multimodal Feature Fusion[J]. Front Microbiol, 2022, 13: 823324. doi: 10.3389/fmicb.2022.823324
[22]	Mao LT, Xia ZQ, Pan L, et al. Deep learning for screening primary osteopenia and osteoporosis using spine radiographs and patient clinical covariates in a Chinese population[J]. Front Endocrinol (Lausanne), 2022, 13: 971877. doi: 10.3389/fendo.2022.971877
[23]	Chen PJ, Zhou ZN, Yu HX, et al. Computerized-assisted scoliosis diagnosis based on faster R-CNN and ResNet for the classification of spine X-ray images[J]. Comput Math Methods Med, 2022, 2022: 3796202.
[24]	Konieczny MR, Senyurt H, Krauspe R. Epidemiology of adolescent idiopathic scoliosis[J]. J Child Orthop, 2013, 7(1): 3-9. doi: 10.1007/s11832-012-0457-4
[25]	Yang JL, Zhang K, Fan HW, et al. Development and validation of deep learning algorithms for scoliosis screening using back images [J]. Commun Biol, 2019, 2: 390. doi: 10.1038/s42003-019-0635-8
[26]	Chen WJ, Liu X, Li KH, et al. A deep- learning model for identifying fresh vertebral compression fractures on digital radiography[J]. Eur Radiol, 2022, 32(3): 1496-505. doi: 10.1007/s00330-021-08247-4
[27]	Yeh LR, Zhang Y, Chen JH, et al. A deep learning-based method for the diagnosis of vertebral fractures on spine MRI: retrospective training and validation of ResNet[J]. Eur Spine J, 2022, 31(8): 2022-30. doi: 10.1007/s00586-022-07121-1
[28]	Kong SH, Lee JW, Bae BU, et al. Development of a spine X-raybased fracture prediction model using a deep learning algorithm[J]. Endocrinol Metab (Seoul), 2022, 37(4): 674-83. doi: 10.3803/EnM.2022.1461
[29]	Fehlings MG, Tetreault L, Nater A, et al. The aging of the global population: the changing epidemiology of disease and spinal disorders[J]. Neurosurgery, 2015, 77(Suppl 4): S1-S5.
[30]	Parizel PM, Van Hoyweghen AJL, Bali A, et al. The degenerative spine: pattern recognition and guidelines to image interpretation[J]. Handb Clin Neurol, 2016, 136: 787-808.
[31]	Lee GW, Shin H, Chang MC. Deep learning algorithm to evaluate cervical spondylotic myelopathy using lateral cervical spine radiograph[J]. BMC Neurol, 2022, 22(1): 147. doi: 10.1186/s12883-022-02670-w
[32]	Zheng HD, Sun YL, Kong DW, et al. Deep learning- based highaccuracy quantitation for lumbar intervertebral disc degeneration from MRI[J]. Nat Commun, 2022, 13(1): 841. doi: 10.1038/s41467-022-28387-5
[33]	Trinh GM, Shao HC, Hsieh KLC, et al. Detection of lumbar spondylolisthesis from X-ray images using deep learning network [J]. J Clin Med, 2022, 11(18): 5450. doi: 10.3390/jcm11185450
[34]	Hallinan JTPD, Zhu L, Yang KY, et al. Deep learning model for automated detection and classification of central canal, lateral recess, and neural foraminal Stenosis at lumbar spine MRI[J]. Radiology, 2021, 300(1): 130-8. doi: 10.1148/radiol.2021204289
[35]	Lehnen NC, Haase R, Faber J, et al. Detection of degenerative changes on MR images of the lumbar spine with a convolutional neural network: a feasibility study[J]. Diagnostics (Basel), 2021, 11 (5): 902. doi: 10.3390/diagnostics11050902
[36]	Rhee JM, Chapman JR, Norvell DC, et al. Radiological determination of postoperative cervical fusion: a systematic review [J]. Spine, 2015, 40(13): 974-91. doi: 10.1097/BRS.0000000000000940
[37]	Park S, Kim JK, Chang MC, et al. Assessment of fusion after anterior cervical discectomy and fusion using convolutional neural network algorithm[J]. Spine, 2022, 47(23): 1645-50. doi: 10.1097/BRS.0000000000004439
[38]	Mobbs R, Phan K, Malham G, et al. Lumbar interbody fusion: techniques, indications and comparison of interbody fusion options including PLIF, TLIF, MI-TLIF, OLIF/ATP, LLIF and ALIF[J]. J Spine Surg, 2015, 1(1): 2-18.
[39]	Hopkins BS, Yamaguchi JT, Garcia R, et al. Using machine learning to predict 30- day readmissions after posterior lumbar fusion: an NSQIP study involving 23, 264 patients[J]. J Neurosurg Spine, 2019, 29: 1-8.
[40]	Hopkins BS, Mazmudar A, Driscoll C, et al. Using artificial intelligence (AI) to predict postoperative surgical site infection: a retrospective cohort of 4046 posterior spinal fusions[J]. Clin Neurol Neurosurg, 2020, 192: 105718. doi: 10.1016/j.clineuro.2020.105718
[41]	Li JM, Xiang Z, Zhou JQ, et al. Three-dimensional reconstruction of a CT image under deep learning algorithm to evaluate the application of percutaneous kyphoplasty in osteoporotic thoracolumbar compression fractures[J]. Contrast Media Mol Imaging, 2022, 2022: 9107021.