Interspinous motion (ISM) is a representative method for evaluating the functional fusion status following anterior cervical discectomy and fusion (ACDF) surgery, but the associated measuring difficulty and potential errors in the clinical setting remain concerns. The aim of this study was to investigate the feasibility of a deep learning–based segmentation model for measuring ISM in patients who underwent ACDF surgery.
This study is a retrospective analysis of flexion-extension dynamic cervical radiographs from a single institution and a validation of a convolutional neural network (CNN)–based artificial intelligence (AI) algorithm for measuring ISM. Data from 150 lateral cervical radiographs from the normal adult population were used to train the AI algorithm. A total of 106 pairs of dynamic flexion-extension radiographs from patients who underwent ACDF at a single institution were analyzed and validated for measuring ISM. To evaluate the agreement power between human experts and the AI algorithm, the authors assessed the interrater reliability using the intraclass correlation coefficient and root mean square error (RMSE) and performed a Bland-Altman plot analysis. They processed 106 pairs of radiographs from ACDF patients into the AI algorithm for autosegmenting the spinous process created using 150 normal population radiographs. The algorithm automatically segmented the spinous process and converted it to a binary large object (BLOB) image. The rightmost coordinate value of each spinous process from the BLOB image was extracted, and the pixel distance between the upper and lower spinous process coordinate value was calculated. The AI-measured ISM was calculated by multiplying the pixel distance by the pixel spacing value included in the DICOM tag of each radiograph.
The AI algorithm showed a favorable prediction power for detecting spinous processes with an accuracy of 99.2% in the test set radiographs. The interrater reliability between the human and AI algorithm of ISM was 0.88 (95% CI 0.83–0.91), and its RMSE was 0.68. In the Bland-Altman plot analysis, the 95% limit of interrater differences ranged from 0.11 to 1.36 mm, and a few observations were outside the 95% limit. The mean difference between observers was 0.02 ± 0.68 mm.
This novel CNN-based autosegmentation algorithm for measuring ISM in dynamic cervical radiographs showed strong agreement power to expert human raters and could help clinicians to evaluate segmental motion following ACDF surgery in clinical settings.
INCLUDE WHEN CITING2023年6月9日在线发表;DOI: 10.3171/2023.5.SPINE23293.
DisclosuresDr. Song reported a patent pending for Algorithm for automated measuring ISM.
BohlmanHH,EmerySE,GoodfellowDB,JonesPK.Robinson anterior cervical discectomy and arthrodesis for cervical radiculopathy. Long-term follow-up of one hundred and twenty-two patients.中华骨科杂志.1993;75(9):1298–1307.
ClowardRB.The anterior approach for removal of ruptured cervical disks.J Neurosurg.1958;15(6):602–617.
FraserJF,HärtlR.Anterior approaches to fusion of the cervical spine: a metaanalysis of fusion rates.J Neurosurg Spine.2007;6(4):298–303.
CannadaLK,ScherpingSC,YooJU,JonesPK,EmerySE.Pseudoarthrosis of the cervical spine: a comparison of radiographic diagnostic measures.Spine (Phila Pa 1976).2003;28(1):46–51.
McAnanySJ,BairdEO,OverleySC,KimJS,QureshiSA,AndersonPA.A meta-analysis of the clinical and fusion results following treatment of symptomatic cervical pseudarthrosis.Global Spine J.2015;5(2):148–155.
KaiserMG,HaidRWJr,SubachBR,BarnesB,RodtsGEJr.Anterior cervical plating enhances arthrodesis after discectomy and fusion with cortical allograft.开云体育app官方网站下载入口.2002;50(2):229–238.
LevenD,ChoSK.Pseudarthrosis of the cervical spine: risk factors, diagnosis and management.Asian Spine J.2016;10(4):776–786.
van EckCF,ReganC,DonaldsonWF,KangJD,LeeJY.修订率和相邻segme的发生nt disease after anterior cervical discectomy and fusion: a study of 672 consecutive patients.Spine (Phila Pa 1976).2014;39(26):2143–2147.
WhitecloudTSIII.Anterior surgery for cervical spondylotic myelopathy. Smith-Robinson, Cloward, and vertebrectomy.Spine (Phila Pa 1976).1988;13(7):861–863.
BensonJC,LehmanVT,SebastianAS,et al.Successful fusion versus pseudarthrosis after spinal instrumentation: a comprehensive imaging review.Neuroradiology.2022;64(9):1719–1728.
LinW,HaA,BoddapatiV,YuanW,RiewKD.Diagnosing pseudoarthrosis after anterior cervical discectomy and fusion.Neurospine.2018;15(3):194–205.
CarreonLY,GlassmanSD,DjurasovicM.Reliability and agreement between fine-cut CT scans and plain radiography in the evaluation of posterolateral fusions.Spine J.2007;7(1):39–43.
GhiselliG,WhartonN,HippJA,WongDA,JatanaS.Prospective analysis of imaging prediction of pseudarthrosis after anterior cervical discectomy and fusion: computed tomography versus flexion-extension motion analysis with intraoperative correlation.Spine (Phila Pa 1976).2011;36(6):463–468.
PloumisA,MehbodA,GarveyT,GilbertT,TransfeldtE,WoodK.Prospective assessment of cervical fusion status: plain radiographs versus CT-scan.Acta Orthop Belg.2006;72(3):342–346.
GoldsteinC,DrewB.When is a spine fused?Injury.2011;42(3):306–313.
PhillipsFM,CarlsonG,EmerySE,BohlmanHH.Anterior cervical pseudarthrosis. Natural history and treatment.Spine (Phila Pa 1976).1997;22(14):1585–1589.
RaizmanNM,O’BrienJR,Poehling-MonaghanKL,YuWD.Pseudarthrosis of the spine.J Am Acad Orthop Surg.2009;17(8):494–503.
KaiserMG,MummaneniPV,MatzPG,et al.Radiographic assessment of cervical subaxial fusion.J Neurosurg Spine.2009;11(2):221–227.
SongKS,PiyaskulkaewC,ChuntarapasT,et al.Dynamic radiographic criteria for detecting pseudarthrosis following anterior cervical arthrodesis.中华骨科杂志.2014;96(7):557–563.
OshinaM,OshimaY,TanakaS,RiewKD.Radiological fusion criteria of postoperative anterior cervical discectomy and fusion: a systematic review.Global Spine J.2018;8(7):739–750.
RiewKD,YangJJ,ChangDG,et al.What is the most accurate radiographic criterion to determine anterior cervical fusion?Spine J.2019;19(3):469–475.
GalbuseraF,CasaroliG,BassaniT.Artificial intelligence and machine learning in spine research.JOR Spine.2019;2(1):e1044.
SegevE,HemoY,WientroubS,et al.Intra- and interobserver reliability analysis of digital radiographic measurements for pediatric orthopedic parameters using a novel PACS integrated computer software program.J Child Orthop.2010;4(4):331–341.
WatanabeK,AokiY,MatsumotoM.An application of artificial intelligence to diagnostic imaging of spine disease: estimating spinal alignment from Moiré images.Neurospine.2019;16(4):697–702.
KooTK,LiMY.A guideline of selecting and reporting intraclass correlation coefficients for reliability research.J Chiropr Med.2016;15(2):155–163.
McHughML.Interrater reliability: the kappa statistic.Biochem Med (Zagreb).2012;22(3):276–282.
ChoBH,KajiD,CheungZB,et al.Automated measurement of lumbar lordosis on radiographs using machine learning and computer vision.Global Spine J.2020;10(5):611–618.
GalbuseraF,NiemeyerF,WilkeHJ,et al.Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach.Eur Spine J.2019;28(5):951–960.
GroverP,SiebenwirthJ,CaspariC,et al.Can artificial intelligence support or even replace physicians in measuring sagittal balance? A validation study on preoperative and postoperative full spine images of 170 patients.Eur Spine J.2022;31(8):1943–1951.
OroszLD,BhattFR,JaziniE,et al.Novel artificial intelligence algorithm: an accurate and independent measure of spinopelvic parameters.J Neurosurg Spine.2022;37(6):893–901.
SchwartzJT,ChoBH,TangP,et al.Deep learning automates measurement of spinopelvic parameters on lateral lumbar radiographs.Spine (Phila Pa 1976).2021;46(12):E671–E678.
WengCH,WangCL,HuangYJ,et al.Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework.J Clin Med.2019;8(11):1826.
ParkS,KimJK,ChangMC,ParkJJ,YangJJ,LeeGW.Assessment of fusion after anterior cervical discectomy and fusion using convolutional neural network algorithm.Spine (Phila Pa 1976).2022;47(23):1645–1650.
All Time | Past Year | Past 30 Days | |
---|---|---|---|
Abstract Views | 286 | 286 | 75 |
Full Text Views | 49 | 49 | 4 |
PDF Downloads | 40 | 40 | 5 |
EPUB Downloads | 0 | 0 | 0 |