Radiomics based on MRI to predict recurrent L4-5 disc herniation after percutaneous endoscopic lumbar discectomy.
Humans
Intervertebral Disc Displacement
/ surgery
Male
Magnetic Resonance Imaging
/ methods
Diskectomy, Percutaneous
/ methods
Retrospective Studies
Female
Middle Aged
Lumbar Vertebrae
/ diagnostic imaging
Adult
Case-Control Studies
Recurrence
Endoscopy
/ methods
ROC Curve
Propensity Score
Radiomics
Diskectomy
Endoscopes
Intervertebral disc displacement
Radiomics
Recurrence
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
10 Oct 2024
10 Oct 2024
Historique:
received:
17
10
2023
accepted:
01
10
2024
medline:
11
10
2024
pubmed:
11
10
2024
entrez:
10
10
2024
Statut:
epublish
Résumé
In recent years, radiomics has been shown to be an effective tool for the diagnosis and prediction of diseases. Existing evidence suggests that imaging features play a key role in predicting the recurrence of lumbar disk herniation (rLDH). Thus, this study aimed to evaluate the risk of rLDH in patients undergoing percutaneous endoscopic lumbar discectomy (PELD) using radiomics to facilitate the development of more rational surgical and perioperative management strategies. This was a retrospective case-control study involving 487 patients who underwent PELD at the L4/5 level. The rLDH and negative groups were matched using propensity score matching (PSM). A total of 1409 radiomic features were extracted from preoperative lumbar MRI images using intraclass correlation coefficient (ICC) analysis, t-test, and LASSO analysis. Afterward, 6 predictive models were constructed and evaluated using ROC curve analysis, AUC, specificity, sensitivity, confusion matrix, and 2 repeated 3-fold cross-validations. Lastly, the Shapley Additive Explanation (SHAP) analysis provided visual explanations for the models. Following screening and matching, 128 patients were included in both the recurrence and control groups. Moreover, 18 of the extracted radiomic features were selected for generating six models, which achieved an AUC of 0.551-0.859 for predicting rLDH. Among these models, SVM, RF, and XG Boost exhibited superior performances. Finally, cross-validation revealed that their accuracy was 0.674-0.791, 0.647-0.729, and 0.674-0.718. Radiomics based on MRI can be used to predict the risk of rLDH, offering more comprehensive guidance for perioperative treatment by extracting imaging information that cannot be visualized with the naked eye. Meanwhile, the accuracy and generalizability of the model can be improved in the future by incorporating more data and conducting multicenter studies.
Sections du résumé
BACKGROUND
BACKGROUND
In recent years, radiomics has been shown to be an effective tool for the diagnosis and prediction of diseases. Existing evidence suggests that imaging features play a key role in predicting the recurrence of lumbar disk herniation (rLDH). Thus, this study aimed to evaluate the risk of rLDH in patients undergoing percutaneous endoscopic lumbar discectomy (PELD) using radiomics to facilitate the development of more rational surgical and perioperative management strategies.
METHOD
METHODS
This was a retrospective case-control study involving 487 patients who underwent PELD at the L4/5 level. The rLDH and negative groups were matched using propensity score matching (PSM). A total of 1409 radiomic features were extracted from preoperative lumbar MRI images using intraclass correlation coefficient (ICC) analysis, t-test, and LASSO analysis. Afterward, 6 predictive models were constructed and evaluated using ROC curve analysis, AUC, specificity, sensitivity, confusion matrix, and 2 repeated 3-fold cross-validations. Lastly, the Shapley Additive Explanation (SHAP) analysis provided visual explanations for the models.
RESULTS
RESULTS
Following screening and matching, 128 patients were included in both the recurrence and control groups. Moreover, 18 of the extracted radiomic features were selected for generating six models, which achieved an AUC of 0.551-0.859 for predicting rLDH. Among these models, SVM, RF, and XG Boost exhibited superior performances. Finally, cross-validation revealed that their accuracy was 0.674-0.791, 0.647-0.729, and 0.674-0.718.
CONCLUSION
CONCLUSIONS
Radiomics based on MRI can be used to predict the risk of rLDH, offering more comprehensive guidance for perioperative treatment by extracting imaging information that cannot be visualized with the naked eye. Meanwhile, the accuracy and generalizability of the model can be improved in the future by incorporating more data and conducting multicenter studies.
Identifiants
pubmed: 39390384
doi: 10.1186/s12880-024-01450-x
pii: 10.1186/s12880-024-01450-x
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
273Subventions
Organisme : the Natural Science Foundation of Shan Dong Province
ID : ZR2021MH020
Organisme : the Qingdao Science and Technology Benefit the People Demonstration Project
ID : 23-2-8-smjk-7-nsh
Informations de copyright
© 2024. The Author(s).
Références
Kanno H, Aizawa T, Hahimoto K, Itoi E. Minimally invasive discectomy for lumbar disc herniation: current concepts, surgical techniques, and outcomes. Int Orthop. 2019;43:917–22. https://doi.org/10.1007/s00264-018-4256-5 .
doi: 10.1007/s00264-018-4256-5
pubmed: 30607499
Choi KC, Kim J-S, Park C-K. Percutaneous endoscopic lumbar discectomy as an alternative to open lumbar microdiscectomy for large lumbar disc herniation. Pain Physician. 2016;19:E291–300.
doi: 10.36076/ppj/2016.19.E291
pubmed: 26815256
Yin S, Du H, Yang W, Duan C, Feng C, Tao H. Prevalence of recurrent herniation following percutaneous endoscopic lumbar discectomy: a Meta-analysis. Pain Physician. 2018;21:337–50.
pubmed: 30045591
Yoon SM, Ahn S-S, Kim KH, Kim YD, Cho JH, Kim D-H. Comparative study of the outcomes of Percutaneous endoscopic lumbar discectomy and microscopic lumbar discectomy using the tubular Retractor System based on the VAS, ODI, and SF-36. Korean J Spine. 2012;9:215–22. https://doi.org/10.14245/kjs.2012.9.3.215 .
doi: 10.14245/kjs.2012.9.3.215
pubmed: 25983818
pmcid: 4431005
Chuanli Z. Unique Complications of Percutaneous EndoscopicLumbar Discectomy and Percutaneous EndoscopicInterlaminar Discectomy. Pain Physician. 2018;1:E105–12. https://doi.org/10.36076/ppj.2018.2.E105 .
doi: 10.36076/ppj.2018.2.E105
Wang H, Chen H, Duan S, Hao D, Liu J. Radiomics and Machine Learning with Multiparametric Preoperative MRI May accurately predict the histopathological grades of soft tissue sarcomas. J Magn Reson Imaging JMRI. 2020;51:791–7. https://doi.org/10.1002/jmri.26901 .
doi: 10.1002/jmri.26901
pubmed: 31486565
Zhang J, Sun J, Han T, Zhao Z, Cao Y, Zhang G, Zhou J. Radiomic features of magnetic resonance images as novel preoperative predictive factors of bone invasion in meningiomas. Eur J Radiol. 2020;132:109287. https://doi.org/10.1016/j.ejrad.2020.109287 .
doi: 10.1016/j.ejrad.2020.109287
pubmed: 32980725
Pan J, Zhang K, Le H, Jiang Y, Li W, Geng Y, Li S, Hong G. Radiomics Nomograms based on non-enhanced MRI and clinical risk factors for the differentiation of Chondrosarcoma from Enchondroma. J Magn Reson Imaging JMRI. 2021;54:1314–23. https://doi.org/10.1002/jmri.27690 .
doi: 10.1002/jmri.27690
pubmed: 33949727
Jiang Y-W, Xu X-J, Wang R, Chen C-M. Radiomics analysis based on lumbar spine CT to detect osteoporosis. Eur Radiol. 2022;32:8019–26. https://doi.org/10.1007/s00330-022-08805-4 .
doi: 10.1007/s00330-022-08805-4
pubmed: 35499565
pmcid: 9059457
Zhao C, Zhang H, Wang Y, Xu D, Han S, Meng S, Han J, Liu H, Zhou C, Ma X. Nomograms for Predicting recurrent herniation in PETD with preoperative radiological factors. J Pain Res. 2021;14:2095–109. https://doi.org/10.2147/JPR.S312224 .
doi: 10.2147/JPR.S312224
pubmed: 34276226
pmcid: 8277456
Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RGPM, Granton P, Zegers CML, Gillies R, Boellard R, Dekker A, Aerts HJWL. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer Oxf Engl 1990. 2012;48:441–6. https://doi.org/10.1016/j.ejca.2011.11.036 .
doi: 10.1016/j.ejca.2011.11.036
He L, Liu Z, Liu C, Gao Z, Ren Q, Lei L, Ren J. Radiomics Based on Lumbar Spine Magnetic Resonance Imaging to detect osteoporosis. Acad Radiol. 2021;28:e165–71. https://doi.org/10.1016/j.acra.2020.03.046 .
doi: 10.1016/j.acra.2020.03.046
pubmed: 32386949
Mu W, Jiang L, Zhang J, Shi Y, Gray JE, Tunali I, Gao C, Sun Y, Tian J, Zhao X, Sun X, Gillies RJ, Schabath MB. Non-invasive decision support for NSCLC treatment using PET/CT radiomics. Nat Commun. 2020;11:5228. https://doi.org/10.1038/s41467-020-19116-x .
doi: 10.1038/s41467-020-19116-x
pubmed: 33067442
pmcid: 7567795
Wang X, Wan Q, Chen H, Li Y, Li X. Classification of pulmonary lesion based on multiparametric MRI: utility of radiomics and comparison of machine learning methods. Eur Radiol. 2020;30:4595–605. https://doi.org/10.1007/s00330-020-06768-y .
doi: 10.1007/s00330-020-06768-y
pubmed: 32222795
Hasegawa K, Kitahara K, Hara T, Takano K, Shimoda H, Homma T. Evaluation of lumbar segmental instability in degenerative diseases by using a new intraoperative measurement system. J Neurosurg Spine. 2008;8:255–62. https://doi.org/10.3171/SPI/2008/8/3/255 .
doi: 10.3171/SPI/2008/8/3/255
pubmed: 18312077
Suk KS, Lee HM, Moon SH, Kim NH. Recurrent lumbar disc herniation: results of operative management. Spine. 2001;26:672–6. https://doi.org/10.1097/00007632-200103150-00024 .
doi: 10.1097/00007632-200103150-00024
pubmed: 11246384
Kim HS, You JD, Ju CI. Predictive scoring and risk factors of early recurrence after percutaneous endoscopic lumbar discectomy. BioMed Res Int. 2019;2019:6492675. https://doi.org/10.1155/2019/6492675 .
doi: 10.1155/2019/6492675
pubmed: 31828113
pmcid: 6881637
Kong M, Xu D, Gao C, Zhu K, Han S, Zhang H, Zhou C, Ma X. Risk factors for recurrent L4-5 disc herniation after percutaneous endoscopic transforaminal discectomy: a retrospective analysis of 654 cases, risk Manag. Healthc Policy. 2020;13:3051–65. https://doi.org/10.2147/RMHP.S287976 .
doi: 10.2147/RMHP.S287976
Zwanenburg A, Leger S, Vallières M, Löck S. Image biomarker standardisation initiative. Radiology. 2020;295:328–38. https://doi.org/10.1148/radiol.2020191145 .
doi: 10.1148/radiol.2020191145
pubmed: 32154773
Lundberg S, Lee S-I, editors. A unified approach to interpreting model predictions., in: Proc. 31st Int. Conf. Neural Inf. Process. Syst., 2017.
Yu G, Yang W, Zhang J, Zhang Q, Zhou J, Hong Y, Luo J, Shi Q, Yang Z, Zhang K, Tu H. Application of a nomogram to radiomics labels in the treatment prediction scheme for lumbar disc herniation. BMC Med Imaging. 2022;22:51. https://doi.org/10.1186/s12880-022-00778-6 .
doi: 10.1186/s12880-022-00778-6
pubmed: 35305577
pmcid: 8934490
Saravi B, Zink A, Ülkümen S, Couillard-Despres S, Wollborn J, Lang G, Hassel F. Clinical and radiomics feature-based outcome analysis in lumbar disc herniation surgery. BMC Musculoskelet Disord. 2023;24:791. https://doi.org/10.1186/s12891-023-06911-y .
doi: 10.1186/s12891-023-06911-y
pubmed: 37803313
pmcid: 10557221
Jiang Y, Chen C, Xie J, Wang W, Zha X, Lv W, Chen H, Hu Y, Li T, Yu J, Zhou Z, Xu Y, Li G. Radiomics signature of computed tomography imaging for prediction of survival and chemotherapeutic benefits in gastric cancer. EBioMedicine. 2018;36:171–82. https://doi.org/10.1016/j.ebiom.2018.09.007 .
doi: 10.1016/j.ebiom.2018.09.007
pubmed: 30224313
pmcid: 6197796
Staub LP, Aghayev E, Skrivankova V, Lord SJ, Haschtmann D, Mannion AF. Development and temporal validation of a prognostic model for 1-year clinical outcome after decompression surgery for lumbar disc herniation. Eur Spine J off Publ Eur Spine Soc Eur Spinal Deform Soc Eur Sect Cerv Spine Res Soc. 2020;29:1742–51. https://doi.org/10.1007/s00586-020-06351-5 .
doi: 10.1007/s00586-020-06351-5