European Spine JournalPub Date : 2025-03-01Epub Date: 2024-12-17DOI: 10.1007/s00586-024-08620-z
Jonathan H Geere, Paul R Hunter, Tom Marjoram, Amarjit S Rai
{"title":"Incidental durotomy in lumbar decompressive surgery: incidence and risk-factors, and the effect of durotomy on hospital and patient metrics.","authors":"Jonathan H Geere, Paul R Hunter, Tom Marjoram, Amarjit S Rai","doi":"10.1007/s00586-024-08620-z","DOIUrl":"10.1007/s00586-024-08620-z","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate incidental lumbar durotomy incidence and risk-factors, and the association of durotomy with perioperative metrics and patient-reported outcomes.</p><p><strong>Methods: </strong>A total 3140 cases of 1-3 level elective decompressive surgery from 2008 to 2023 at a single centre were included. Multivariable analysis was performed on literature derived variables to identify independent risk-factors for durotomy. Absolute difference or absolute risk increase (ARI) between durotomy and non-durotomy perioperative metrics was calculated. The association between durotomy and 3-month or 12-month patient-reported outcome measures was assessed.</p><p><strong>Results: </strong>All-procedure durotomy incidence was 4.5% (142/3140). Durotomy risk-factors were age (odds ratio (OR) 1.016, 95% confidence intervals (95% CI) 1.011-1.020), female (OR 1.48, 95% CI 1.26-1.74), number of operative levels (two-level OR 1.81, 95% CI 1.48-2.21; three-level OR 3.18, 95% CI 2.14-4.72), multiple versus no previous operation (OR 1.85, 95% CI 1.11-3.07), and fusion with discectomy versus discectomy (OR 2.36, 95% CI 1.90-2.93). Durotomy was associated with longer length of stay (∆2.4 days, p < 0.001), longer operative time (∆21 min, p < 0.001), and higher rate of iatrogenic nerve injury (ARI 4.3%, p < 0.001), 30-day return to theatre (ARI 5.7%, p < 0.001), and 30-day readmission (ARI 4.4%, p = 0.002). Durotomy was not associated with poorer patient-reported outcomes.</p><p><strong>Conclusion: </strong>Dural tears are often under-reported and are associated with longer hospital stay, increased operative time, and rare perioperative complications which increase healthcare costs. Dural tears did not, however, detrimentally affect patient-reported disability or pain outcomes.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1018-1025"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142834441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cross-cultural adaptation and validation of the simplified Chinese version of the Fukushima Lumbar Spinal Stenosis Scale.","authors":"Yuan Dong, Shiqi Cao, Shiran Zhou, Fanqi Hu, Wenhao Hu, Dingfei Qian, Haichao Yu, Zhen Zhang, Qiaoling Chen, Xuesong Zhang","doi":"10.1007/s00586-024-08562-6","DOIUrl":"10.1007/s00586-024-08562-6","url":null,"abstract":"<p><strong>Purpose: </strong>To translate and cross-culturally adapt Fukushima Lumbar Spinal Stenosis Scale into a Simplified Chinese version (FLS-25-SC), and evaluate the reliability and validity of FLS-25-SC in patients with lumbar spinal stenosis.</p><p><strong>Methods: </strong>Test-retest reliability was assessed by Intra-class correlation coefficient (ICC). Construct validity was analyzed by correlations between FLS-25-SC and the Swiss Spinal Stenosis (SSS) Questionnaire, Visual analogue scale (VAS) as well as the short form (36) health survey (SF-36).</p><p><strong>Results: </strong>The original version of the FLS-25 was cross-culturally adapted and translated into Simplified Chinese. FLS-25-SC was indicated to have excellent reliability (Cronbach's alpha = 0.941, ICC = 0.952). FLS-25-SC had almost perfect correlation with Physical Functioning (r = -0.870, P < 0.001) subscale of SF-36. Moderate to substantial correlations between FLS-25-SC and Symptom severity (r = 0.542, P < 0.001), Physical function (r = 0.604, P < 0.001) subscales of Swiss Spinal Stenosis (SSS) Questionnaire, VAS (r = 0.613, P < 0.001), as well as Role Physical (r = -0.537, P < 0.001) and Bodily Pain (r = -0.474, P < 0.001). It was observed that the loading of the 3 factors explained 63.108% of the total variance: [Kaiser-Mayer-Olkin (KMO) = 0.903, C2 = 1769.491, p < 0.001].</p><p><strong>Conclusion: </strong>FLS-25-SC has been shown to have acceptable reliability and validity in patients with degenerative lumbar spinal stenosis and may be recommended for patients in Chinese mainland.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"815-823"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142686366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2025-01-27DOI: 10.1007/s00586-025-08667-6
Zhicheng Li, Bo Liu, Liyan Su
{"title":"Effect and safety of percutaneous endoscopic interlaminar discectomy for L5-S1 disc herniation: direct inferior endplate approach versus indirect approach.","authors":"Zhicheng Li, Bo Liu, Liyan Su","doi":"10.1007/s00586-025-08667-6","DOIUrl":"10.1007/s00586-025-08667-6","url":null,"abstract":"<p><strong>Objective: </strong>To explore the efficacy and safety of the direct inferior endplate approach in percutaneous endoscopic interlaminar discectomy (PEID) for the treatment of L5-S1 disc herniation.</p><p><strong>Methods: </strong>This was a retrospective analysis of 116 patients with L5-S1 disc herniation treated with PEID; 74 patients underwent surgery via the direct inferior endplate approach (group A), and 42 patients underwent surgery via the indirect approach (group B). The number of intraoperative fluoroscopy exposures, establishment channel time, operation time, postoperative visual analogue scale (VAS) score, and Oswestry Disability Index (ODI) were compared between the 2 groups.</p><p><strong>Results: </strong>Compared with those in Group B, the channel establishment time, number of fluoroscopy exposures, and operation time in Group A were significantly lower (P < 0.05). There was no significant difference in the VAS score or ODI between the two groups (P > 0.05).</p><p><strong>Conclusions: </strong>Compared with the indirect approach, the direct inferior endplate approach can allow the exposed target to be reached more quickly, shorten the operation time, and reduce the degree of radiation exposure of doctors and patients, resulting in a high safety profile.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1115-1122"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2025-01-22DOI: 10.1007/s00586-025-08643-0
Carlos Alberto Cañas, Santiago Lopez-Garcia, Valentina Pérez-Uribe, Juan Diego Bolaños, Leidy Johanna Hurtado-Bermúdez, Fabio Bonilla-Abadía
{"title":"Efficacy of subcutaneous perispinal infiltration of triamcinolone in patients with symptomatic cervical osteoarthritis.","authors":"Carlos Alberto Cañas, Santiago Lopez-Garcia, Valentina Pérez-Uribe, Juan Diego Bolaños, Leidy Johanna Hurtado-Bermúdez, Fabio Bonilla-Abadía","doi":"10.1007/s00586-025-08643-0","DOIUrl":"10.1007/s00586-025-08643-0","url":null,"abstract":"<p><strong>Objective: </strong>To assess the efficacy and safety of subcutaneous perispinal infiltration of low dose of triamcinolone and lidocaine indicated for pain control in patients with cervical osteoarthritis (COA).</p><p><strong>Methods: </strong>Patients with symptomatic COA resistant to conventional treatment including anti-inflammatory drugs, analgesics, and physical therapy were included. Technetium-99 m pyrophosphate (99mTc-PYP) scintigraphy and computerized tomography (CT) fusion scans images were used for diagnosis of COA and as a guide for level(s) of infiltration(s). Infiltration consisted of subcutaneous administration of 1 cc of a mixture of triamcinolone (6 mg/0.7 cc) and 2% lidocaine (6 mg/0.3 cc) into the posterior central interspinal area, at the levels where the greatest uptake of the radiotracer was observed. Response was assessed using a pain analogue scale (PAS) (range 0-10 with 10 representing worst pain).</p><p><strong>Results: </strong>Forty-two patients were included. Thirty-six (85.7%) were women. The mean age was 59.2 years. Three months after infiltration clinical improvement was confirmed by a decrease in the PAS value: before and after infiltrations was 7.26 (range 4-10, SD:1.48) and 1.97 (range 0-6, SD:1.24), respectively. This difference being statistically significant (P < 0.05). No patient presented local or systemic adverse effects.</p><p><strong>Conclusions: </strong>Low dose subcutaneous perispinal injection of triamcinolone and lidocaine may offer clinical benefits for patients with symptomatic COA refractory to conventional treatments. 99mTc-PYP/CT fusion scans images were useful as a guide for localization of infiltrations.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1198-1202"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2025-01-20DOI: 10.1007/s00586-025-08651-0
Kensuke Toriumi, Hiroshi Miyamoto, Terumasa Ikeda, Koji Goto
{"title":"Magnetic resonance imaging evaluation of cervical paraspinal muscles in dropped head syndrome.","authors":"Kensuke Toriumi, Hiroshi Miyamoto, Terumasa Ikeda, Koji Goto","doi":"10.1007/s00586-025-08651-0","DOIUrl":"10.1007/s00586-025-08651-0","url":null,"abstract":"<p><strong>Purpose: </strong>The pathomechanism of dropped head syndrome (DHS) is unclear. In this study, we aimed to examine the features of the paraspinal cervical muscles in patients with DHS by analyzing the volume of these muscles using magnetic resonance imaging (MRI).</p><p><strong>Methods: </strong>Thirty-six patients with DHS and 25 patients with cervical spondylotic myelopathy (controls) were enrolled. The volume analyzer measured the cross-sectional area (CSA) of the paraspinal muscles on the axial image of a T2-weighted MRI at each level, from C2/3 to C6/7. The histogram used pixel intensities to measure the fat infiltration in the extensor muscles. The data were compared between the groups.</p><p><strong>Results: </strong>The CSA of the semispinalis capitis and the splenius capitis and cervicis from the extensor muscles in DHS was larger than that of the control group at almost all levels. The CSAs of other extensor muscles were equivalent to those of the controls. The CSA of the sternocleidomastoideus in DHS was smaller than in the control group at C4/5/6/7. The CSA of any extensor muscle in the chronic group of the DHS was smaller than that of the acute group at the lower levels. The percentage of fat infiltration was not significantly different between the groups.</p><p><strong>Conclusion: </strong>MRI analyses of the present study revealed that neither the extensor muscles in DHS were atrophic nor the flexor muscles were hypertrophic. Further, fatty infiltration of the extensor muscles may not induce muscle weakness of the extensors in patients with DHS.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"896-903"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2025-01-30DOI: 10.1007/s00586-025-08672-9
E J A Verheijen, T Kapogiannis, D Munteh, J Chabros, M Staring, T R Smith, C L A Vleggeert-Lankamp
{"title":"Artificial intelligence for segmentation and classification in lumbar spinal stenosis: an overview of current methods.","authors":"E J A Verheijen, T Kapogiannis, D Munteh, J Chabros, M Staring, T R Smith, C L A Vleggeert-Lankamp","doi":"10.1007/s00586-025-08672-9","DOIUrl":"10.1007/s00586-025-08672-9","url":null,"abstract":"<p><strong>Purpose: </strong>Lumbar spinal stenosis (LSS) is a frequently occurring condition defined by narrowing of the spinal or nerve root canal due to degenerative changes. Physicians use MRI scans to determine the severity of stenosis, occasionally complementing it with X-ray or CT scans during the diagnostic work-up. However, manual grading of stenosis is time-consuming and induces inter-reader variability as a standardized grading system is lacking. Machine Learning (ML) has the potential to aid physicians in this process by automating segmentation and classification of LSS. However, it is unclear what models currently exist to perform these tasks.</p><p><strong>Methods: </strong>A systematic review of literature was performed by searching the Cochrane Library, Embase, Emcare, PubMed, and Web of Science databases for studies describing an ML-based algorithm to perform segmentation or classification of the lumbar spine for LSS. Risk of bias was assessed through an adjusted version of the Newcastle-Ottawa Quality Assessment Scale that was more applicable to ML studies. Qualitative analyses were performed based on type of algorithm (conventional ML or Deep Learning (DL)) and task (segmentation or classification).</p><p><strong>Results: </strong>A total of 27 articles were included of which nine on segmentation, 16 on classification and 2 on both tasks. The majority of studies focused on algorithms for MRI analysis. There was wide variety among the outcome measures used to express model performance. Overall, ML algorithms are able to perform segmentation and classification tasks excellently. DL methods tend to demonstrate better performance than conventional ML models. For segmentation the best performing DL models were U-Net based. For classification U-Net and unspecified CNNs powered the models that performed the best for the majority of outcome metrics. The number of models with external validation was limited.</p><p><strong>Conclusion: </strong>DL models achieve excellent performance for segmentation and classification tasks for LSS, outperforming conventional ML algorithms. However, comparisons between studies are challenging due to the variety in outcome measures and test datasets. Future studies should focus on the segmentation task using DL models and utilize a standardized set of outcome measures and publicly available test dataset to express model performance. In addition, these models need to be externally validated to assess generalizability.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1146-1155"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143064871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2024-12-17DOI: 10.1007/s00586-024-08610-1
Ulysse Coneys, Anne Tabard-Fougère, Nathaly Gavira, Romain Dayer
{"title":"Validating rasterstereography to evaluate thoracic kyphosis in patients with Scheuermann's disease.","authors":"Ulysse Coneys, Anne Tabard-Fougère, Nathaly Gavira, Romain Dayer","doi":"10.1007/s00586-024-08610-1","DOIUrl":"10.1007/s00586-024-08610-1","url":null,"abstract":"<p><strong>Purpose: </strong>Evaluate the validity of rasterstereography compared to low-dose, biplanar spine radiography for assessing thoracic kyphosis (TK) angles in Scheuermann's disease patients.</p><p><strong>Methods: </strong>This prospective study included all the Scheuermann's disease patients consulting our clinic from 2016 to 2018. Recruited patients underwent two-dimensional low-dose biplanar anteroposterior full-length spine radiography and rasterstereography on the same day. Relationships between the TK angles measured were evaluated using Pearson correlation coefficients. Agreement between radiographic and rasterstereographic TK angles was evaluated using two-way intraclass correlation coefficients (ICCs) and Bland-Altman plots. Proportional biases were assessed using the slope regression lines fitted to Bland-Altman plots.</p><p><strong>Results: </strong>The mean demographic and radiological characteristics of the 52 patients (20 girls; 39%) included were: age 13.1 ± 2 years; BMI 17.3 ± 2.8; and TK max. 50.4° ± 10°. Rasterstereographic TK angles were strongly correlated with radiographic TK angles evaluated from T2-T12 (r = 0.677) and from C7-Max (r = 0.704), with 'good' agreement (ICC > 0.75). A proportional bias was revealed in the slope regression line fitted to the Bland-Altman plot from the C7-Max radiography and the rasterstereography measurements (p = 0.034) but not from the T2-T12 and rasterstereographic TK angles (p = 0.997).</p><p><strong>Conclusion: </strong>Rasterstereography is a reliable means of quantifying TK angles in Scheuermann's disease patients. It could directly reduce the number of radiographic scans patients need over time, minimising their radiation exposure.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"831-836"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142834491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
European Spine JournalPub Date : 2025-03-01Epub Date: 2025-01-19DOI: 10.1007/s00586-025-08649-8
Menekse Salar Barim, M Fehmi Capanoglu, Richard F Sesek, Sean Gallagher, Mark C Schall, Ronald J Beyers, Gerard A Davis
{"title":"Scan/rescan reliability of magnetic resonance imaging (MRI).","authors":"Menekse Salar Barim, M Fehmi Capanoglu, Richard F Sesek, Sean Gallagher, Mark C Schall, Ronald J Beyers, Gerard A Davis","doi":"10.1007/s00586-025-08649-8","DOIUrl":"10.1007/s00586-025-08649-8","url":null,"abstract":"<p><strong>Background: </strong>Magnetic resonance imaging (MRI) is increasingly used to estimate the geometric dimensions of lower lumbar vertebrae. While MRI-based measurements have demonstrated good reliability with interclass correlation coefficients (ICCs) of 0.80 or higher, many evaluations focus solely on the comparison of identical MRI images. This approach primarily reflects analyst dexterity and does not assess the reliability of the entire process, including imaging and image selection.</p><p><strong>Objective: </strong>To evaluate the inter- and intra-rater reliability of the entire process of using MRI to measure biomechanically relevant lumbar spinal characteristics, incorporating imaging, image selection, and analysis.</p><p><strong>Methods: </strong>A dataset of 144 low-back MRI scans was analyzed. Reliability assessments were performed under different conditions: (1) identical scans rated by the same analyst at different times (intra-rater reliability) and (2) distinct scans of the same subject obtained by different MRI operators and analyzed by different analysts (inter-rater reliability). Mean absolute differences in measurements were calculated, and sources of variability, such as breathing artifacts, were noted.</p><p><strong>Results: </strong>Larger discrepancies were observed when comparing distinct scans analyzed by different MRI operators and analysts. In the \"worst-case\" scenario, where both the MRI operator and analyst differed, a 4.05% mean absolute difference was noted for anterior endplate measurements. This was higher than the 2.76% difference observed when analysts re-rated their own scans after one month. Despite these discrepancies, the variability in measurements was relatively low and primarily attributed to factors like breathing artifacts.</p><p><strong>Conclusion: </strong>The process of using MRI to derive biomechanical measures, particularly for bony structures, demonstrates robust reliability. Variability in measurements is minimal even under challenging conditions, supporting the use of MRI for biomechanical assessments.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"887-895"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909044/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT.","authors":"Jianan Chen, Song Liu, Yong Li, Zaoqiang Zhang, Nianchun Liao, Huihong Shi, Wenjun Hu, Youxi Lin, Yanbo Chen, Bo Gao, Dongsheng Huang, Anjing Liang, Wenjie Gao","doi":"10.1007/s00586-024-08623-w","DOIUrl":"10.1007/s00586-024-08623-w","url":null,"abstract":"<p><strong>Purpose: </strong>To develop a deep learning system for automatic segmentation of compression fracture vertebral bodies on thoracolumbar CT and differentiate between fresh and old fractures.</p><p><strong>Methods: </strong>We included patients with thoracolumbar fractures treated at our Hospital South Campus from January 2020 to December 2023, with prospective validation from January to June 2024, and used data from the North Campus from January to December 2023 for external validation. Fresh fractures were defined as back pain lasting less than 4 weeks, with MRI showing bone marrow edema (BME). We utilized a 3D V-Net for image segmentation and several ResNet and DenseNet models for classification, evaluating performance with ROC curves, accuracy, sensitivity, specificity, precision, F1 score, and AUC. The optimal model was selected to construct deep learning system and its diagnostic efficacy was compared with that of two clinicians.</p><p><strong>Results: </strong>The training dataset included 238 vertebras (man/women: 55/183; age: 72.11 ± 11.55), with 59 in internal validation (man/women: 13/46; age: 74.76 ± 8.96), 34 in external validation, and 48 in prospective validation. The 3D V-Net model achieved a DSC of 0.90 on the validation dataset. ResNet18 performed best among classification models, with an AUC of 0.96 in validation, 0.89 in external dataset, and 0.87 in prospective validation, surpassing the two clinicians in both external and prospective validations.</p><p><strong>Conclusion: </strong>The deep learning model can automatically and accurately segment the vertebral bodies with compression fractures and classify them as fresh or old fractures, thereby assisting clinicians in making clinical decisions.</p>","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1177-1186"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142871908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Correction: Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT.","authors":"Jianan Chen, Song Liu, Yong Li, Zaoqiang Zhang, Nianchun Liao, Huihong Shi, Wenjun Hu, Youxi Lin, Yanbo Chen, Bo Gao, Dongsheng Huang, Anjing Liang, Wenjie Gao","doi":"10.1007/s00586-024-08636-5","DOIUrl":"10.1007/s00586-024-08636-5","url":null,"abstract":"","PeriodicalId":12323,"journal":{"name":"European Spine Journal","volume":" ","pages":"1218"},"PeriodicalIF":2.6,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143058496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}