Spine deformity最新文献

{"title":"18th International Congress on Early Onset Scoliosis and the Growing Spine : November 13-15, 2024 Scottsdale, Arizona, USA.","authors":"","doi":"10.1007/s43390-024-00972-2","DOIUrl":"https://doi.org/10.1007/s43390-024-00972-2","url":null,"abstract":"","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142583746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A team approach to improve outcomes in pediatric scoliosis surgery: a review of the current literature.","authors":"Anshu Jonnalagadda, Jay Moran, Albert Rancu, Michael J Gouzoulis, Sahir S Jabbouri, Seongho Jeong, Dominick A Tuason","doi":"10.1007/s43390-024-01004-9","DOIUrl":"https://doi.org/10.1007/s43390-024-01004-9","url":null,"abstract":"<p><strong>Study design: </strong>Review article.</p><p><strong>Objective: </strong>To review the literature on the effect of specialized pediatric spine teams on clinical outcomes.</p><p><strong>Results: </strong>Thirty-eight studies were identified in the review. There were 11 studies discussing the efficacy of the dual-surgeon strategy, 5 studies discussing the benefits of adult dedicated spine teams, 3 studies discussing the benefits of dedicated pediatric spine teams, 8 studies discussing the healthcare professional composition of multidisciplinary spine teams, and 20 studies discussing various clinical markers evaluating the efficacy of new team- or protocol-based interventions.</p><p><strong>Conclusion: </strong>Pediatric spinal deformity surgery is a highly invasive procedure with room for intervention to minimize surgical complications and enhance patient outcomes. The use of standardized spine teams, comprising surgeons and various healthcare professionals from diverse disciplines, has proven to be an effective strategy for improving both quality and efficiency of care. Furthermore, implementing uniform protocols among these teams has led to reductions in surgical duration, hospitalization periods, and risks such as infections at the surgical site and excessive bleeding. Further studies are necessary to evaluate additional benefits that specialized pediatric spine teams can offer in terms of clinical outcomes.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142583842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research trends of biomechanics in scoliosis from 1999 to 2023: a bibliometric analysis.","authors":"Peng Dou, Xuan Li, Haobo Jin, Boning Ma, Ming Jin, Yi Xu","doi":"10.1007/s43390-024-01000-z","DOIUrl":"https://doi.org/10.1007/s43390-024-01000-z","url":null,"abstract":"<p><strong>Objective: </strong>Despite the abundance of research on the biomechanics of scoliosis, there is a lack of a comprehensive bibliometric analysis. This study utilizes bibliometric methods to elucidate the research trends and hotspots within this domain.</p><p><strong>Methods: </strong>The data for this study were obtained from the Web of Science Core Collection and then analyzed using the open-source Bibliometrix R package and Citespace.</p><p><strong>Results: </strong>The analysis encompassed 410 publications published from 1999 to 2023. There is a sustained increase in the number of publications within the field. Utilizing citation analysis and keyword analysis, the study identified key research focuses. Burst keyword analysis identified 19 keywords.</p><p><strong>Conclusions: </strong>The period from 1999 to 2023 has witnessed significant research attention on the biomechanics of scoliosis. The demographic shift towards an aging population has recently increased interest in ASD. Proximal biomechanical changes and transitional zones in PJK and PJF are hotspots in research, offering emerging scholars in this discipline valuable opportunities for exploration.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142583941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D external shape analysis and barycentremetry can provide early signs of progression in adolescent idiopathic scoliosis.","authors":"Tristan Langlais, Claudio Vergari, Nicolas Mainard, Xavier du Cluzel, Matthieu Baudoux, Laurent Gajny, Kariman Abelin-Genevois, Jean Claude Bernard, Zongshan Hu, Jack Chun Yiu Cheng, Winnie Chiu Wing Chu, Ayman Assi, Mohamad Karam, Ismat Ghanem, Tito Bassani, Fabio Galbusera, Luca Maria Sconfienza, Marco Brayda-Bruno, Isabelle Courtois, Eric Ebermeyer, Raphael Vialle, Jean Dubousset, Wafa Skalli","doi":"10.1007/s43390-024-01001-y","DOIUrl":"https://doi.org/10.1007/s43390-024-01001-y","url":null,"abstract":"<p><strong>Purpose: </strong>Our objective was to analysis the barycentremetry, obtained from the external envelope reconstruction of biplanar radiographs, in adolescent idiopathic scoliosis (AIS) and to determine whether assessing would help predict the distinction between progressive and stable AIS at the early stage.</p><p><strong>Methods: </strong>A retrospective study with a multicentre cohort of 205 AIS was conducted. All AIS underwent a biplanar X-ray between 2013 and 2020. Inclusion criteria were Cobb angle between 10° and 25°; Risser sign lower than 3; age higher than 10 years; and no previous treatment. A 3D spine reconstruction was performed, and the barycentremetry parameters were computed, i.e., the center of mass position at the apex and the axial torque at the apex, the upper and lower junction. A severity index, helping to distinguish stable and progressive AIS, was computed on the first radiograph, and weighted according to these parameters. A clinical and radiographic monitoring determined if AIS were classified such a stable or progressive scoliosis.</p><p><strong>Results: </strong>One hundred and sixty-two AIS were included (i.e., 87 were classified as stable and 75 as progressive). The apex center of mass position was different between the stable and progressive AIS groups (6 mm, SD = 4 mm for the whole cohort; 5 mm, SD = 4 mm for stable AIS versus 7 mm, SD = 4 mm for progressive AIS; p = 0.02). In AIS thoracic, the specificity and positive predictive value of the severity index increased by 19% and 16%, respectively, by adding the apex vertebral axial torque.</p><p><strong>Conclusion: </strong>Early assessment of the external envelope from biplanar X-ray reconstruction of idiopathic scoliosis showed that the apex centre of mass position was significantly different between progressive and stable scoliosis. The inclusion of the axial torque of the apex vertebra in the severity index is promising to help the clinician distinguish between stable and progressive thoracic AIS at an early stage.</p><p><strong>Level of evidence: </strong>II - Prognostic studies.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What imaging does my AIS patient need? A multi-group survey of provider preferences.","authors":"Jenny L Zheng, Ying Li, Grant Hogue, Megan Johnson, Jason B Anari, Maia D Regan, Keith D Baldwin","doi":"10.1007/s43390-024-00995-9","DOIUrl":"https://doi.org/10.1007/s43390-024-00995-9","url":null,"abstract":"<p><strong>Introduction: </strong>Adolescent idiopathic scoliosis (AIS) is a common diagnosis managed by pediatric orthopedic surgeons with nonoperative radiographic monitoring representing a cornerstone of treatment. Differences in practices and techniques for obtaining radiographic studies contribute to variation, cost of care, and hamper data aggregation. We surveyed several large organizations dedicated to children's orthopedics or scoliosis care to obtain a consensus for radiographic evaluation of AIS.</p><p><strong>Methods: </strong>A REDCap-based survey was developed across four institutions and beta-tested by staff and fellows from a single institution. The finalized survey was distributed to members of POSNA, PSSG, and SOSORT, and shared on social media. Participants were asked to rank the importance of various datapoints in radiographic assessment of the spinal deformity, skeletal maturity, and study indications during initial, subsequent, preoperative, and final office visits for AIS. Response rate for the overall group was 26%.</p><p><strong>Results: </strong>Cobb angle was considered the most important (> 94%) radiographic index across all time points. For positioning, 46% of respondents favored arms bent touching clavicles as the ideal positioning for X-rays, and another 24% favored arms down with palms forward (Table 2). The majority of respondents obtain lateral X-rays at the first visit (99%) and at the preoperative visit (70%). At the preoperative visit, sagittal contour (86%), apex location (85%), and Lenke classification (73%) were considered important factors to record. Flexibility studies are primarily obtained at the preoperative visit (89%) and 81% of respondents prefer bending films as the flexibility technique of choice. Regarding measures of skeletal maturity, Sanders bone age was considered to be the most important by over 70% of respondents across initial, subsequent, preoperative and brace wean visits (Fig. 2). MRIs were obtained routinely by 34% of respondents and only when the patient had a concerning symptom or finding for 67% of respondents.</p><p><strong>Conclusions: </strong>Despite large variations in radiographic examination of AIS, large areas of agreement were found. It is important to establish standards for positioning patients, evaluating skeletal maturity, and obtaining assessments including lateral views, flexibility studies, and advanced imaging. Establishing common practices for radiographic evaluation of AIS will allow for less variation in care and for critical questions to be answered through registry formation and large multicenter data collection.</p><p><strong>Significance: </strong>This study establishes current practitioner opinion on the radiographic evaluation of the AIS patient. Minimum data sets are useful for data aggregation and answering research questions in the face of data variability.</p><p><strong>Level of evidence: </strong>Level V.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Is the information provided by large language models valid in educating patients about adolescent idiopathic scoliosis? An evaluation of content, clarity, and empathy : The perspective of the European Spine Study Group.","authors":"Siegmund Lang, Jacopo Vitale, Fabio Galbusera, Tamás Fekete, Louis Boissiere, Yann Philippe Charles, Altug Yucekul, Caglar Yilgor, Susana Núñez-Pereira, Sleiman Haddad, Alejandro Gomez-Rice, Jwalant Mehta, Javier Pizones, Ferran Pellisé, Ibrahim Obeid, Ahmet Alanay, Frank Kleinstück, Markus Loibl","doi":"10.1007/s43390-024-00955-3","DOIUrl":"https://doi.org/10.1007/s43390-024-00955-3","url":null,"abstract":"<p><strong>Purpose: </strong>Large language models (LLM) have the potential to bridge knowledge gaps in patient education and enrich patient-surgeon interactions. This study evaluated three chatbots for delivering empathetic and precise adolescent idiopathic scoliosis (AIS) related information and management advice. Specifically, we assessed the accuracy, clarity, and relevance of the information provided, aiming to determine the effectiveness of LLMs in addressing common patient queries and enhancing their understanding of AIS.</p><p><strong>Methods: </strong>We sourced 20 webpages for the top frequently asked questions (FAQs) about AIS and formulated 10 critical questions based on them. Three advanced LLMs-ChatGPT 3.5, ChatGPT 4.0, and Google Bard-were selected to answer these questions, with responses limited to 200 words. The LLMs' responses were evaluated by a blinded group of experienced deformity surgeons (members of the European Spine Study Group) from seven European spine centers. A pre-established 4-level rating system from excellent to unsatisfactory was used with a further rating for clarity, comprehensiveness, and empathy on the 5-point Likert scale. If not rated 'excellent', the raters were asked to report the reasons for their decision for each question. Lastly, raters were asked for their opinion towards AI in healthcare in general in six questions.</p><p><strong>Results: </strong>The responses among all LLMs were 'excellent' in 26% of responses, with ChatGPT-4.0 leading (39%), followed by Bard (17%). ChatGPT-4.0 was rated superior to Bard and ChatGPT 3.5 (p = 0.003). Discrepancies among raters were significant (p < 0.0001), questioning inter-rater reliability. No substantial differences were noted in answer distribution by question (p = 0.43). The answers on diagnosis (Q2) and causes (Q4) of AIS were top-rated. The most dissatisfaction was seen in the answers regarding definitions (Q1) and long-term results (Q7). Exhaustiveness, clarity, empathy, and length of the answers were positively rated (> 3.0 on 5.0) and did not demonstrate any differences among LLMs. However, GPT-3.5 struggled with language suitability and empathy, while Bard's responses were overly detailed and less empathetic. Overall, raters found that 9% of answers were off-topic and 22% contained clear mistakes.</p><p><strong>Conclusion: </strong>Our study offers crucial insights into the strengths and weaknesses of current LLMs in AIS patient and parent education, highlighting the promise of advancements like ChatGPT-4.o and Gemini alongside the need for continuous improvement in empathy, contextual understanding, and language appropriateness.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel radiological predictors for the progression of proximal junctional kyphosis in osteoporotic vertebral compression fracture with kyphosis following posterior corrective surgery.","authors":"Junyu Li, Yinghong Ma, Baitao Liu, Junjie Ma, Zhuoran Sun, Yongqiang Wang, Miao Yu, Weishi Li, Yan Zeng","doi":"10.1007/s43390-024-00983-z","DOIUrl":"https://doi.org/10.1007/s43390-024-00983-z","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to identify the effect of some novel risk factors associated with L1 vertebrae and parameters closely related to the sagittal alignment for the occurrence of proximal junctional kyphosis (PJK) following surgery for patients with osteoporotic vertebral compression fractures (OVCF) kyphosis.</p><p><strong>Methods: </strong>74 OVCF patients undergoing posterior corrective surgery between January 2008 and June 2021 with a minimum 2-year follow-up were included. These patients were divided into PJK and non-PJK groups. Spinopelvic parameters, including thoracolumbar slope (TLS) and the L1 plumb line (L1PL) were measured preoperatively, postoperatively, and at follow-up. Multivariate logistic analysis was performed on various risk factors and Global Alignment and Proportion (GAP) scores. Associations between novel parameters and PJK were analyzed using receiver operating characteristic (ROC) analysis.</p><p><strong>Results: </strong>PJK was identified in 28.4% of patients. The mean age and follow-up were 63.45 years and 38.17 months, respectively. There was no difference between the PJK and the non-PJK groups in baseline demographics, pre-operative and immediate post-operative pelvic incidence-lumbar lordosis mismatch. Multiple comparisons showed that the proportion of PJK in the severely disproportioned group(the group with the highest GAP scores) and that of the other two groups with lower GAP scores were statistically different (P < 0.001). Potential risk factors for PJK included preoperative thoracic kyphosis (TK) (P < 0.001), TLS (P = 0.016), postoperative TLS (P < 0.001), and L1PL (P < 0.001). Postoperative TLS and L1PL were respectively independent risk factors for PJK, with the cut-off values set at 8.6° and 10.4 mm to predict the occurrence of PJK.</p><p><strong>Conclusions: </strong>TLS and L1PL can be used to predict the occurrence of PJK in patients undergoing surgery for OVCF and are crucial for preventing the progression of PJK. Achieving a proportionate GAP Score postoperatively seems to be a viable option as higher GAP scores were associated with higher rates of PJK.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142564309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-cultural adaptation, reliability and validity of the Greek version of the Spinal Appearance Questionnaire (SAQ) in patients with adolescent idiopathic scoliosis.","authors":"Marianna Oikonomaki, George Kelalis, Apostolos Z Skouras, Spiros Sotiropoulos, George Georgoudis, Theodoros Grivas","doi":"10.1007/s43390-024-00907-x","DOIUrl":"10.1007/s43390-024-00907-x","url":null,"abstract":"<p><strong>Purpose: </strong>The Spinal Appearance Questionnaire (SAQ) is a widely validated tool for assessing perceptions of spinal deformity in adolescent idiopathic scoliosis (AIS) patients. This study aimed to develop and validate a Greek version of the SAQ (GR-SAQ).</p><p><strong>Methods: </strong>A cross-cultural adaptation of the SAQ following international guidelines was performed. Internal consistency and test-retest reliability were evaluated. Convergent validity was assessed by correlating the GR-SAQ with the Appearance domain of Scoliosis Research Society-22 (SRS-22) and the Cobb angle with the Trunk Shift domain of GR-SAQ. Divergent validity was examined through the relationship between GR-SAQ, patient characteristics, and clinical measures including Cobb angle, DIERS Formetric 4D angle, and scoliometer readings.</p><p><strong>Results: </strong>The study included 61 AIS patients (52 females, 13.91 ± 2.57 years, 25.33 ± 10.14° Cobb angle). GR-SAQ exhibited good internal consistency (Cronbach's α = 0.794) and excellent test-retest reliability (ICC = 0.931, 95%CI: 0.880-0.960). Correlations between GR-SAQ and SRS-22 showed a low-to-moderate negative correlation (r = -0.351, p = 0.006). The Trunk Shift domain moderately correlated with the Cobb Angle (r = 0.393, p = 0.002). Divergent validity analyses did not demonstrate statistical significance (p > 0.05).</p><p><strong>Conclusion: </strong>The GR-SAQ is a valid and reliable tool for evaluating spinal deformity perception in Greek AIS patients.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141237302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influence of slippage reduction and correction of lumbosacral kyphosis by single-level posterior lumbar interbody fusion on spinal alignment in patients with dysplastic spondylolisthesis.","authors":"Kazuki Takeda, Satoshi Suzuki, Masahiro Ozaki, Yohei Takahashi, Osahiko Tsuji, Narihito Nagoshi, Mitsuru Yagi, Morio Matsumoto, Masaya Nakamura, Kota Watanabe","doi":"10.1007/s43390-024-00917-9","DOIUrl":"10.1007/s43390-024-00917-9","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate the influence of slippage reduction and correction of lumbosacral kyphosis by L5-S1 single-level posterior lumbar interbody fusion (PLIF) on spinal alignment and clinical outcomes including postoperative complications in patients with dysplastic spondylolisthesis (DS).</p><p><strong>Methods: </strong>Twenty consecutive patients with symptomatic and severe DS who underwent L5-S1 single-level PLIF with a minimum of 2 years of follow-up after surgery were included. Clinical outcomes were evaluated using the Japanese Orthopaedic Association (JOA) and visual analog scale (VAS) scores for low back and leg pain obtained on preoperative and postoperative examinations. Postoperative instrumentation failure and L5 radiculopathy were also evaluated. The preoperative and postoperative spinopelvic parameters were measured.</p><p><strong>Results: </strong>The JOA score significantly improved from 21.5 ± 4.8 (preoperative) to 27.0 ± 2.5 (postoperative), with a mean recovery rate of 75.0% ± 30.4%. The VAS score for low back pain significantly improved from 44.5 ± 30.1 (preoperative) to 11.5 ± 15.9 (postoperative), and that for leg pain significantly improved from 31.0 ± 33.2 (preoperative) to 5.0 ± 10.2 (postoperative). The slip percentage (% slip) significantly improved from 59.6% ± 13.5% (preoperative) to 25.2% ± 15.0% (postoperative). The lumbosacral angle (LSA) significantly improved from 12.3° ± 9.5° (preoperative) to 1.0° ± 4.9° (postoperative). L5-S1 PLIF led to significant improvement of lumbar lordosis (from 52.0° ± 15.9° to 59.7° ± 8.0°) and pelvic incidence - lumbar lordosis mismatch (from 23.9° ± 20.6° to 13.3° ± 10.0°). Correction of lumbosacral kyphosis had a significant positive correlation with postoperative pelvic tilt (PT) (r = 0.50, P = 0.02), while postoperative % slip did not have a significant correlation with postoperative PT.</p><p><strong>Conclusions: </strong>L5-S1 PLIF for DS provided good clinical outcomes. Correction of lumbosacral kyphosis had a positive impact on regaining ideal spinopelvic balance and may be beneficial in the setting of treating DS.</p><p><strong>Level of evidence iv: </strong></p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141459299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning classification of pediatric spinal radiographs for use in large scale imaging registries.","authors":"Kellen L Mulford, Christina M Regan, Julia E Todderud, Charles P Nolte, Zachariah Pinter, Connie Chang-Chien, Shi Yan, Cody Wyles, Bardia Khosravi, Pouria Rouzrokh, Hilal Maradit Kremers, A Noelle Larson","doi":"10.1007/s43390-024-00933-9","DOIUrl":"10.1007/s43390-024-00933-9","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study is to develop and apply an algorithm that automatically classifies spine radiographs of pediatric scoliosis patients.</p><p><strong>Methods: </strong>Anterior-posterior (AP) and lateral spine radiographs were extracted from the institutional picture archive for patients with scoliosis. Overall, there were 7777 AP images and 5621 lateral images. Radiographs were manually classified into ten categories: two preoperative and three postoperative categories each for AP and lateral images. The images were split into training, validation, and testing sets (70:15:15 proportional split). A deep learning classifier using the EfficientNet B6 architecture was trained on the spine training set. Hyperparameters and model architecture were tuned against the performance of the models in the validation set.</p><p><strong>Results: </strong>The trained classifiers had an overall accuracy on the test set of 1.00 on 1166 AP images and 1.00 on 843 lateral images. Precision ranged from 0.98 to 1.00 in the AP images, and from 0.91 to 1.00 on the lateral images. Lower performance was observed on classes with fewer than 100 images in the dataset. Final performance metrics were calculated on the assigned test set, including accuracy, precision, recall, and F1 score (the harmonic mean of precision and recall).</p><p><strong>Conclusions: </strong>A deep learning convolutional neural network classifier was trained to a high degree of accuracy to distinguish between 10 categories pre- and postoperative spine radiographs of patients with scoliosis. Observed performance was higher in more prevalent categories. These models represent an important step in developing an automatic system for data ingestion into large, labeled imaging registries.</p>","PeriodicalId":21796,"journal":{"name":"Spine deformity","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141749012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}