Automated detection, labelling and radiological grading of clinical spinal MRIs.

Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful information from these scans can be challenging, time-consuming and hard to reproduce across different radiologists. In this paper, we alleviate these problems by introducing a multi-stage automated pipeline for analysing spinal MR scans. This pipeline first detects and labels vertebral bodies across several commonly used sequences (e.g. T1w, T2w and STIR) and fields of view (e.g. lumbar, cervical, whole spine). Using these detections it then performs automated diagnosis for several spinal disorders, including intervertebral disc degenerative changes in T1w and T2w lumbar scans, and spinal metastases, cord compression and vertebral fractures. To achieve this, we propose a new method of vertebrae detection and labelling, using vector fields to group together detected vertebral landmarks and a language-modelling inspired beam search to determine the corresponding levels of the detections. We also employ a new transformer-based architecture to perform radiological grading which incorporates context from multiple vertebrae and sequences, as a real radiologist would. The performance of each stage of the pipeline is tested in isolation on several clinical datasets, each consisting of 66 to 421 scans. The outputs are compared to manual annotations of expert radiologists, demonstrating accurate vertebrae detection across a range of scan parameters. Similarly, the model's grading predictions for various types of disc degeneration and detection of spinal metastases closely match those of an expert radiologist. To aid future research, our code and trained models are made publicly available.

Chiropractors' perceptions on the use of spinal radiographs in clinical practice: a qualitative study.

BACKGROUND: Radiography is commonly used in the assessment of spinal disorders, despite a lack of high-quality evidence demonstrating improved clinical outcomes or additional benefit to the patient. There is disagreement amongst chiropractors regarding the appropriate use of radiography for clinical management. This study aims to qualitatively explore chiropractors' perceptions on the use of spinal radiographs in clinical practice with respect to how they determine when to order radiographs; and how they use radiographs to inform clinical management. METHODS: Online qualitative semi-structured interviews were conducted with 17 Australian chiropractors who currently manage patients with spinal disorders. Convienence, snowball, and purposive sampling strategies were used to ensure an appropriate breadth and depth of participant characterisitcs and beliefs. Interview data were recorded, transcribed and analysed using framework analysis. RESULTS: Three themes were developed to describe how chiropractors determined when to order radiographs. These themes included specific findings from the clinical encounter that may inform clinical management, their perceptions of radiation risk, and the influence of clinical experience/intuition. Three themes and four subthemes were developed for how chiropractors use radiographs to inform their management. These themes explored the use of radiography for the application of chiropractic technique, as well as the role of radiographs in predicting patient prognosis, and as an educational tool to provide reassurance. CONCLUSION: Australian chiropractors' decision-making around spinal radiography is diverse and can be influenced by a number of clinical and external factors. Previously unexplored uses of spinal radiography in clinical practice were highlighted. Some chiropractors reported potential benefits of radiography that are currently not supported by research evidence. Future research should address how radiographic findings are reported to patients with spinal disorders and how this could be optimised to improve patient outcomes.

Deep learning reconstruction for lumbar spine MRI acceleration: a prospective study.

BACKGROUND: We compared magnetic resonance imaging (MRI) turbo spin-echo images reconstructed using a deep learning technique (TSE-DL) with standard turbo spin-echo (TSE-SD) images of the lumbar spine regarding image quality and detection performance of common degenerative pathologies. METHODS: This prospective, single-center study included 31 patients (15 males and 16 females; aged 51 ± 16 years (mean ± standard deviation)) who underwent lumbar spine exams with both TSE-SD and TSE-DL acquisitions for degenerative spine diseases. Images were analyzed by two radiologists and assessed for qualitative image quality using a 4-point Likert scale, quantitative signal-to-noise ratio (SNR) of anatomic landmarks, and detection of common pathologies. Paired-sample t, Wilcoxon, and McNemar tests, unweighted/linearly weighted Cohen κ statistics, and intraclass correlation coefficients were used. RESULTS: Scan time for TSE-DL and TSE-SD protocols was 2:55 and 5:17 min:s, respectively. The overall image quality was either significantly higher for TSE-DL or not significantly different between TSE-SD and TSE-DL. TSE-DL demonstrated higher SNR and subject noise scores than TSE-SD. For pathology detection, the interreader agreement was substantial to almost perfect for TSE-DL, with κ values ranging from 0.61 to 1.00; the interprotocol agreement was almost perfect for both readers, with κ values ranging from 0.84 to 1.00. There was no significant difference in the diagnostic confidence or detection rate of common pathologies between the two sequences (p ≥ 0.081). CONCLUSIONS: TSE-DL allowed for a 45% reduction in scan time over TSE-SD in lumbar spine MRI without compromising the overall image quality and showed comparable detection performance of common pathologies in the evaluation of degenerative lumbar spine changes. RELEVANCE STATEMENT: Deep learning-reconstructed lumbar spine MRI protocol enabled a 45% reduction in scan time compared with conventional reconstruction, with comparable image quality and detection performance of common degenerative pathologies. KEY POINTS: • Lumbar spine MRI with deep learning reconstruction has broad application prospects. • Deep learning reconstruction of lumbar spine MRI saved 45% scan time without compromising overall image quality. • When compared with standard sequences, deep learning reconstruction showed similar detection performance of common degenerative lumbar spine pathologies.

Baastrup's disease prevalence across various age groups and its association with degenerative changes: insights from STIR sequence in MRI.

PURPOSE: Baastrup's disease is characterized by abnormal contact between adjacent spinous processes. Our study is the first to systematically incorporate the STIR sequence, recognized for its heightened sensitivity to fluid and edema, into the MRI protocol for diagnosing Baastrup's disease in symptomatic individuals. The objective is to determine its prevalence and association with lumbar spinal degenerative changes. MATERIALS AND METHODS: Lumbar spinal MRI examinations of 375 patients performed between January 2021 and 2022 were retrospectively reviewed by two radiologists. Baastrup's disease was diagnosed based on meeting any of the following criteria: lumbar interspinous bursitis, hyperintense signal changes in adjacent spinous processes, and ligaments on the STIR sequence. The study also investigated the presence of degenerative changes and interreader agreement among radiologists. RESULTS: Baastrup's disease was found in 141 of 375 individuals (37.8%). It correlated significantly with degenerative lumbar changes such as bulging (P = 0.0012), herniation (P = 0.0033), disc degeneration (P = 0.0013), Modic changes (P = 0.034), facet osteoarthritis (P = 0.0041), spinal stenosis (P = 0.005), and anterolisthesis (P = 0.0049). No significant associations were observed with gender (P = 0.468) or retrolisthesis (P = 0.167). Its occurrence increased gradually, peaking at 87.5% in individuals aged 80 and above. Radiologists showed complete agreement with Baastrup's diagnoses. CONCLUSION: Baastrup's disease is more commonly observed than being considered rare, displaying an incremental occurrence with increasing age in symptomatic individuals notably discernible on the STIR sequence. Using the STIR sequence seems to promote a consensus among radiologists, irrespective of their experience levels.

Fast and accurate 3-D spine MRI segmentation using FastCleverSeg.

Accurate and efficient segmenting of vertebral bodies, muscles, and discs is crucial for analyzing various spinal diseases. However, traditional methods are either laborious and time-consuming (manual segmentation) or require extensive training data (fully automatic segmentation). FastCleverSeg, our proposed semi-automatic segmentation approach, addresses those limitations by significantly reducing user interaction while maintaining high accuracy. First, we reduce user interaction by requiring the manual annotation of only two or three slices. Next, we automatically Estimate the Annotation on Intermediary Slices (EANIS) using traditional computer vision/graphics concepts. Finally, our proposed method leverages improved voxel weight balancing to achieve fast and precise volumetric segmentation in the segmentation process. Experimental evaluations on our assembled diverse MRI databases comprising 179 patients (60 male, 119 female), demonstrate a remarkable 25 ms (30 ms standard deviation) processing time and a significant reduction in user interaction compared to existing approaches. Importantly, FastCleverSeg maintains or surpasses the segmentation quality of competing methods, achieving a Dice score of 94%. This invaluable tool empowers physicians to efficiently generate reliable ground truths, expediting the segmentation process and paving the way for future integration with deep learning approaches. In turn, this opens exciting possibilities for future fully automated spine segmentation.

Comparison of image quality and diagnostic efficacy of routine clinical lumbar spine imaging at 0.55T and 1.5/3T.

PURPOSE: To compare image quality, assess inter-reader variability, and evaluate the diagnostic efficacy of routine clinical lumbar spine sequences at 0.55T compared with those collected at 1.5/3T to assess common spine pathology. METHODS: 665 image series across 70 studies, collected at 0.55T and 1.5/3T, were assessed by two neuroradiology fellows for overall imaging quality (OIQ), artifacts, and accurate visualization of anatomical features (intervertebral discs, neural foramina, spinal cord, bone marrow, and conus / cauda equina nerve roots) using a 4-point Likert scale (1 = non-diagnostic to 4 = excellent). For the 0.55T scans, the most appropriate diagnosis(es) from a picklist of common spine pathologies was selected. The mean ± SD of all scores for all features for each sequence and reader at 0.55T and 1.5/3T were calculated. Paired t-tests (p ≤ 0.05) were used to compare ratings between field strengths. The inter-reader agreement was calculated using linear-weighted Cohen's Kappa coefficient (p ≤ 0.05). Unpaired VCG analysis for OIQ was additionally employed to represent differences between 0.55T and 1.5/3T (95 % CI). RESULTS: All sequences at 0.55T were rated as acceptable (≥2) for diagnostic use by both readers despite significantly lower scores for some compared to those at 1.5/3T. While there was low inter-reader agreement on individual scores, the agreement on the diagnosis was high, demonstrating the potential of this system for detecting routine spine pathology. CONCLUSIONS: Clinical lumbar spine imaging at 0.55T produces diagnostic-quality images demonstrating the feasibility of its use in diagnosing spinal pathology, including osteomyelitis/discitis, post-surgical changes with complications, and metastatic disease.

Butterfly Vertebra: A Retrospective Study of 30 Patients.

BACKGROUND: Butterfly vertebra (BV) is a rare congenital spinal anomaly for which there is a paucity of large-scale retrospective studies and established guidelines for treatment. The objective of this study was to elucidate the clinical characteristics, imaging findings, and therapeutic approaches for BV. METHODS: We conducted a retrospective analysis of 30 patients diagnosed with BV at our hospital from 2009 to 2023, examining clinical data, imaging findings, and clinical interventions. RESULTS: The analysis comprised a cohort of 30 patients, consisting of 15 males and 15 females, with a mean age of 27.63 ± 19.84 years. Imaging studies indicated that the majority of vertebral bodies affected by BV were single-segmented (63.3%, 19/30) and less commonly multi-segmented (36.7%, 11/30). These findings frequently coexisted with other medical conditions, most notably spinal scoliosis (76.7%, 23/30). Furthermore, the study identified a range of spinal abnormalities among patients, including hemivertebral deformity (30.0%, 9/30), spinal cleft (10.0%, 3/30), lumbar disc protrusion or herniation (10.0%, 3/30), vertebral slippage (10.0%, 3/30), thoracic kyphosis deformity (6.67%, 2/30), vertebral fusion deformity (6.67%, 2/30), compressive fractures (3.3%, 1/30), and vertebral developmental anomalies (3.3%, 1/30). Clinical intervention resulted in symptom relief for 23 nonsurgical patients through lifestyle modifications, analgesic use, and physical therapy. Seven surgical patients underwent appropriate surgical procedures, leading to satisfaction and adherence to regular postoperative follow-up appointments. CONCLUSIONS: BV is a rare vertebral anomaly that can be easily misdiagnosed due to its similarity to other diseases. Consequently, it is imperative to enhance vigilance in the differential diagnosis process in order to promptly recognize BV. Furthermore, in cases where patients present with additional associated radiographic findings, a thorough evaluation is typically warranted and timely measures should be taken for treatment.

Imaging review of the atypical spinal epidural space pathologies.

Pathologies affecting the spinal epidural space (SES) comprise various abnormalities. However, they all have the potential to cause thecal sac narrowing or spinal cord compression. In this review, we group these pathologies into degenerative, infective, neoplastic, vascular, traumatic, and others, focusing on their imaging features. Degenerative pathologies of the SES range from disc to facet disease, with a particular emphasis on the less common degenerative pathologies in this review. Infective pathologies affecting the epidural space include spondylodiscitis and associated epidural phlegmon and abscess. Neoplasms arising from typical SES components include neurofibroma, hemangioma, and liposarcoma. MRI is the best modality to assess the anatomy and abnormalities of the epidural space. MRI, combined with computed tomography, or a radiograph, is useful for the evaluation of bones or radiopaque foreign bodies.

Generative adversarial networks for spine imaging: A critical review of current applications.

PURPOSE: In recent years, the field of medical imaging has witnessed remarkable advancements, with innovative technologies which revolutionized the visualization and analysis of the human spine. Among the groundbreaking developments in medical imaging, Generative Adversarial Networks (GANs) have emerged as a transformative tool, offering unprecedented possibilities in enhancing spinal imaging techniques and diagnostic outcomes. This review paper aims to provide a comprehensive overview of the use of GANs in spinal imaging, and to emphasize their potential to improve the diagnosis and treatment of spine-related disorders. A specific review focusing on Generative Adversarial Networks (GANs) in the context of medical spine imaging is needed to provide a comprehensive and specialized analysis of the unique challenges, applications, and advancements within this specific domain, which might not be fully addressed in broader reviews covering GANs in general medical imaging. Such a review can offer insights into the tailored solutions and innovations that GANs bring to the field of spinal medical imaging. METHODS: An extensive literature search from 2017 until July 2023, was conducted using the most important search engines and identified studies that used GANs in spinal imaging. RESULTS: The implementations include generating fat suppressed T2-weighted (fsT2W) images from T1 and T2-weighted sequences, to reduce scan time. The generated images had a significantly better image quality than true fsT2W images and could improve diagnostic accuracy for certain pathologies. GANs were also utilized in generating virtual thin-slice images of intervertebral spaces, creating digital twins of human vertebrae, and predicting fracture response. Lastly, they could be applied to convert CT to MRI images, with the potential to generate near-MR images from CT without MRI. CONCLUSIONS: GANs have promising applications in personalized medicine, image augmentation, and improved diagnostic accuracy. However, limitations such as small databases and misalignment in CT-MRI pairs, must be considered.

Multiple spinal gas in an 86-year-old diabetic man.

Although spinal gas is common and can be found in various sites and lesions, it should prompt a search for the underlying cause, given that the clinical significance of ectopic gas varies from benign to scary. Spinal gas can occur in the traumatic, iatrogenic, degenerative, osteoporotic, infectious, or neoplastic lesions. The imaging similarity may cause the misdiagnosis or delayed diagnosis which sometimes requires immediate attention. The pattern of gas distribution, detailed appearance, clinical history, and findings on examination can provide clues to diagnosis. Computed tomography is the best method for sensitive detection of gas.

Diagnostic evaluation of deep learning accelerated lumbar spine MRI.

BACKGROUND AND PURPOSE: Deep learning (DL) accelerated MR techniques have emerged as a promising approach to accelerate routine MR exams. While prior studies explored DL acceleration for specific lumbar MRI sequences, a gap remains in comprehending the impact of a fully DL-based MRI protocol on scan time and diagnostic quality for routine lumbar spine MRI. To address this, we assessed the image quality and diagnostic performance of a DL-accelerated lumbar spine MRI protocol in comparison to a conventional protocol. METHODS: We prospectively evaluated 36 consecutive outpatients undergoing non-contrast enhanced lumbar spine MRIs. Both protocols included sagittal T1, T2, STIR, and axial T2-weighted images. Two blinded neuroradiologists independently reviewed images for foraminal stenosis, spinal canal stenosis, nerve root compression, and facet arthropathy. Grading comparison employed the Wilcoxon signed rank test. For the head-to-head comparison, a 5-point Likert scale to assess image quality, considering artifacts, signal-to-noise ratio (SNR), anatomical structure visualization, and overall diagnostic quality. We applied a 15% noninferiority margin to determine whether the DL-accelerated protocol was noninferior. RESULTS: No significant differences existed between protocols when evaluating foraminal and spinal canal stenosis, nerve compression, or facet arthropathy (all p > .05). The DL-spine protocol was noninferior for overall diagnostic quality and visualization of the cord, CSF, intervertebral disc, and nerve roots. However, it exhibited reduced SNR and increased artifact perception. Interobserver reproducibility ranged from moderate to substantial (κ = 0.50-0.76). CONCLUSION: Our study indicates that DL reconstruction in spine imaging effectively reduces acquisition times while maintaining comparable diagnostic quality to conventional MRI.

Surgical management of spinal pathologies in the octogenarian: a narrative review.

Optimal management paradigms of spinal pathologies in the octogenarian population are controversial given the higher incidence of comorbidities with concern for poor prognosis and fear of increased complications associated with surgical management. In this narrative review, we aim to detail the complex clinical considerations when approaching odontoid screw fixation/instrumented fusion, spinal decompression, and spinal fusion in the octogenarian. Literature review was conducted via Google Scholar and PubMed databases, with literature selected based on statistical power and clinical relevance to the following pathologies/surgical techniques: odontoid fracture, surgical decompression, and surgical fusion in the octogenarian. The aforementioned pathologies were selected based on prevalence in the advanced-age population in which surgical screening techniques and management remain nonuniform. Preoperative evaluation of the octogenarian patient increasingly includes frailty, sarcopenia, and osteopenia/osteoporosis assessments. In cases of odontoid fracture, conservative management appears to provide beneficial clinical outcomes with lower rates of complication compared to surgery; however, rates of radiographic odontoid fusion are far lower in conservatively managed patients. Regarding surgical decompression and fusion, the presence of comorbidities may be more predictive of outcome rather than age status, with the advent of minimally invasive techniques providing safety and efficacy in the surgical management of this age cohort. Age status may be less pertinent than previously thought in the decision to pursue spinal surgery for odontoid fracture, spinal decompression, or spinal fusion; however, each of these procedures has respective risks and benefits that must be considered within the context of each patient's comorbidity profile.

Management of Tarlov cysts: an uncommon but potentially serious spinal column disease-review of the literature and experience with over 1000 referrals.

Tarlov cysts were thought to be anatomic variants of uncertain etiology and clinical significance when initially described over 80 years ago. They are often detected in routine lumbosacral imaging and generally not reported in a differential diagnosis. There is increasing evidence that at least some Tarlov cysts are symptomatic and can have a significant adverse impact on patients' health and well-being. Women are disproportionately affected with this condition, often presenting with long-standing pain and neurological dysfunctions. Significant gender bias has been a concern in the management of these patients. Unfortunately, there is no consensus on patient selection or management approaches for symptomatic Tarlov cysts. This review article updates information on the prevalence, diagnosis, clinical significance, and treatments of these cysts. Based on these findings and experience with over 1000 patient referrals, a treatment decision algorithm for symptomatic Tarlov cysts was constructed to provide guidance for appropriate management of patients with these complex cysts.

Socioeconomic differences in the utilization of diagnostic imaging and non-pharmaceutical conservative therapies for spinal diseases.

BACKGROUND: A different utilization of health care services due to socioeconomic status on the same health plan contradicts the principle of equal treatment. We investigated the presence and magnitude of socioeconomic differences in utilization of diagnostic imaging and non-pharmaceutical conservative therapies for patients with spinal diseases. METHODS: The cohort study based on routine healthcare data from Germany with 11.7 million patient-years between 2012 and 2016 for patients with physician-confirmed spinal diseases (ICD-10: M40-M54), occupation and age 20 to 64 years. A Poisson model estimated the effects of the socioeconomic status (school education, professional education and occupational position) for the risk ratio of receiving diagnostic imaging (radiography, computed tomography, magnetic resonance imaging) and non-pharmaceutical conservative therapies (physical therapy including exercise therapy, manual therapy and massage, spinal manipulative therapy, acupuncture). RESULTS: Patients received diagnostic imaging in 26%, physical therapy in 32%, spinal manipulative therapy in 25%, and acupuncture in 4% of all patient-years. Similar to previous survey-based studies higher rates of utilization were associated with higher socioeconomic status. These differences were most pronounced for manual therapy, exercise therapy, and magnetic resonance imaging. CONCLUSIONS: The observed differences in health care utilization were highly related to socioeconomic status. Socioeconomic differences were higher for more expensive health services. Further research is necessary to identify barriers to equitable access to health services and to take appropriate action to decrease existing social disparities.

Update on Pediatric Spine Imaging.

The spine is often difficult to evaluate clinically in children, increasing the importance of diagnostic imaging to detect a wide variety of spinal disorders ranging from congenital abnormalities to severe infections. Clinical history and physical examination can help determine whether imaging is needed and which imaging technique would be best. The most common cause for back pain, even in children, is muscular strain/spasm that does not require any imaging. However, red flags such as pain at age < 5 years, constant pain, night pain, radicular pain, pain lasting > 4 weeks, or an abnormal neurologic examination may require further investigation. Imaging can be of great value for diagnosis but must be interpreted along with the clinical history, physical examination, and laboratory findings to achieve an accurate diagnosis. We discuss imaging for the most common and/or important spine pathologies in children: congenital and developmental pathologies, trauma, infectious processes, inflammatory causes, and tumors.

A comparison of radiographic degeneration features of older Chinese women and older Italian Caucasian women with a focus on thoracic spine.

BACKGROUND: Compared with Caucasians, East Asians have a lower incident of back pain, lower prevalence and severity of osteoporotic vertebral fracture and lumbar spine degeneration. AIM: This study compares radiographic spine degeneration features of older Chinese women (as an example of East Asians) and older Italian women (as an example of Caucasians) with a focus on the thoracic spine. METHODS: From two population-based epidemiological studies conducted in Hong Kong, China and Rome, Italy, 297 pairs (mean age: 73.6 years) age-matched older community women's lateral spine radiographs were sampled. Existence (or absence) of seven degeneration features were assessed including: (1) hyper-kyphosis, (2) disc space narrowing (T3/T4 ~ T11/T12), (3) osteoarthritic (OA) wedging (T4 ~ T12), (4) generalised osteophyte formation (T4 ~ T12); (5) acquired short vertebrae (T4 ~ T12), (6) Schmorl node (T4 - L5), (7) disc calcification (T4-L5). RESULTS: Italian women were more likely to have hyper-kyphosis (53.4% vs 25.6%), disc space narrowing (34.4% vs. 17.2%), OA wedging (6.4% vs. 0.67%), Schmorl node (19.5% vs. 4.4%, all P < 0.001). However, there was no statistically significant difference in osteophyte formation (7.7% vs. 9.4%, P > 0.1) and acquired short vertebrae (8.0% vs. 10.4%, P > 0.1). Disc calcification was uncommon among both Chinese and Italians. DISCUSSION AND CONCLUSION: For the first time, this study documented a lower prevalence of a number of thoracic spine degeneration features among Chinese. This study further affirms the concept of a generally healthier spine in older Chinese relative to older Caucasians. The observed differences may reflect a foundational background influence of genetic predisposition that represents an important line of future research.

Spinal Navigation for Lateral Instrumentation of the Thoracolumbar Spine.

BACKGROUND AND OBJECTIVES: Three-dimensional imaging-based navigation in spine surgery is mostly applied for pedicle screw placement. However, its potential reaches beyond. In this study, we analyzed the incorporation of spinal navigation for lateral instrumentation of the thoracolumbar spine in clinical routine at a high-volume spine center. METHODS: Patients scheduled for lateral instrumentation were prospectively enrolled. A reference array was attached to the pelvis, and a computed tomography scan was acquired intraoperatively. A control computed tomography scan was routinely performed after final cage placement, replacing conventional 2-dimensional X-ray imaging. RESULTS: 145 cases were enrolled from April to October 2021 with a median of 1 (1-4) level being instrumented. Indications for surgery were trauma (35.9%), spinal infection (31.7%), primary and secondary tumors of the spine (17.2%), and degenerative spine disease (15.2%). The duration of surgery after the first scan was 98 ± 41 (20-342) minutes. In total, 190 cages were implanted (94 expandable cages for vertebral body replacement (49.5%) and 96 cages for interbody fusion [50.5%]). Navigation was successfully performed in 139 cases (95.9%). The intraoperative mental load was rated on a scale from 0 to 150 (maximal effort) by the surgeons, showing a moderate effort (median 30 [10-120]). CONCLUSION: Three-dimensional imaging-based spinal navigation can easily be incorporated in clinical routine and serves as a reliable tool to achieve precise implant placement in lateral instrumentation of the spine. It helps to minimize radiation exposure to the surgical staff.

Langerhans Cell Histiocytosis in the Pediatric Spine Requiring Stabilization: A Literature Review and Report of 3 Cases.

CASE: This report describes 3 cases of Langerhans cell histiocytosis (LCH) of the cervical and thoracic spine in patients aged 4 to 10 years. Each patient had painful lytic spinal lesions with vertebral body collapse and posterior involvement suggesting instability requiring corpectomy, grafting, and fusion. All 3 patients were doing well at their most recent follow-up without pain or recurrence. CONCLUSION: Although LCH of the pediatric spine is usually successfully treated non-operatively, we recommend corpectomy and fusion when there is instability of the spinal column and/or severe stenosis. Posterior element involvement occurred in all 3 cases and may lead to instability.