Automatic classification of the vertebral endplate lesions in magnetic resonance imaging by deep learning model.

Introduction: A novel classification scheme for endplate lesions, based on T2-weighted images from magnetic resonance imaging (MRI) scan, has been recently introduced and validated. The scheme categorizes intervertebral spaces as "normal," "wavy/irregular," "notched," and "Schmorl's node." These lesions have been associated with spinal pathologies, including disc degeneration and low back pain. The exploitation of an automatic tool for the detection of the lesions would facilitate clinical practice by reducing the workload and the diagnosis time. The present work exploits a deep learning application based on convolutional neural networks to automatically classify the type of lesion. Methods: T2-weighted MRI scans of the sagittal lumbosacral spine of consecutive patients were retrospectively collected. The middle slice of each scan was manually processed to identify the intervertebral spaces from L1L2 to L5S1, and the corresponding lesion type was labeled. A total of 1,559 gradable discs were obtained, with the following types of distribution: "normal" (567 discs), "wavy/irregular" (485), "notched" (362), and "Schmorl's node" (145). The dataset was divided randomly into a training set and a validation set while preserving the original distribution of lesion types in each set. A pretrained network for image classification was utilized, and fine-tuning was performed using the training set. The retrained net was then applied to the validation set to evaluate the overall accuracy and accuracy for each specific lesion type. Results: The overall rate of accuracy was found equal to 88%. The accuracy for the specific lesion type was found as follows: 91% (normal), 82% (wavy/irregular), 93% (notched), and 83% (Schmorl's node). Discussion: The results indicate that the deep learning approach achieved high accuracy for both overall classification and individual lesion types. In clinical applications, this implementation could be employed as part of an automatic detection tool for pathological conditions characterized by the presence of endplate lesions, such as spinal osteochondrosis.

Is posteromedial translation with sublaminar bands effective in correcting axial rotation in adolescent idiopathic scoliosis surgery? A 3D reconstruction study.

PURPOSE: Hybrid constructs with sublaminar bands have recently regained popularity as an alternative to all-screw construct for correction of adolescent idiopathic scoliosis (AIS). The aim of this study is to evaluate the ability of hybrid constructs with sublaminar bands to achieve a tridimensional correction of the scoliotic deformity. Our hypothesis is that hybrid construct with sublaminar bands are able to achieve a substantial derotation of the apical vertebrae, while preserving the thoracic kyphosis. METHODS: A prospective evaluation of 50 consecutive cases (41 F, 9 M, mean age 14.7 ± 2 years) of AIS correction with hybrid construct was performed. In all cases, sublaminar bands were used at the apex of the main curve on concave side. All patients underwent pre and postoperative X-rays with EOS System, with full 3D reconstruction. Spinopelvic parameters and axial rotation of the vertebrae were measured pre and postoperatively. RESULTS: 2.7 ± 0.9 mean sublaminar bands were used per patient. Mean correction of deformity was 50 ± 9.5%. on the coronal plane. The mean axial rotation of the apical vertebra went from 18° ± 11.5° preoperatively to 9.4° ± 7.2° postoperatively (p < 0.001) with a mean derotation of 47.7%. Thoracic kyphosis went from 32.1° ± 18° preoperatively to 37.3° ± 13.1° postoperatively (p < 0.05). No intraoperative complications due to sublaminar bands were recorded. CONCLUSIONS: Hybrid construct with sublaminar band have been showed to be safe and effective in deformity correction and in maintaining or restoring thoracic kyphosis. This study showed that with sublaminar bands applied at the curve apex a substantial derotation of the apical vertebrae can be achieved.

The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach.

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index-ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a "good early outcome". A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an "excellent early outcome". The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months' follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Accounting for Biomechanical Measures from Musculoskeletal Simulation of Upright Posture Does Not Enhance the Prediction of Curve Progression in Adolescent Idiopathic Scoliosis.

A major clinical challenge in adolescent idiopathic scoliosis (AIS) is the difficulty of predicting curve progression at initial presentation. The early detection of progressive curves can offer the opportunity to better target effective non-operative treatments, reducing the need for surgery and the risks of related complications. Predictive models for the detection of scoliosis progression in subjects before growth spurt have been developed. These models accounted for geometrical parameters of the global spine and local descriptors of the scoliotic curve, but neglected contributions from biomechanical measurements such as trunk muscle activation and intervertebral loading, which could provide advantageous information. The present study exploits a musculoskeletal model of the thoracolumbar spine, developed in AnyBody software and adapted and validated for the subject-specific characterization of mild scoliosis. A dataset of 100 AIS subjects with mild scoliosis and in pre-pubertal age at first examination, and recognized as stable (60) or progressive (40) after at least 6-months follow-up period was exploited. Anthropometrical data and geometrical parameters of the spine at first examination, as well as biomechanical parameters from musculoskeletal simulation replicating relaxed upright posture were accounted for as predictors of the scoliosis progression. Predicted height and weight were used for model scaling because not available in the original dataset. Robust procedure for obtaining such parameters from radiographic images was developed by exploiting a comparable dataset with real values. Six predictive modelling approaches based on different algorithms for the binary classification of stable and progressive cases were compared. The best fitting approaches were exploited to evaluate the effect of accounting for the biomechanical parameters on the prediction of scoliosis progression. The performance of two sets of predictors was compared: accounting for anthropometrical and geometrical parameters only; considering in addition the biomechanical ones. Median accuracy of the best fitting algorithms ranged from 0.76 to 0.78. No differences were found in the classification performance by including or neglecting the biomechanical parameters. Median sensitivity was 0.75, and that of specificity ranged from 0.75 to 0.83. In conclusion, accounting for biomechanical measures did not enhance the prediction of curve progression, thus not supporting a potential clinical application at this stage.

The Role of the Size and Location of the Tumors and of the Vertebral Anatomy in Determining the Structural Stability of the Metastatically Involved Spine: a Finite Element Study.

Vertebral fractures associated with the loss of structural integrity of neoplastic vertebrae are common, and determined to the deterioration of the bone quality in the lesion area. The prediction of the fracture risk in metastatically involved spines can guide in deciding if preventive solutions, such as medical prophylaxis, bracing, or surgery are indicated for the patient. In this study, finite element models of 22 thoracolumbar vertebrae were built based on CT scans of three spines, covering a wide spectrum of possible clinical scenarios in terms of age, bone quality and degenerative features, taking into account the local material properties of bone tissue. Simulations were performed in order to investigate the effect of the size and location of the tumoral lesion, the bone quality and the vertebral level in determining the structural stability of the neoplastic vertebrae. Tumors with random size and positions were added to the models, for a total of 660 simulations in which a compressive load was simulated. Results highlighted the fundamental role of the tumor size, whereas the other parameters had a lower, but non-negligible impact on the axial collapse of the vertebra, the vertebral bulge in the transverse plane and the canal narrowing under the application of the load. All the considered parameters are radiologically measurable, and can therefore be translated in a straightforward way to the clinical practice to support decisions about preventive treatment of metastatic fractures.

Surgical treatment of spinal disorders in Parkinson's disease.

PURPOSE: Most patients suffering from Parkinson's disease (PD) exhibit alterations in the posture, which can in several cases give rise to spine deformities, both in the sagittal and the coronal plane. In addition, degenerative disorders of the spine frequently associated to PD, such as spinal stenosis and sagittal instability, can further impact the quality of life of the patient. In recent years, spine surgery has been increasingly performed, with mixed results. The aim of this narrative review is to analyze the spinal disorders associated to PD, and the current evidence about their surgical treatment. METHODS: Narrative review. RESULTS: Camptocormia, i.e., a pronounced flexible forward bending of the trunk with 7% prevalence, is the most reported sagittal disorder of the spine. Pisa syndrome and scoliosis are both common and frequently associated. Disorders to the spinopelvic alignment were not widely investigated, but a tendency toward a lower ability of PD patients to compensate the sagittal malalignment with respect to non-PD elderly subjects with imbalance seems to emerge. Spine surgery in PD patients showed high rates of complications and re-operations. CONCLUSIONS: Disorders of the posture and spinal alignment, both in the sagittal and in the coronal planes, are common in PD patients, and have a major impact on the quality of life. Outcomes of spine surgery are generally not satisfactory, likely mostly due to muscle dystonia and poor bone quality. Knowledge in this field needs to be consolidated by further clinical and basic science studies. These slides can be retrieved under Electronic Supplementary Material.

Univariate and bivariate symbolic analyses of cardiovascular variability differentiate general anesthesia procedures.

General anesthesia attenuates autonomic function and baroreflex control. This side effect should be prevented as much as possible because it limits the subject's ability in responding to physiological challenges during surgery (e.g. arterial pressure and ventricular contractility drops). This study is designed to rank two of the most commonly exploited general anesthesia treatments, i.e. intravenous anesthesia (IA) based on a propofol-opioid combination and volatile anesthesia (VA) based on a sevoflurane-opioid combination, according to their ability to maintain autonomic nervous system activity and baroreflex control. Univariate and bivariate symbolic techniques were applied to spontaneous heart period (HP) and systolic arterial pressure (SAP) variability series recorded during IA and VA procedures in 19 and 18 patients undergoing elective intracranial neurosurgery. Traditional linear univariate and bivariate frequency domain markers of the autonomic nervous system state and baroreflex control were evaluated as well. We found that: (i) univariate symbolic analysis of HP series suggests a better preservation of vagal modulation in VA than in IA; (ii) bivariate symbolic markers assessing the degree of HP-SAP association differentiate IA from VA, while baroreflex sensitivity and squared coherence function cannot; (iii) bivariate symbolic analysis indicates a better preservation of the HP-SAP association at slow frequencies in IA than in VA, thus suggesting a more active baroreflex control in IA. We conclude that symbolic indexes can be fruitfully exploited to rank general anesthesia treatments, and their performance appears to be superior to that of more traditional linear markers.

Model-based causal closed-loop approach to the estimate of baroreflex sensitivity during propofol anesthesia in patients undergoing coronary artery bypass graft.

Cardiac baroreflex is a fundamental component of the cardiovascular control. The continuous assessment of baroreflex sensitivity (BRS) from spontaneous heart period (HP) and systolic arterial pressure (SAP) variations during general anesthesia provides relevant information about cardiovascular regulation in physiological conditions. Unfortunately, several difficulties including unknown HP-SAP causal relations, negligible SAP changes, small BRS values, and confounding influences due to mechanical ventilation prevent BRS monitoring from HP and SAP variabilities during general anesthesia. We applied a model-based causal closed-loop approach aiming at BRS assessment during propofol anesthesia in 34 patients undergoing coronary artery bypass graft (CABG) surgery. We found the following: 1) traditional time and frequency domain approaches (i.e., baroreflex sequence, cross-correlation, spectral, and transfer function techniques) exhibited irremediable methodological limitations preventing the assessment of the BRS decrease during propofol anesthesia; 2) Granger causality approach proved that the methodological caveats were linked to the decreased presence of bidirectional closed-loop HP-SAP interactions and to the increased incidence of the HP-SAP uncoupling; 3) our model-based closed-loop approach detected the significant BRS decrease during propofol anesthesia as a likely result of accounting for the influences of mechanical ventilation and causal HP-SAP interactions; and 4) the model-based closed-loop approach found also a diminished gain of the relation from HP to SAP linked to vasodilatation and reduced ventricular contractility during propofol anesthesia. The proposed model-based causal closed-loop approach is more effective than traditional approaches in monitoring cardiovascular control during propofol anesthesia and indicates an overall depression of the HP-SAP closed-loop regulation.