Search

Abstract Background Humans should sleep for about a third of their lifetime and the choice of the mattress is very important from a quality-of-life perspective. Therefore, the primary aim of this study was to assess the changes of lumbar angles, evaluated in a supine position using magnetic resonance imaging (MRI), on a mattress versus a rigid surface. Methods Twenty healthy subjects (10 females, 10 males), aged 32.3 ± 6.5 (mean ± standard deviation), with body mass index 22.4 ± 2.9, completed three evaluations: (i) spine MRI in supine position on a mattress (MAT); (ii) spine MRI in supine position on rigid surface (CON); and (iii) biplanar radiographic imaging in standing position. The following indexes were calculated for both MAT and CON: lumbar lordosis angles L1–L5, L1–S1, L5–S1, and the sacral slope (SS). Further, pelvic incidence (PI) was calculated from the biplanar radiographic images. Results Main findings were (i) L1–L5 and SS were greater in MAT than CON (L1:L5: +2.9°; SS: +2.0°); (ii) L5–S1 was lower in MAT than CON (−1.6°); (iii) L1–S1 was greater in MAT than CON only for male subjects (+2.0°); (iv) significant and positive correlations between PI and L1–L5, L1–S1 and SS were observed in both CON and MAT. Conclusions The use of a mattress determined small but statistically significant changes in lumbar angles. Relevance statement The use of a mattress determines small but statistically significant changes in radiological angles describing the sagittal alignment of the lumbar spine when lying in the supine position. Key points • Lordosis angle L1–L5 was greater in MAT than in CON condition (+2.9°). • Sacral slope was greater in MAT than in CON condition (+2.0°). • Lordosis angle L5–S1 was lower in MAT than in CON condition (−1.6°). Graphical Abstract

IntroductionA 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.MethodsT2-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.ResultsThe 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).DiscussionThe 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.

Abstract In this work we propose to use Deep Learning to automatically calculate the coordinates of the vertebral corners in sagittal x-rays images of the thoracolumbar spine and, from those landmarks, to calculate relevant radiological parameters such as L1–L5 and L1–S1 lordosis and sacral slope. For this purpose, we used 10,193 images annotated with the landmarks coordinates as the ground truth. We realized a model that consists of 2 steps. In step 1, we trained 2 Convolutional Neural Networks to identify each vertebra in the image and calculate the landmarks coordinates respectively. In step 2, we refined the localization using cropped images of a single vertebra as input to another convolutional neural network and we used geometrical transformations to map the corners to the original image. For the localization tasks, we used a differentiable spatial to numerical transform (DSNT) as the top layer. We evaluated the model both qualitatively and quantitatively on a set of 195 test images. The median localization errors relative to the vertebrae dimensions were 1.98% and 1.68% for x and y coordinates respectively. All the predicted angles were highly correlated with the ground truth, despite non-negligible absolute median errors of 1.84°, 2.43° and 1.98° for L1–L5, L1–S1 and SS respectively. Our model is able to calculate with good accuracy the coordinates of the vertebral corners and has a large potential for improving the reliability and repeatability of measurements in clinical tasks.

We developed and used a deep learning tool to process biplanar radiographs of 9,832 non-surgical patients suffering from spinal deformities, with the aim of reporting the statistical distribution of radiological parameters describing the spinal shape and the correlations and interdependencies between them. An existing tool able to automatically perform a three-dimensional reconstruction of the thoracolumbar spine has been improved and used to analyze a large set of biplanar radiographs of the trunk. For all patients, the following parameters were calculated: spinopelvic parameters; lumbar lordosis; mismatch between pelvic incidence and lumbar lordosis; thoracic kyphosis; maximal coronal Cobb angle; sagittal vertical axis; T1-pelvic angle; maximal vertebral rotation in the transverse plane. The radiological parameters describing the sagittal alignment were found to be highly interrelated with each other, as well as dependent on age, while sex had relatively minor but statistically significant importance. Lumbar lordosis was associated with thoracic kyphosis, pelvic incidence and sagittal vertical axis. The pelvic incidence-lumbar lordosis mismatch was found to be dependent on the pelvic incidence and on age. Scoliosis had a distinct association with the sagittal alignment in adolescent and adult subjects. The deep learning-based tool allowed for the analysis of a large imaging database which would not be reasonably feasible if performed by human operators. The large set of results will be valuable to trigger new research questions in the field of spinal deformities, as well as to challenge the current knowledge.

Abstract Adolescent idiopathic scoliosis is a three-dimensional deformity of the spine which is frequently corrected with the implantation of instrumentation with generally good or excellent clinical results; mechanical post-operative complications such as implant loosening and breakage are however relatively frequent. The rate of complications is associated with a lack of consensus about the surgical decision-making process; choices about the instrumentation length, the anchoring implants and the degree of correction are indeed mostly based on personal views and previous experience of the surgeon. In this work, we performed an in silico clinical trial on a large number of subjects in order to clarify which factors have the highest importance in determining the risk of complications by quantitatively analysing the mechanical stresses and loads in the instrumentation after the correction maneuvers. The results of the simulations highlighted the fundamental role of the curve severity, also in its three-dimensional aspect, and of the instrumentation strategy, whereas the length of the fixation had a lower importance.

Simplified loading conditions such as pure moments are frequently used to compare different instrumentation techniques to treat spine disorders. The purpose of this study was to determine if the use of realistic loading conditions such as muscle forces can alter the stresses in the implants with respect to pure moment loading. A musculoskeletal model and a finite element model sharing the same anatomy were built and validated against in vitro data, and coupled in order to drive the finite element model with muscle forces calculated by the musculoskeletal one for a prescribed motion. Intact conditions as well as a L1-L5 posterior fixation with pedicle screws and rods were simulated in flexion-extension and lateral bending. The hardware stresses calculated with the finite element model with instrumentation under simplified and realistic loading conditions were compared. The ROM under simplified loading conditions showed good agreement with in vitro data. As expected, the ROMs between the two types of loading conditions showed relatively small differences. Realistic loading conditions increased the stresses in the pedicle screws and in the posterior rods with respect to simplified loading conditions; an increase of hardware stresses up to 40 MPa in extension for the posterior rods and 57 MPa in flexion for the pedicle screws were observed with respect to simplified loading conditions. This conclusion can be critical for the literature since it means that previous models which used pure moments may have underestimated the stresses in the implants in flexion-extension and in lateral bending.

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.

Abstract Background Deep learning is a ground-breaking technology that is revolutionising many research and industrial fields. Generative models are recently gaining interest. Here, we investigate their potential, namely conditional generative adversarial networks, in the field of magnetic resonance imaging (MRI) of the spine, by performing clinically relevant benchmark cases. Methods First, the enhancement of the resolution of T2-weighted (T2W) images (super-resolution) was tested. Then, automated image-to-image translation was tested in the following tasks: (1) from T1-weighted to T2W images of the lumbar spine and (2) vice versa; (3) from T2W to short time inversion-recovery (STIR) images; (4) from T2W to turbo inversion recovery magnitude (TIRM) images; (5) from sagittal standing x-ray projections to T2W images. Clinical and quantitative assessments of the outputs by means of image quality metrics were performed. The training of the models was performed on MRI and x-ray images from 989 patients. Results The performance of the models was generally positive and promising, but with several limitations. The number of disc protrusions or herniations showed good concordance (κ = 0.691) between native and super-resolution images. Moderate-to-excellent concordance was found when translating T2W to STIR and TIRM images (κ ≥ 0.842 regarding disc degeneration), while the agreement was poor when translating x-ray to T2W images. Conclusions Conditional generative adversarial networks are able to generate perceptually convincing synthetic images of the spine in super-resolution and image-to-image translation tasks. Taking into account the limitations of the study, deep learning-based generative methods showed the potential to be an upcoming innovation in musculoskeletal radiology.

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.

The pathomechanisms of curve progression in adolescent idiopathic scoliosis (AIS) remain poorly understood and biomechanical data are limited. A deeper insight into spinal loading could provide valuable information toward the improvement of current treatment strategies. This work therefore aimed at using subject-specific musculoskeletal full-body models of patients with AIS to predict segmental compressive forces around the curve apex and to investigate how these forces are affected by simulated load carrying. Models were created based on spatially calibrated biplanar radiographic images from 24 patients with mild to moderate AIS and validated by comparing predictions of paravertebral muscle activity with reported values from in vivo studies. Spinal compressive forces were predicted during unloaded upright standing as well as standing with external loads of 10, 15, and 20% of body weight (BW) applied to the scapulae to simulate carrying a backpack in the regular way on the back as well as in front of the body and over the shoulder on the concave and convex sides of the scoliotic curve. The predicted muscle activities around the curve apex were higher on the convex side for the erector spinae (ES) and multifidi (MF) muscles, which was comparable to the EMG-based in vivo measurements from the literature. In terms of spinal loading, the implementation of spinal deformity resulted in a 10% increase of compressive force at the curve apex during unloaded upright standing. Apical compressive forces further increased by 50–62% for a simulated 10% BW load and by 77–94% and 103–128% for 15% and 20% BW loads, respectively. Moreover, load-dependent compressive force increases were the lowest in the regular backpack and the highest in the frontpack and convex conditions, with concave side-carrying forces in between. The predictions indicated increased segmental compressive forces during unloaded upright standing, which could be ascribed to the scoliotic deformation. When carrying loads, compressive forces further increased depending on the carrying mode and the weight of the load. These results can be used as a basis for further studies investigating segmental loading in AIS patients during functional activities. Models can thereby be created using the same approach as proposed in this study.

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer‐aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content‐based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.

Still little is known about how spinopelvic alignment affects spinal load distribution. Musculoskeletal modeling can potentially help to discover associations between spine alignment and risk factors of spinal disorders (e.g. disc herniation, vertebral fracture, spondylolisthesis, low back pain). The present study exploited the AnyBody full-body musculoskeletal model to assess the relation between lumbar loads and spinopelvic alignment in the sagittal plane. The model was evaluated in the standing position. The simulated postures were set using spinopelvic parameters gleaned from the literature and characterizing the healthy adult population. The parameters were: sagittal vertical axis, Roussouly lumbar type, sacral slope, and pelvic incidence. A total of 2772 configurations were simulated based on the following measurements: compression force and anterior shear at levels L4L5 and L5S1; multifidus, longissimus spinae, and rectus abdominis muscle forces. Changes in global sagittal alignment, lumbar typology, and sacral inclination, but not in pelvic incidence, were found to affect intervertebral loads in the lumbar spine and spinal muscle activation. Considering these changes would be advantageous for clinical evaluation, due to the recognized relation between altered loads and risk of disc herniation, vertebral fracture, spondylolisthesis, and low back pain. Musculoskeletal modeling proved to be a valuable biomechanical tool to non-invasively investigate the relation between internal loads and anatomical parameters.

In silico trials recently emerged as a disruptive technology, which may reduce the costs related to the development and marketing approval of novel medical technologies, as well as shortening their time-to-market. In these trials, virtual patients are recruited from a large database and their response to the therapy, such as the implantation of a medical device, is simulated by means of numerical models. In this work, we propose the use of generative adversarial networks to produce synthetic radiological images to be used in in silico trials. The generative models produced credible synthetic sagittal X-rays of the lumbar spine based on a simple sketch, and were able to generate sagittal radiological images of the trunk using coronal projections as inputs, and vice versa. Although numerous inaccuracies in the anatomical details may still allow distinguishing synthetic and real images in the majority of cases, the present work showed that generative models are a feasible solution for creating synthetic imaging data to be used in in silico trials of novel medical devices.

From its first appearance in early vertebrates, the spine evolved the function of protecting the spinal cord, avoiding excessive straining during body motion. Its stiffness and strength provided the basis for the development of the axial skeleton as the mechanical support of later animals, especially those which moved to the terrestrial environment where gravity loads are not alleviated by the buoyant force of water. In tetrapods, the functions of the spine can be summarized as follows: protecting the spinal cord; supporting the weight of the body, transmitting it to the ground through the limbs; allowing the motion of the trunk, through to its flexibility; providing robust origins and insertions to the muscles of trunk and limbs. This narrative review provides a brief perspective on the development of the spine in vertebrates, first from an evolutionary, and then from an embryological point of view. The paper describes functions and the shape of the spine throughout the whole evolution of vertebrates and vertebrate embryos, from primordial jawless fish to extant animals such as birds and humans, highlighting its fundamental features such as strength, stability, and flexibility, which gives it huge potential as a basis for bio-inspired technologies.

The proposed approach evaluates complexity of the cardiovascular control and causality among cardiovascular regulatory mechanisms from spontaneous variability of heart period (HP), systolic arterial pressure (SAP) and respiration (RESP). It relies on construction of a multivariate embedding space, optimization of the embedding dimension and a procedure allowing the selection of the components most suitable to form the multivariate embedding space. Moreover, it allows the comparison between linear model-based (MB) and nonlinear model-free (MF) techniques and between MF approaches exploiting local predictability (LP) and conditional entropy (CE). The framework was applied to study age-related modifications of complexity and causality in healthy humans in supine resting (REST) and during standing (STAND). We found that: 1) MF approaches are more efficient than the MB method when nonlinear components are present, while the reverse situation holds in presence of high dimensional embedding spaces; 2) the CE method is the least powerful in detecting age-related trends; 3) the association of HP complexity on age suggests an impairment of cardiac regulation and response to STAND; 4) the relation of SAP complexity on age indicates a gradual increase of sympathetic activity and a reduced responsiveness of vasomotor control to STAND; 5) the association from SAP to HP on age during STAND reveals a progressive inefficiency of baroreflex; 6) the reduced connection from HP to SAP with age might be linked to the progressive exploitation of Frank-Starling mechanism at REST and to the progressive increase of peripheral resistances during STAND; 7) at REST the diminished association from RESP to HP with age suggests a vagal withdrawal and a gradual uncoupling between respiratory activity and heart; 8) the weakened connection from RESP to SAP with age might be related to the progressive increase of left ventricular thickness and vascular stiffness and to the gradual decrease of respiratory sinus arrhythmia.

The study assesses complexity of the cardiac control directed to the sinus node and to ventricles in long QT syndrome type 1 (LQT1) patients with KCNQ1-A341V mutation. Complexity was assessed via refined multiscale entropy (RMSE) computed over the beat-to-beat variability series of heart period (HP) and QT interval. HP and QT interval were approximated respectively as the temporal distance between two consecutive R-wave peaks and between the R-wave apex and T-wave end. Both measures were automatically taken from 24-hour electrocardiographic Holter traces recorded during daily activities in non mutation carriers (NMCs, n = 14) and mutation carriers (MCs, n = 34) belonging to a South African LQT1 founder population. The MC group was divided into asymptomatic (ASYMP, n = 11) and symptomatic (SYMP, n = 23) patients according to the symptom severity. Analyses were carried out during daytime (DAY, from 2PM to 6PM) and nighttime (NIGHT, from 12PM to 4AM) off and on beta-adrenergic blockade (BBoff and BBon). We found that the complexity of the HP variability at short time scale was under vagal control, being significantly increased during NIGHT and BBon both in ASYMP and SYMP groups, while the complexity of both HP and QT variability at long time scales was under sympathetic control, being smaller during NIGHT and BBon in SYMP subjects. Complexity indexes at long time scales in ASYMP individuals were smaller than those in SYMP ones regardless of therapy (i.e. BBoff or BBon), thus suggesting that a reduced complexity of the sympathetic regulation is protective in ASYMP individuals. RMSE analysis of HP and QT interval variability derived from routine 24-hour electrocardiographic Holter recordings might provide additional insights into the physiology of the cardiac control and might be fruitfully exploited to improve risk stratification in LQT1 population.

The autonomic regulation is non-invasively estimated from heart rate variability (HRV). Many methods utilized to assess autonomic regulation require stationarity of HRV recordings. However, non-stationarities are frequently present even during well-controlled experiments, thus potentially biasing HRV indices. The aim of our study is to quantify the potential bias of spectral, symbolic and entropy HRV indices due to non-stationarities. We analyzed HRV series recorded in healthy subjects during uncontrolled daily life activities typical of 24 h Holter recordings and during predetermined levels of robotic-assisted treadmill-based physical exercise. A stationarity test checking the stability of the mean and variance over short HRV series (about 300 cardiac beats) was utilized to distinguish stationary periods from non-stationary ones. Spectral, symbolic and entropy indices evaluated solely over stationary periods were contrasted with those derived from all the HRV segments. When indices were calculated solely over stationary series, we found that (i) during both uncontrolled daily life activities and controlled physical exercise, the entropy-based complexity indices were significantly larger; (ii) during uncontrolled daily life activities, the spectral and symbolic indices linked to sympathetic modulation were significantly smaller and those associated with vagal modulation were significantly larger; (iii) while during uncontrolled daily life activities, the variance of spectral, symbolic and entropy rate indices was significantly larger, during controlled physical exercise, it was smaller. The study suggests that non-stationarities increase the likelihood to overestimate the contribution of sympathetic control and affect the power of statistical tests utilized to discriminate conditions and/or groups. [ABSTRACT FROM AUTHOR]