Prediction outcomes for anterior vertebral body growth modulation surgery from discriminant spatiotemporal manifolds

Predicting radiographic outcomes of vertebral body tethering in adolescent idiopathic scoliosis patients using machine learning

Anterior Vertebral Body Tethering (AVBT) is a growing alternative treatment for adolescent idiopathic scoliosis (AIS), offering an option besides spinal fusion. While AVBT aims to correct spinal deformity through growth correction, its outcomes have been mixed. To improve surgical outcomes, this study aimed to develop a machine learning-based tool to predict short- and midterm spinal curve correction in AIS patients who underwent AVBT surgery, using the most predictive clinical, radiographic, and surgical parameters. After institutional review board approval and based on inclusion criteria, 91 AIS patients who underwent AVBT surgery were selected from the Shriners Hospitals for Children, Philadelphia. For all patients, longitudinal standing (PA or AP, and lateral) and side bending spinal Radiographs were retrospectively obtained at six visits: preop and first standing, one year, two years, five years postop, and at the most recent follow-up. Demographic, radiographic, and surgical features associated with curve correction were collected. The sequential backward feature selection method was used to eliminate correlated features and to provide a rank-ordered list of the most predictive features of the AVBT correction. A Gradient Boosting Regressor (GBR) model was trained and tested using the selected features to predict the final correction of the curve in AIS patients. Eleven most predictive features were identified. The GBR model predicted the final Cobb angle with an average error of 6.3 ± 5.6 degrees. The model also provided a prediction interval, where 84% of the actual values were within the 90% prediction interval. A list of the most predictive features for AVBT curve correction was provided. The GBR model, trained on these features, predicted the final curve magnitude with a clinically acceptable margin of error. This model can be used as a clinical tool to plan AVBT surgical parameters and improve outcomes.

Patient-specific finite element modeling of scoliotic curve progression using region-specific stress-modulated vertebral growth

PURPOSE

This study describes the creation of patient-specific (PS) osteo-ligamentous finite element (FE) models of the spine, ribcage, and pelvis, simulation of up to three years of region-specific, stress-modulated growth, and validation of simulated curve progression with patient clinical angle measurements.

RESEARCH QUESTION

Does the inclusion of region-specific, stress-modulated vertebral growth, in addition to scaling based on age, weight, skeletal maturity, and spine flexibility allow for clinically accurate scoliotic curve progression prediction in patient-specific FE models of the spine, ribcage, and pelvis?

METHODS

Frontal, lateral, and lateral bending X-Rays of five AIS patients were obtained for approximately three-year timespans. PS-FE models were generated by morphing a normative template FE model with landmark points obtained from patient X-rays at the initial X-ray timepoint. Vertebral growth behavior and response to stress, as well as model material properties were made patient-specific based on several prognostic factors. Spine curvature angles from the PS-FE models were compared to the corresponding X-ray measurements.

RESULTS

Average FE model errors were 6.3 ± 4.6°, 12.2 ± 6.6°, 8.9 ± 7.7°, and 5.3 ± 3.4° for thoracic Cobb, lumbar Cobb, kyphosis, and lordosis angles, respectively. Average error in prediction of vertebral wedging at the apex and adjacent levels was 3.2 ± 2.2°. Vertebral column stress ranged from 0.11 MPa in tension to 0.79 MPa in compression.

CONCLUSION

Integration of region-specific stress-modulated growth, as well as adjustment of growth and material properties based on patient-specific data yielded clinically useful prediction accuracy while maintaining physiological stress magnitudes. This framework can be further developed for PS surgical simulation.

Development of a Finite Element Model of the Pediatric Thoracic and Lumbar Spine, Ribcage, and Pelvis with Orthotropic Region-Specific Vertebral Growth

Finite element (FE) modeling of the spine has increasingly been applied in orthopedic precision-medicine approaches. Previously published FE models of the pediatric spine growth have made simplifications in geometry of anatomical structures, material properties, and representation of vertebral growth. To address those limitations, a comprehensive FE model of a pediatric (10-year-old) osteo-ligamentous thoracic and lumbar spine (T1-L5 with intervertebral discs (IVDs) and ligaments), ribcage, and pelvis with age- and level-specific ligament properties and orthotropic region-specific vertebral growth was developed and validated. Range of motion (ROM) measures, namely lateral bending, flexion-extension, and axial rotation, of the current 10 YO FE model were generally within reported ranges of scaled in vitro adult ROM data. Changes in T1-L5 spine height, as well as kyphosis (T2-T12) and lordosis (L1-L5) angles in the current FE model for two years of growth (from ages 10 to 12 years) were within ranges reported from corresponding pediatric clinical data. The use of such comprehensive pediatric FE models can provide clinically relevant insights into normative and pathological biomechanical responses of the spine, and also contribute to the development and optimization of clinical interventions for spine deformities.

Prediction of post transarterial chemoembolization MR images of hepatocellular carcinoma using spatio-temporal graph convolutional networks

Magnetic resonance imaging (MRI) plays a critical role in the planning and monitoring of hepatocellular carcinomas (HCC) treated with locoregional therapies, in order to assess disease progression or recurrence. Dynamic contrast-enhanced (DCE)-MRI sequences offer temporal data on tumor enhancement characteristics which has strong prognostic value. Yet, predicting follow-up DCE-MR images from which tumor enhancement and viability can be measured, before treatment of HCC actually begins, remains an unsolved problem given the complexity of spatial and temporal information. We propose an approach to predict future DCE-MRI examinations following transarterial chemoembolization (TACE) by learning the spatio-temporal features related to HCC response from pre-TACE images. A novel Spatial-Temporal Discriminant Graph Neural Network (STDGNN) based on graph convolutional networks is presented. First, embeddings of viable, equivocal and non-viable HCCs are separated within a joint low-dimensional latent space, which is created using a discriminant neural network representing tumor-specific features. Spatial tumoral features from independent MRI volumes are then extracted with a structural branch, while dynamic features are extracted from the multi-phase sequence with a separate temporal branch. The model extracts spatio-temporal features by a joint minimization of the network branches. At testing, a pre-TACE diagnostic DCE-MRI is embedded on the discriminant spatio-temporal latent space, which is then translated to the follow-up domain space, thus allowing to predict the post-TACE DCE-MRI describing HCC treatment response. A dataset of 366 HCC's from liver cancer patients was used to train and test the model using DCE-MRI examinations with associated pathological outcomes, with the spatio-temporal framework yielding 93.5% classification accuracy in response identification, and generating follow-up images yielding insignificant differences in perfusion parameters compared to ground-truth post-TACE examinations.

Intra-operative forecasting of growth modulation spine surgery outcomes with spatio-temporal dynamic networks

PURPOSE

In adolescent idiopathic scoliosis (AIS), non-invasive surgical techniques such as anterior vertebral body tethering (AVBT) enable to treat patients with mild and severe degrees of deformity while maintaining lower lumbar motion by avoiding spinal fusion. However, multiple features and characteristics affect the overall patient outcome, notably the 3D spine geometry and bone maturity, but also from decisions taken intra-operatively such as the selected tethered vertebral levels, which makes it difficult to anticipate the patient response.

METHODS

We propose here a forecasting method which can be used during AVBT surgery, exploiting the spatio-temporal features extracted from a dynamic networks. The model learns the corrective effect from the spine's different segments while taking under account the time differences in the initial diagnosis and between the serial acquisitions taken before and during surgery. Clinical parameters are integrated through an attention-based decoder, allowing to associate geometrical features to patient status. Long-term relationships allow to ensure regularity in geometrical curve prediction, using a manifold-based smoothness term to regularize geometrical outputs, capturing the temporal variations of spine correction.

RESULTS

A dataset of 695 3D spine reconstructions was used to train the network, which was evaluated on a hold-out dataset of 72 scoliosis patients using the baseline 3D reconstruction obtained prior to surgery, yielding an overall reconstruction error of [Formula: see text]mm based on pre-identified landmarks on vertebral bodies. The model was also tested prospectively on a separate cohort of 15 AIS patients, demonstrating the integration within the OR theatre.

CONCLUSION

The proposed predictive network allows to intra-operatively anticipate the geometrical response of the spine to AVBT procedures using the dynamic features.

Image-Guided Tethering Spine Surgery With Outcome Prediction Using Spatio-Temporal Dynamic Networks

Recent fusionless surgical techniques for corrective spine surgery such as Anterior Vertebral Body Growth Modulation (AVBGM) allow to treat mild to severe spinal deformations by tethering vertebral bodies together, helping to preserve lower back flexibility. Forecasting the outcome of AVBGM from skeletally immature patients remains elusive with several factors involved in corrective vertebral tethering, but could help orthopaedic surgeons plan and tailor AVBGM procedures prior to surgery. We introduce an intra-operative framework forecasting the outcomes during AVBGM surgery in scoliosis patients. The method is based on spatial-temporal corrective networks, which learns the similarity in segmental corrections between patients and integrates a long-term shifting mechanism designed to cope with timing differences in onset to surgery dates, between patients in the training set. The model captures dynamic geometric dependencies in scoliosis patients, ensuring long-term dependency with temporal dynamics in curve evolution and integrated features from inter-vertebral disks extracted from T2-w MRI. The loss function of the network introduces a regularization term based on learned group-average piecewise-geodesic path to ensure the generated corrective transformations are coherent with regards to the observed evolution of spine corrections at follow-up exams. The network was trained on 695 3D spine models and tested on 72 operative patients using a set of 3D spine reconstructions as inputs. The spatio-temporal network predicted outputs with errors of 1.8 ± 0.8mm in 3D anatomical landmarks, yielding geometries similar to ground-truth spine reconstructions obtained at one and two year follow-ups and with significant improvements to comparative deep learning and biomechanical models.