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

Mandel, William J.; Turcot, Olivier; Knez, Dejan; Parent, Stefan; Kadoury, Samuel

doi:10.1007/s11548-019-02041-w

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we compared the predictive performance with 4 recent future image prediction methods, namely GenSeg [ 23 ], ST-ResNet [ 38 ], ST-Manifold [ 39 ] and contrastive unpaired translation (CUT [ 40 ]). The choice of these methods was made based on their ability to generate future temporal images.…”

Section: Resultsmentioning

confidence: 99%

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, anatomically complete FE models of progressive AIS can serve as a foundation for testing growth-modulation devices, as current human cadaveric spines or surrogates cannot mimic the growth patterns and biomechanical responses observed in children and adolescents, as well as to do so with large animal models used for device testing [ 24 , 62 , 63 ]. In a broader sense, predictive biomechanical models such as that developed in the current study can contribute to advancements in precision medicine and optimized clinical outcomes [ 64 ].…”

Section: Discussionmentioning

confidence: 99%

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

2023

View full text Add to dashboard Cite

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.

show abstract

“…Mandel et al developed a 3D reconstruction computer model helping to answer this question with equal results to existing biomechanical models. 10 Newton et al in a retrospective look into anterior spinal growth tethering (ASGT) in patients with skeletally immature thoracic scoliosis found out that scoliosis could be corrected while maintaining spinal flexibility and natural growth of the spine. This is a promising alternative technique compared to a rigid fixation for the skeletally immature spine.11 Scoliosis vertebral growth plate histomorphometry was studied by Bylski-Austrow et al helping us to understand better the bio mechanics of the curve.…”

Section: Discussionmentioning

confidence: 99%

Role of growth modulation in the management of idiopathic scoliosis: A narrative review of literature

Prabhavi,

Amarasekera

2022

sljo-j-tsljos

View full text Add to dashboard Cite

Scoliosis is a condition in which there is a lateral curve to the spine. The cause of scoliosis is unknown, but different aetiologies have been suggested, but mostly cause has been idiopathic in nature. Muscle spasms, cerebral palsy, Marfan syndrome, and tumours (neurofibromatosis) are some of the suggested aetiologies. Progressive adolescent idiopathic scoliosis (AIS) affects mainly girls and anterior spinal overgrowth during the second growth spurt appear to be a significant cause. The diagnosis of scoliosis is primarily a clinical suspicion followed by an AP and lateral X ray of spine in standing position. Measurement of the Cobb angle is the standard method of assessing the curvature in a quantitative manner. It is the angle between two lines, drawn perpendicular to the upper endplate of the first vertebra involved and the lower endplate of the last vertebra involved. Cobb angles are followed for both curves for those with two curves. Risser classification grades the skeletal maturity on X rays and is considered along with the Cobb angle to making a decision towards surgery. Indications for surgical correction of scoliosis is not clearly defined however, the treatment of scoliosis is based on the severity and progressive nature of the curve. Cobb angle above 40 degrees, rapidly progressing curve, major thoracic deformity affecting the function such as breathing and cosmetic reasons, are some of the indications for surgery. There are several modalities of surgical correction. Main method has been correction of the deformity and fixation with one or two rods and pedicle screws followed by bone grafting. Harrington rods were the primarily used system, but with time many spinal instrumentation systems and rods have been introduced to the market. Apart from using rods some have tried anterior vertebral body stapling and anterior vertebral body tethering for correction scoliosis using the principle of growth modulation. We conducted a systematic review to answer the question, 'What is the role of growth modulation in the management of idiopathic scoliosis?' All articles / publications published from 2010 May to 2019 October were used as research data. A health, related database (PubMed) was used for the search. Search criteria revealed 99 articles initially and 37 articles after filtered based on title reading. Then 18 articles were selected for the final analysis after being filtered manually by reading summary and abstracts of each article.

show abstract

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

Cited by 8 publications

References 14 publications

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

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

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

Role of growth modulation in the management of idiopathic scoliosis: A narrative review of literature

Contact Info

Product

Resources

About