Automated Pipeline to Generate Anatomically Accurate Patient-Specific Biomechanical Models of Healthy and Pathological FSUs

Abstract

State-of-the-art preoperative biomechanical analysis for the planning of spinal surgery not only requires the generation of three-dimensional patient-specific models but also the accurate biomechanical representation of vertebral joints. The benefits offered by computational models suitable for such purposes are still outweighed by the time and effort required for their generation, thus compromising their applicability in a clinical environment. In this work, we aim to ease the integration of computerized methods into patient-specific planning of spinal surgery. We present the first pipeline combining deep learning and finite element methods that allows a completely automated model generation of functional spine units (FSUs) of the lumbar spine for patient-specific FE simulations (FEBio). The pipeline consists of three steps: (a) multiclass segmentation of cropped 3D CT images containing lumbar vertebrae using the DenseVNet network, (b) automatic landmark-based mesh fitting of statistical shape models onto 3D semantic segmented meshes of the vertebral models, and (c) automatic generation of patient-specific FE models of lumbar segments for the simulation of flexion-extension, lateral bending, and axial rotation movements. The automatic segmentation of FSUs was evaluated against the gold standard (manual segmentation) using 10-fold cross-validation. The obtained Dice coefficient was 93.7% on average, with a mean surface distance of 0.88 mm and a mean Hausdorff distance of 11.16 mm (N = 150). Automatic generation of finite element models to simulate the range of motion (ROM) was successfully performed for five healthy and five pathological FSUs. The results of the simulations were evaluated against the literature and showed comparable ROMs in both healthy and pathological cases, including the alteration of ROM typically observed in severely degenerated FSUs. The major intent of this work is to automate the creation of anatomically accurate patient-specific models by a single pipeline allowing functional modeling of spinal motion in healthy and pathological FSUs. Our approach reduces manual efforts to a minimum and the execution of the entire pipeline including simulations takes approximately 2 h. The automation, time-efficiency and robustness level of the pipeline represents a first step toward its clinical integration.

A novel approach for tetrahedral-element-based finite element simulations of anisotropic hyperelastic intervertebral disc behavior

“…The 3D geometrical mesh information of individual bony structures (i.e., cranial and caudal vertebra of each segment) was obtained from manual segmentation of CT images (Philips Brilliance 64, Philips Healthcare, Cleveland, OH, United States) using the 3D Slicer (V4.8.1) ( 3D Slicer, 2021 ; Fedorov et al, 2012 ) software ( Figure 1 ). Statistical shape models were transformed onto this outcome by utilizing specific landmarks and invoking a non-rigid registration approach ( Caprara et al, 2021 ). This information was then utilized in conjunction with custom-made scripts in MATLAB ® (The MathWorks Inc., Natick, MA, United States) to generate the 3D geometry of the enclosed IVD.…”

“…Various image-processing-based methods are in use to generate FE models for spinal segments. These approaches use computed tomography (CT) images of vertebrae ( Moramarco et al, 2010 ; del Palomar et al, 2008 ; Rohlmann et al, 2007 ; Eberlein et al, 2004 ; Schmidt et al, 2006 ; Pickering et al, 2021 ; Jaramillo et al, 2015 ) and magnetic resonance imaging (MRI) scans of IVDs ( Maquer et al, 2015 , 2014 ), including those based on automatic segmentation ( Caprara et al, 2021 ). Hexahedral elements (HE) often feature in the subsequent discretization of the resulting geometry, in particular of healthy IVDs ( Eberlein et al, 2001 , 2004 ; Jaramillo et al, 2015 ; Moramarco et al, 2010 ; Rohlmann et al, 2007 ; Pickering et al, 2021 ; Baroud et al, 2003 ; Schmidt et al, 2006 , 2007b , a ; Zander et al, 2009 , 2017 ; Cegoñino et al, 2014 ).…”

Statistical Shape and Appearance Models: Development Towards Improved Osteoporosis Care

“…One of the applications of SSAMs that is increasingly popular is FE analysis. SSAM-based FE models could be aimed at, e.g., predicting subject-specific bone strength from clinical images [21,28,30,31], evaluating the efficacy of treatment [11], investigating the effect of femoral anatomy on its strength [29], estimating range of motions [26], and providing augmented information to clinical images [16,17].…”

“…Another trend that can be observed, thanks to the increasing computational power, is to adopt SSAMs to perform only small parts of an FE modeling pipeline. For example, PCs can be further used for supervised learning aimed at obtaining shape regression [27], or the SSM can be fitted to an automatic segmentation to obtain isotopological meshes for all samples, with benefits of, e.g., applying consistent boundary conditions [26].…”

Validation of a Patient-Specific Musculoskeletal Model for Lumbar Load Estimation Generated by an Automated Pipeline From Whole Body CT

“…To this date, automated approaches for modeling from medical imaging are rare in the literature. In 2021, Caprara et al introduced the first automated pipeline for the generation of patient-specific finite element models of the functional spine unit using a combination of deep learning, statistical, and FE methods on 3D CT scans ( Caprara et al, 2021 ). To the best of our knowledge, a similar approach for multi-body modeling does not exist in the literature.…”