Periodic Reporting for period 1 - iBack-epic (Biomechanical modelling and computational imaging to identify different causes of back pain in large epidemiological studies)
Periodo di rendicontazione: 2022-05-01 al 2024-10-31
Chronic back pain is a major burden and source of disability worldwide. It is primarily attributed to different biomechanical factors, but can also have inflammatory, neurological or psychological causes. Clinical findings and conventional imaging alone cannot reliably distinguish different causes of back pain. In contrast, individual biomechanical models can quantify diverse (pathologic) loading patterns and thus could be used to distinguish different aetiologies of back pain, to better understand individual pathophysiology and guide preventive strategies.
During my recent ERC-StG iBack, I developed quantitative imaging methods and deep-learning based image processing to automatically generate a fully individualised biomechanical model of the thoracolumbar spine. Simultaneously, two large-scale epidemiologic studies collected clinical and high-resolution imaging data of the spine of more than 15,000 participants to date, aiming at more than 35,000 participants by mid 2022.
The high-level objective of iBack-epic is to use such novel image analysis techniques to identify different biomechanical and inflammatory causes of back pain in study participants.
I will adopt and extend my recently developed deep-learning based spine labelling and segmentation algorithms to fully automatically calculate individual biomechanical, functional and morphometric parameters of the spine. In this large-scale population data, I will identify different biomechanical loading patterns, use quantitative image-based parameters to discriminate normal ageing from pathologic degeneration, and identify pathological conditions that are linked to back pain or subsequent development of chronic back pain.
Such a differentiation – for the first time based on quantitative image data – will allow for a better understanding of the underlying pathophysiology of back pain, an improved risk stratification, a tailored investigation of genetic causes and thus will help to better guide preventive strategies.
During my recent ERC-StG iBack, I developed quantitative imaging methods and deep-learning based image processing to automatically generate a fully individualised biomechanical model of the thoracolumbar spine. Simultaneously, two large-scale epidemiologic studies collected clinical and high-resolution imaging data of the spine of more than 15,000 participants to date, aiming at more than 35,000 participants by mid 2022.
The high-level objective of iBack-epic is to use such novel image analysis techniques to identify different biomechanical and inflammatory causes of back pain in study participants.
I will adopt and extend my recently developed deep-learning based spine labelling and segmentation algorithms to fully automatically calculate individual biomechanical, functional and morphometric parameters of the spine. In this large-scale population data, I will identify different biomechanical loading patterns, use quantitative image-based parameters to discriminate normal ageing from pathologic degeneration, and identify pathological conditions that are linked to back pain or subsequent development of chronic back pain.
Such a differentiation – for the first time based on quantitative image data – will allow for a better understanding of the underlying pathophysiology of back pain, an improved risk stratification, a tailored investigation of genetic causes and thus will help to better guide preventive strategies.
On the biomechanical side, we have conducted a series of tasks and research efforts aimed at advancing the understanding and modeling of spinal biomechanics through patient-specific musculoskeletal models and finite element models (FEM). Our primary objective was to validate an automatically generated patient-specific musculoskeletal model of the spine, which simulates static loading tasks using CT and MRI imaging data and a deep learning-based segmentation pipeline. We found that our model's results closely correlated with in vivo data from the literature, indicating that our process is suitable for systematic investigation of spinal biomechanics in large datasets. We also investigated the effects of different degrees of individualization on observed effects of morphological characteristics on lumbar loads by creating 279 models from CT data of 93 patients. We discovered that while significant effects of morphological parameters on lumbar loads were identified, the strength of these effects decreased with the inclusion of more individual characteristics. Further, we compared different methods for fiber reinforcement in the annulus fibrosus of a human intervertebral disc model, finding that the Holzapfel-Gasser-Ogden (HGO) model provided the highest accuracy in simulations.
To streamline the modeling process, we developed an automated pipeline for biomechanical simulations of vertebrae and intervertebral discs, using automated MRI segmentations. This pipeline successfully generated and simulated patient-specific models with high bio-fidelity, robustness, and time-efficiency. Our conference contributions included a pipeline for the automated generation of individualized musculoskeletal spine models, highlighting differences in spinal loading related to curvature in large patient cohorts. We also explored the role of spinal muscles in lumbar loads during static loading tasks and conducted a multivariant analysis on the effects of six morphological parameters on lumbar loading, identifying significant correlations with considerable variability yet to be explained.
In computer vision, we addressed the challenge of accurately delineating posterior spine structures in MRI. We translated T1-weighted and T2-weighted images into CT images from 263 pairs of CT/MR series using landmark-based registration. We compared various 2D and 3D image translation methods, including Pix2Pix and DDIM, evaluating the results with peak signal-to-noise ratio and Dice similarity coefficients. A publicly available segmentation network was used to segment the synthesized CT datasets. Based on this work, we developed SPINEPS, an open-source deep learning segmentation framework designed to accurately segment 14 essential spine structures in T2-weighted MRI scans. Our approach involved training two models using a combination of CT and T2-weighted segmentations on datasets including 218 subjects from the SPIDER dataset and 1,449 subjects from the German National Cohort. We also generated synthetic sagittal T1-weighted fast spin echo (T1w FSE) and short tau inversion recovery (STIR) images from sagittal T2-weighted (T2w) FSE and axial T1w gradient echo Dixon sequences. Using datasets from the Study of Health in Pomerania (SHIP), the German National Cohort (NAKO), and an internal dataset, we employed 3D Pix2Pix deep learning models to enhance image quality. Additionally, we proposed an unpaired inpainting superresolution algorithm to address the limitations of anisotropic 2D axial or sagittal spine MRI images. By generating synthetic training pairs and modeling various MR acquisition challenges, we trained diffusion-based superresolution models, enabling the separation of individual vertebrae instances and improving automatic segmentation. Finally, we compared different methods for identifying the thoracolumbar junction, evaluating rib-based assessments against vertebral shape-based classifications. In addition, we developed a full-body tissue and organ segmentation model based on T1-w gradient echo Dixon images.
This gives us the possibility to reliably assess 30k spines in NAKO as well as 6k spines in SHIP in a highly reliable fashion. It will be the basis for our biomechanical analysis as well as an image-based analysis of back pain in the NAKO cohort. We also implemented first methods of feature analysis, including spinal fracture detection and analysis of intervertebral disc geometry and degeneration.
To streamline the modeling process, we developed an automated pipeline for biomechanical simulations of vertebrae and intervertebral discs, using automated MRI segmentations. This pipeline successfully generated and simulated patient-specific models with high bio-fidelity, robustness, and time-efficiency. Our conference contributions included a pipeline for the automated generation of individualized musculoskeletal spine models, highlighting differences in spinal loading related to curvature in large patient cohorts. We also explored the role of spinal muscles in lumbar loads during static loading tasks and conducted a multivariant analysis on the effects of six morphological parameters on lumbar loading, identifying significant correlations with considerable variability yet to be explained.
In computer vision, we addressed the challenge of accurately delineating posterior spine structures in MRI. We translated T1-weighted and T2-weighted images into CT images from 263 pairs of CT/MR series using landmark-based registration. We compared various 2D and 3D image translation methods, including Pix2Pix and DDIM, evaluating the results with peak signal-to-noise ratio and Dice similarity coefficients. A publicly available segmentation network was used to segment the synthesized CT datasets. Based on this work, we developed SPINEPS, an open-source deep learning segmentation framework designed to accurately segment 14 essential spine structures in T2-weighted MRI scans. Our approach involved training two models using a combination of CT and T2-weighted segmentations on datasets including 218 subjects from the SPIDER dataset and 1,449 subjects from the German National Cohort. We also generated synthetic sagittal T1-weighted fast spin echo (T1w FSE) and short tau inversion recovery (STIR) images from sagittal T2-weighted (T2w) FSE and axial T1w gradient echo Dixon sequences. Using datasets from the Study of Health in Pomerania (SHIP), the German National Cohort (NAKO), and an internal dataset, we employed 3D Pix2Pix deep learning models to enhance image quality. Additionally, we proposed an unpaired inpainting superresolution algorithm to address the limitations of anisotropic 2D axial or sagittal spine MRI images. By generating synthetic training pairs and modeling various MR acquisition challenges, we trained diffusion-based superresolution models, enabling the separation of individual vertebrae instances and improving automatic segmentation. Finally, we compared different methods for identifying the thoracolumbar junction, evaluating rib-based assessments against vertebral shape-based classifications. In addition, we developed a full-body tissue and organ segmentation model based on T1-w gradient echo Dixon images.
This gives us the possibility to reliably assess 30k spines in NAKO as well as 6k spines in SHIP in a highly reliable fashion. It will be the basis for our biomechanical analysis as well as an image-based analysis of back pain in the NAKO cohort. We also implemented first methods of feature analysis, including spinal fracture detection and analysis of intervertebral disc geometry and degeneration.
Overall, our biomechanical efforts underscore a significant advancement in automated, patient-specific modeling and the understanding of the biomechanics of the spine. We currently convert our MBS models from SIMPAC to OPENSIM; this will allow for biomechanics modeling in the complete NAKO dataset. Regarding Finite Element Modelling in the spine, we currently aim to include a specific model for degenerated discs.
We successfully trained several machine learning models to structure and assess the spine and soft tissues in the NAKO dataset. We are now able to segment the body tissues, organs and the spine in all subjects reliably, identify anomalies of the spine and automatically transfer the segmented anatomy to our biomechanical models.
We successfully trained several machine learning models to structure and assess the spine and soft tissues in the NAKO dataset. We are now able to segment the body tissues, organs and the spine in all subjects reliably, identify anomalies of the spine and automatically transfer the segmented anatomy to our biomechanical models.