SynSpine: an automated workflow for the generation of longitudinal spinal cord synthetic MRI data

Marco Ganzetti^1*Paola Valsasina²Frederik Barkhof^3,4Maria Assunta Rocca^2,5Massimo Filippi^5,6Ferran Prados^7,8Licinio Craveiro^1*

• ¹F Hoffmann-La Roche AG, Basel, Switzerland
• ²Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy
• ³Queen Square Institute of Neurology, University College London, London, United Kingdom
• ⁴Department of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, Amsterdam, Netherlands
• ⁵Universita Vita Salute San Raffaele, Milan, Italy
• ⁶Department of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy
• ⁷UCL Hawkes Institute, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
• ⁸Universitat Oberta de Catalunya, Barcelona, Spain

Background: Spinal cord atrophy is a key biomarker for tracking disease progression in neurological disorders, including multiple sclerosis, amyotrophic lateral sclerosis, and spinal cord injury. Recent MRI advancements have improved atrophy detection, particularly in the cervical region, facilitating longitudinal studies. However, validating atrophy quantification algorithms remains challenging due to limited ground truth data. Objective: This study introduces SynSpine, a workflow for generating synthetic spinal cord MRI data with varying degrees of artificial atrophy that addresses existing difficulties in monitoring spinal cord degeneration over time. Methods: The workflow consists of two phases: 1) generating synthetic MR images by isolating, extracting and scaling the spinal cord, simulating atrophy on the PAM50 template; 2) performing non-rigid registration to align the synthetic images with the subject's native space, ensuring accurate anatomical correspondence. A proof-of-concept application utilizing the Active Surface and Reg methods implemented in Jim demonstrated its effectiveness in detecting atrophy across various levels of simulated atrophy and noise. Results: SynSpine successfully generates synthetic spinal cord images with varying atrophy levels. Non-rigid registration did not significantly affect atrophy measurements. Atrophy estimation errors, estimated using Active Surface and Reg methods, varied with both simulated atrophy magnitude and noise level, exhibiting region-dependent differences. Increased noise led to higher measurement errors. Conclusions: This study demonstrates the potential for benchmarking spinal cord analysis algorithms, offering a controlled setting for testing algorithm performance and robustness. Future research will focus on enhancing the realism of the synthetic dataset by simulating additional pathologies, thus improving its application for evaluating spinal cord atrophy in clinical and research contexts.