Segmentation of clinical imagery for improved epidural stimulation to address spinal cord injury
Matelsky, J. K.; Sharma, P.; Johnson, E. C.; Wang, S.; Boakye, M.; Angeli, C.; Forrest, G. F.; Harkema, S. J.; Tenore, F.
Show abstract
Spinal cord injury (SCI) can severely impair motor and autonomic function, with long-term consequences for quality of life. Epidural stimulation has emerged as a promising intervention, offering partial recovery by activating neural circuits below the injury. To make this therapy effective in practice, precise placement of stimulation electrodes is essential -- and that requires accurate segmentation of spinal cord structures in MRI data. We present a protocol for manual segmentation tailored to SCI anatomy, and evaluated a deep learning approach using a U-Net architecture to automate this segmentation process. Our approach yields accurate, efficient segmentation that identify potential electrode placement sites with high fidelity. Preliminary results suggest that this framework can accelerate SCI MRI analysis and improve planning for epidural stimulation, helping bridge the gap between advanced neurotechnologies and real-world clinical application with faster surgeries and more accurate electrode placement.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- TAP: Targeting and analysis pipeline for optimization and verification of coil placement in transcranial magnetic stimulation 94%
- Fast FEM-based Electric Field Calculations for Transcranial Magnetic Stimulation 93%
- Combining biophysical models and machine learning to optimize implant geometry and stimulation protocol for intraneural electrodes 93%
Similar papers in this journal
Similar papers in this journal
- Implementation and prospective real-time evaluation of a generalized system for in-clinic deployment and validation of machine learning models in radiology 91%
- Classification of Hyper-scale Multimodal Imaging Datasets 91%
- Designing a computer-assisted diagnosis system for cardiomegaly detection and radiology report generation 90%
Similar papers in this journal
- Endogenous signals during active movement predict deep brain stimulation evoked potential pathways: Results of a transfer function analysis 92%
- Somatotopic Arrangement of Eight Distinct Skin Areas in the Human Primary Somatosensory Cortex Derived from Functional Magnetic Resonance Imaging 92%
- Perceptual super-resolution in multiple sclerosis MRI 92%
Similar papers in this journal
- Multi-locus transcranial magnetic stimulation system for electronically targeted brain stimulation 94%
- TI-Toolbox: An Open-Source Software for Temporal Interference Stimulation Research 93%
- Adaptive current-flow models of ECT: Explaining individual static impedance, dynamic impedance, and brain current delivery 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.