Enhancing epidural needle guidance using a polarization-sensitive optical coherence tomography probe with...

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Anesthesiology

Background:

• Epidural anesthesia is crucial for surgical pain management.
• Accurate epidural needle placement is technically challenging.
• Current methods lack sufficient real-time guidance.

Purpose of the Study:

• To develop and evaluate a novel probe using polarization-sensitive optical coherence tomography (PS-OCT) for enhanced epidural needle placement.
• To assess the efficacy of multimodal imaging modes for tissue differentiation.
• To implement machine learning for automated tissue classification.

Main Methods:

• A PS-OCT probe was developed and tested on porcine spinal samples.
• Multimodal imaging included OCT intensity and three PS-OCT modes (phase retardation, optic axis, DOPU).
• Convolutional neural networks (CNNs), specifically ResNet50 models, were trained for automated tissue recognition.

Main Results:

• Each imaging mode exhibited distinct characteristics for classifying epidural tissues.
• CNN models achieved autonomous tissue identification.
• The Degree of Polarization Uniformity (DOPU) mode demonstrated the highest cross-testing accuracy at 91.53%.

Conclusions:

• PS-OCT provides improved precision for guiding epidural anesthesia needle placement.
• The developed probe and AI-driven analysis offer a promising solution for a challenging clinical problem.
• This technology has the potential to enhance patient safety and procedural success rates.