Automated Spinal Landmark Identification to Improve Patient Safety and Efficacy During Neuraxial Anaesthesia Needle Insertion

Neuraxial procedures are commonly performed with wide range of therapeutic and diagnostic indications. Applications include neuraxial anesthesia for surgery, epidural labour analgesia, epidural steroid injections and lumbar punctures. The current blind palpation landmark technique is known to be highly inaccurate and may increase the risk of multiple insertion attempts, patient suffering and complication rates such as spinal cord injury. A key challenge for neuraxial procedures is the correct identification of needle insertion site.

The ultrasound imaging technique has found its way to neuraxial procedures as an imaging method to detect the inner anatomical structure of the lumbar spine and is superior to the traditional palpation method. However, a full interpretation of ultrasound images requires professional training and experience.

The overall aim of this proposal is to develop an automated spinal landmark identification system to improve patient safety and efficacy of neuraxial procedure needle insertion success. The primary aim is to develop an automated spinal landmark identification algorithm using image processing system to achieve 90% 1st spinal needle success rate within 12 months. The investigators will recruit 100 subjects in a prospective cohort study to investigate the spinal needle success rate as a clinically relevant outcome.