A machine learning system is presented that successfully identifies lumbar vertebral levels. The small study on human subjects demonstrated real-time performance. A projection-based augmented reality display was used to show the vertebral level directly on the subject adjacent to the puncture site.

SummaryControversy exists as to whether effective spinal anaesthesia can be achieved as quickly as general anaesthesia for a category-1 caesarean section. Sixteen consultants and three fellows in obstetric anaesthesia were timed performing spinal and general anaesthesia for category-1 caesarean section on a simulator. The simulation time commenced upon entry of the anaesthetist into the operating theatre and finished for the spinal anaesthetic at the end of intrathecal injection and for the general anaesthetic when the anaesthetist was happy for surgery to start. In the second clinical part of the study, the time from intrathecal administration to 'adequate surgical anaesthesia' (defined as adequate for start of a category-1 caesarean section) was estimated in 100 elective (category-4) caesarean sections. The median (IQR [range]) times (min:s) for spinal procedure, onset of spinal block and general anaesthesia were 2:56 (2:32 -3:32 [1:22 -3:50]), 5:56 (4:23 -7:39 [2:9 -13:32]) and 1:56 (1:39 -2:9 [1:13 -3:12]), respectively. The limiting factor in urgent spinal anaesthesia is the unpredictable time needed for adequate surgical block to develop.

No abstract

A real-time machine learning system based on the local directional Hadamard features extracted by the sequency-ordered Hadamard transform for detecting the laminae and facet joints in ultrasound images has been proposed. The system has the potential to assist the anesthesiologists in quickly finding the target plane for epidural steroid injections and facet joint injections.

Spinal anesthesia was used safely for CS in this parturient with LQTS.