Search Results

You are looking at 1 - 2 of 2 items for

  • Author or Editor: William Muirhead x
  • Refine by Access: all x
Clear All Modify Search
Full access

Matthew A. Kirkman, William Muirhead, and Nick Sevdalis

OBJECTIVE

Ventriculostomy is a relatively common neurosurgical procedure, often performed in the setting of acute hydrocephalus. Accurate positioning of the catheter is vital to minimize morbidity and mortality, and several anatomical landmarks are currently used. The aim of this study was to prospectively evaluate the relative performance of 3 recognized trajectories for frontal ventriculostomy using imaging-derived metrics: perpendicular to skull (PTS), contralateral medial canthus/external auditory meatus (CMC/EAM), and ipsilateral medial canthus/external auditory meatus (IMC/EAM).

METHODS

Participants completed 9 simulated ventriculostomy attempts (3 of each trajectory) on a model head with Medtronic StealthStation coregistered imaging. Performance measures were distance of the ventricular catheter tip to the foramen of Monro (FoM) and presence of the catheter tip in a lateral ventricle.

RESULTS

Thirty-one individuals of varying seniority and prior ventriculostomy experience performed a total of 279 simulated freehand frontal ventriculostomies. The PTS and CMC/EAM trajectories were found to be significantly more likely to result in both the catheter tip being closer to the FoM and in a lateral ventricle compared with the IMC/EAM trajectory. These findings were not influenced by the prior ventriculostomy experience of the participant, corroborating the significance of these results.

CONCLUSIONS

The PTS and CMC/EAM trajectories were superior to the IMC/EAM trajectories during freehand frontal ventriculostomy in this study, and further data from studies incorporating varying ventricular sizes and bur hole locations are required to facilitate a change in clinical practice. In addition, neuronavigation and other guidance techniques for ventriculostomy are becoming increasingly popular and may be superior to freehand techniques, necessitating further prospective data evaluating their safety, efficacy, and feasibility for routine clinical use.

Restricted access

Danyal Z. Khan, Imanol Luengo, Santiago Barbarisi, Carole Addis, Lucy Culshaw, Neil L. Dorward, Pinja Haikka, Abhiney Jain, Karen Kerr, Chan Hee Koh, Hugo Layard Horsfall, William Muirhead, Paolo Palmisciano, Baptiste Vasey, Danail Stoyanov, and Hani J. Marcus

OBJECTIVE

Surgical workflow analysis involves systematically breaking down operations into key phases and steps. Automatic analysis of this workflow has potential uses for surgical training, preoperative planning, and outcome prediction. Recent advances in machine learning (ML) and computer vision have allowed accurate automated workflow analysis of operative videos. In this Idea, Development, Exploration, Assessment, Long-term study (IDEAL) stage 0 study, the authors sought to use Touch Surgery for the development and validation of an ML-powered analysis of phases and steps in the endoscopic transsphenoidal approach (eTSA) for pituitary adenoma resection, a first for neurosurgery.

METHODS

The surgical phases and steps of 50 anonymized eTSA operative videos were labeled by expert surgeons. Forty videos were used to train a combined convolutional and recurrent neural network model by Touch Surgery. Ten videos were used for model evaluation (accuracy, F1 score), comparing the phase and step recognition of surgeons to the automatic detection of the ML model.

RESULTS

The longest phase was the sellar phase (median 28 minutes), followed by the nasal phase (median 22 minutes) and the closure phase (median 14 minutes). The longest steps were step 5 (tumor identification and excision, median 17 minutes); step 3 (posterior septectomy and removal of sphenoid septations, median 14 minutes); and step 4 (anterior sellar wall removal, median 10 minutes). There were substantial variations within the recorded procedures in terms of video appearances, step duration, and step order, with only 50% of videos containing all 7 steps performed sequentially in numerical order. Despite this, the model was able to output accurate recognition of surgical phases (91% accuracy, 90% F1 score) and steps (76% accuracy, 75% F1 score).

CONCLUSIONS

In this IDEAL stage 0 study, ML techniques have been developed to automatically analyze operative videos of eTSA pituitary surgery. This technology has previously been shown to be acceptable to neurosurgical teams and patients. ML-based surgical workflow analysis has numerous potential uses—such as education (e.g., automatic indexing of contemporary operative videos for teaching), improved operative efficiency (e.g., orchestrating the entire surgical team to a common workflow), and improved patient outcomes (e.g., comparison of surgical techniques or early detection of adverse events). Future directions include the real-time integration of Touch Surgery into the live operative environment as an IDEAL stage 1 (first-in-human) study, and further development of underpinning ML models using larger data sets.