About the Project
Applications are invited for a self-funded, 3 year full-time or 6 year part-time PhD project.
The PhD will be based in the School of Electrical and Mechanical Engineering and will be supervised by Dr Shamsul Masum, Dr John Chiverton and Dr Jennifer Straatman (Consultant from Portsmouth Hospital University Trust).
Robotic cholecystectomy is a common procedure, yet variation in surgical technique impacts patient outcomes. Traditional evaluation methods, such as OSATS and GEARS, are subjective, time-consuming, and resource-intensive. This PhD project proposes the development of an integrated, AI-driven video analysis tool to objectively assess robotic cholecystectomy performance. By leveraging state-of-the-art computer vision and machine learning techniques, the project aims to enhance patient safety, improve surgical training, and standardize operative practices across institutions.
The work on this project will:
- Development of an AI-based tool for automatic segmentation, skill scoring, and safety assessment in robotic cholecystectomy.
- Objective benchmarking of intraoperative performance using instrument motion metrics and phase recognition.
- Identification of critical safety events, including attainment of the critical view of safety (CVS).
- Integration of clinical and intraoperative data to correlate surgical metrics with patient outcomes.
- Contribution to surgical training, credentialing, and quality improvement initiatives through data-driven feedback.
- Potential to extend the tool to other robotic gastrointestinal procedures and outcome prediction models.
Project description
Robotic cholecystectomy is increasingly used in surgical practice, yet variability in intraoperative technique can influence outcomes such as complications, length of stay, and patient recovery. Current assessment relies on subjective scoring systems like OSATS and GEARS, which are limited by human bias and the need for expert time. Advances in AI and computer vision, particularly self-supervised models such as VideoMAE and pretrained surgical video libraries, now offer the potential for automated, objective evaluation of surgical performance.
This PhD will develop and validate an AI-driven video analysis tool for robotic cholecystectomy. The tool will operate in three stages: (1) Workflow Segmentation: deep learning models will identify standardized surgical phases and steps, enabling benchmarking of procedural flow and efficiency; (2) Safety Assurance: semantic segmentation and classification models will detect anatomical landmarks and confirm attainment of critical safety steps such as the CVS; (3) Skill Scoring: instrument motion metrics—including path length, smoothness, and velocity—will be extracted from videos and used to estimate technical proficiency against validated benchmarks.
The project will analyse a dataset of robotic cholecystectomy videos from Portsmouth Hospital University Trust, with automatic annotation augmented by expert input. Clinical outcomes—including length of stay, complications, and readmissions—will be correlated with objective intraoperative metrics. The resulting tool will provide data-driven feedback to surgeons, support internal quality assurance, and potentially guide future training and credentialing initiatives.
By combining AI with detailed video and clinical analysis, this project aims to transform surgical assessment, enhancing patient safety, standardizing operative practice, and reducing the resource burden of manual video review. Its findings could form the foundation for broader adoption of AI-driven evaluation across robotic gastrointestinal surgery, ultimately contributing to improved outcomes and safer, more efficient surgical care.
General admissions criteria
You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a Master’s degree in an appropriate subject (Computer Science, Data science, Data analytics, Artificial intelligence, Machine Learning) or a related area. In exceptional cases, we may consider equivalent professional experience and/or Qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
This is a Preview Listing…
You must sign in to see the full job description, and to apply.
Manage / Upgrade this job to a Full Job Listing.
Find Your Best Opportunity
Tell them AcademicJobs.com sent you!