1
|
Boal MWE, Anastasiou D, Tesfai F, Ghamrawi W, Mazomenos E, Curtis N, Collins JW, Sridhar A, Kelly J, Stoyanov D, Francis NK. Evaluation of objective tools and artificial intelligence in robotic surgery technical skills assessment: a systematic review. Br J Surg 2024; 111:znad331. [PMID: 37951600 PMCID: PMC10771126 DOI: 10.1093/bjs/znad331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Revised: 09/18/2023] [Accepted: 09/19/2023] [Indexed: 11/14/2023]
Abstract
BACKGROUND There is a need to standardize training in robotic surgery, including objective assessment for accreditation. This systematic review aimed to identify objective tools for technical skills assessment, providing evaluation statuses to guide research and inform implementation into training curricula. METHODS A systematic literature search was conducted in accordance with the PRISMA guidelines. Ovid Embase/Medline, PubMed and Web of Science were searched. Inclusion criterion: robotic surgery technical skills tools. Exclusion criteria: non-technical, laparoscopy or open skills only. Manual tools and automated performance metrics (APMs) were analysed using Messick's concept of validity and the Oxford Centre of Evidence-Based Medicine (OCEBM) Levels of Evidence and Recommendation (LoR). A bespoke tool analysed artificial intelligence (AI) studies. The Modified Downs-Black checklist was used to assess risk of bias. RESULTS Two hundred and forty-seven studies were analysed, identifying: 8 global rating scales, 26 procedure-/task-specific tools, 3 main error-based methods, 10 simulators, 28 studies analysing APMs and 53 AI studies. Global Evaluative Assessment of Robotic Skills and the da Vinci Skills Simulator were the most evaluated tools at LoR 1 (OCEBM). Three procedure-specific tools, 3 error-based methods and 1 non-simulator APMs reached LoR 2. AI models estimated outcomes (skill or clinical), demonstrating superior accuracy rates in the laboratory with 60 per cent of methods reporting accuracies over 90 per cent, compared to real surgery ranging from 67 to 100 per cent. CONCLUSIONS Manual and automated assessment tools for robotic surgery are not well validated and require further evaluation before use in accreditation processes.PROSPERO: registration ID CRD42022304901.
Collapse
Affiliation(s)
- Matthew W E Boal
- The Griffin Institute, Northwick Park & St Marks’ Hospital, London, UK
- Wellcome/ESPRC Centre for Interventional Surgical Sciences (WEISS), University College London (UCL), London, UK
- Division of Surgery and Interventional Science, Research Department of Targeted Intervention, UCL, London, UK
| | - Dimitrios Anastasiou
- Wellcome/ESPRC Centre for Interventional Surgical Sciences (WEISS), University College London (UCL), London, UK
- Medical Physics and Biomedical Engineering, UCL, London, UK
| | - Freweini Tesfai
- The Griffin Institute, Northwick Park & St Marks’ Hospital, London, UK
- Wellcome/ESPRC Centre for Interventional Surgical Sciences (WEISS), University College London (UCL), London, UK
| | - Walaa Ghamrawi
- The Griffin Institute, Northwick Park & St Marks’ Hospital, London, UK
| | - Evangelos Mazomenos
- Wellcome/ESPRC Centre for Interventional Surgical Sciences (WEISS), University College London (UCL), London, UK
- Medical Physics and Biomedical Engineering, UCL, London, UK
| | - Nathan Curtis
- Department of General Surgey, Dorset County Hospital NHS Foundation Trust, Dorchester, UK
| | - Justin W Collins
- Division of Surgery and Interventional Science, Research Department of Targeted Intervention, UCL, London, UK
- University College London Hospitals NHS Foundation Trust, London, UK
| | - Ashwin Sridhar
- Division of Surgery and Interventional Science, Research Department of Targeted Intervention, UCL, London, UK
- University College London Hospitals NHS Foundation Trust, London, UK
| | - John Kelly
- Division of Surgery and Interventional Science, Research Department of Targeted Intervention, UCL, London, UK
- University College London Hospitals NHS Foundation Trust, London, UK
| | - Danail Stoyanov
- Wellcome/ESPRC Centre for Interventional Surgical Sciences (WEISS), University College London (UCL), London, UK
- Computer Science, UCL, London, UK
| | - Nader K Francis
- The Griffin Institute, Northwick Park & St Marks’ Hospital, London, UK
- Division of Surgery and Interventional Science, Research Department of Targeted Intervention, UCL, London, UK
- Yeovil District Hospital, Somerset Foundation NHS Trust, Yeovil, Somerset, UK
| |
Collapse
|
2
|
Hutchinson K, Reyes I, Li Z, Alemzadeh H. COMPASS: a formal framework and aggregate dataset for generalized surgical procedure modeling. Int J Comput Assist Radiol Surg 2023; 18:2143-2154. [PMID: 37145250 DOI: 10.1007/s11548-023-02922-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2022] [Accepted: 04/14/2023] [Indexed: 05/06/2023]
Abstract
PURPOSE We propose a formal framework for the modeling and segmentation of minimally invasive surgical tasks using a unified set of motion primitives (MPs) to enable more objective labeling and the aggregation of different datasets. METHODS We model dry-lab surgical tasks as finite state machines, representing how the execution of MPs as the basic surgical actions results in the change of surgical context, which characterizes the physical interactions among tools and objects in the surgical environment. We develop methods for labeling surgical context based on video data and for automatic translation of context to MP labels. We then use our framework to create the COntext and Motion Primitive Aggregate Surgical Set (COMPASS), including six dry-lab surgical tasks from three publicly available datasets (JIGSAWS, DESK, and ROSMA), with kinematic and video data and context and MP labels. RESULTS Our context labeling method achieves near-perfect agreement between consensus labels from crowd-sourcing and expert surgeons. Segmentation of tasks to MPs results in the creation of the COMPASS dataset that nearly triples the amount of data for modeling and analysis and enables the generation of separate transcripts for the left and right tools. CONCLUSION The proposed framework results in high quality labeling of surgical data based on context and fine-grained MPs. Modeling surgical tasks with MPs enables the aggregation of different datasets and the separate analysis of left and right hands for bimanual coordination assessment. Our formal framework and aggregate dataset can support the development of explainable and multi-granularity models for improved surgical process analysis, skill assessment, error detection, and autonomy.
Collapse
Affiliation(s)
- Kay Hutchinson
- Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, 22903, USA.
| | - Ian Reyes
- Department of Computer Science, University of Virginia, Charlottesville, VA, 22903, USA
- IBM, RTP, Durham, NC, 27709, USA
| | - Zongyu Li
- Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, 22903, USA
| | - Homa Alemzadeh
- Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, 22903, USA
- Department of Computer Science, University of Virginia, Charlottesville, VA, 22903, USA
| |
Collapse
|
3
|
Ballesta Martinez B, Kallidonis P, Tsaturyan A, Peteinaris A, Faitatziadis S, Gkeka K, Tatanis V, Vagionis A, Pagonis K, Obaidat M, Anaplioti E, Haney C, Vrettos T, Liatsikos E. Transfer of acquired practical skills from dry lab into live surgery using the avatera robotic system: An experimental study. Actas Urol Esp 2023; 47:611-617. [PMID: 37574013 DOI: 10.1016/j.acuroe.2023.08.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Revised: 06/14/2023] [Accepted: 06/15/2023] [Indexed: 08/15/2023]
Abstract
OBJECTIVE To evaluate the transfer of the practical skills of robot-assisted surgery acquired in the dry-lab into a real live experimental setting for performing upper and lower urinary tract surgeries. MATERIAL AND METHODS An in vivo experimental study design was utilized. Six urology trainees and fellows; two 2nd year trainees with no previous exposure to laparoscopic surgery (Group 1), two 4th year residents with medium exposure to laparoscopic surgery (Group 2) and two fellows trained to perform laparoscopic surgeries (Group 3) performed ureteral reimplantation into the bladder, pyeloplasty, and radical nephrectomy on three female pigs under general anesthesia. Prior to performing the requested procedures, each participant completed 10-14 h dry-lab robotic training acquiring skills in basic surgical tasks, such as suturing, cutting and needle passage. The recorded variables were the successful completion of the procedures, the console time, and the time to perform different steps and major complications. RESULTS All procedures were completed successfully by all groups except the pyeloplasty by group 1 which was complicated by bleeding from the renal vein, and the procedure was abandoned. Group 3 achieved shorter console time for all successfully completed procedures and for separate surgical steps compared to all groups, followed by Group 2. The slowest group for all procedures and steps analyzed was Group 3. CONCLUSIONS Although further clinical evidence is needed, the robotic-assisted urological procedures and the most challenging steps could be performed safely and effectively after proper training in the dry lab under mentor supervision according to our study.
Collapse
Affiliation(s)
- B Ballesta Martinez
- Department of Urology, University of Patras, Patras, Greece; Department of Urology, Hospital Vinalopó, Elche, Spain
| | - P Kallidonis
- Department of Urology, University of Patras, Patras, Greece
| | - A Tsaturyan
- Department of Urology, University of Patras, Patras, Greece
| | - A Peteinaris
- Department of Urology, University of Patras, Patras, Greece
| | - S Faitatziadis
- Department of Urology, University of Patras, Patras, Greece
| | - K Gkeka
- Department of Urology, University of Patras, Patras, Greece
| | - V Tatanis
- Department of Urology, University of Patras, Patras, Greece
| | - A Vagionis
- Department of Urology, University of Patras, Patras, Greece
| | - K Pagonis
- Department of Urology, University of Patras, Patras, Greece
| | - M Obaidat
- Department of Urology, University of Patras, Patras, Greece
| | - E Anaplioti
- Department of Urology, University of Patras, Patras, Greece
| | - C Haney
- Department of Urology, University Hospital of Leipzig, Leipzig, Germany
| | - T Vrettos
- Department of Anesthesiology and ICU, University of Patras, Patras, Greece
| | - E Liatsikos
- Department of Urology, University of Patras, Patras, Greece; Department of Urology, Medical University of Vienna, Vienna, Austria.
| |
Collapse
|
4
|
Chadebecq F, Lovat LB, Stoyanov D. Artificial intelligence and automation in endoscopy and surgery. Nat Rev Gastroenterol Hepatol 2023; 20:171-182. [PMID: 36352158 DOI: 10.1038/s41575-022-00701-y] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 10/03/2022] [Indexed: 11/10/2022]
Abstract
Modern endoscopy relies on digital technology, from high-resolution imaging sensors and displays to electronics connecting configurable illumination and actuation systems for robotic articulation. In addition to enabling more effective diagnostic and therapeutic interventions, the digitization of the procedural toolset enables video data capture of the internal human anatomy at unprecedented levels. Interventional video data encapsulate functional and structural information about a patient's anatomy as well as events, activity and action logs about the surgical process. This detailed but difficult-to-interpret record from endoscopic procedures can be linked to preoperative and postoperative records or patient imaging information. Rapid advances in artificial intelligence, especially in supervised deep learning, can utilize data from endoscopic procedures to develop systems for assisting procedures leading to computer-assisted interventions that can enable better navigation during procedures, automation of image interpretation and robotically assisted tool manipulation. In this Perspective, we summarize state-of-the-art artificial intelligence for computer-assisted interventions in gastroenterology and surgery.
Collapse
Affiliation(s)
- François Chadebecq
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK.
| |
Collapse
|