Machine Learning based Classification of Local Robotic Surgical Skills in a Training Tasks Set

Juarez-Villalobos, L.; Hevia–Montiel, Nidiyare; Perez‐Gonzalez, Jorge

doi:10.1109/embc46164.2021.9629579

Cited by 3 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most often, motion data from surgical videos or kinematic data from robotic systems or sensors were collected from simulators rather than during actual surgical procedures. The most common simulators used were robotic box models (51%, n=19) 21,[23][24][25][26]28,29,31,35,38,41,45,[47][48][49]52,[54][55][56] . Laparoscopic simulators were the second most common setting for data collection (32%, n=12) 20,27,30,32,33,36,37,40,43,50,51,53 .…”

Section: Settings and Tasksmentioning

confidence: 99%

“…The most common tasks assessed were suturing (62%, n=23) 21,23,25,26,[28][29][30][31]33,35,37,38,40,41,47,[49][50][51][52][53][54][55][56] , knot-tying (41%, n=15) 21,23,25,26,28,29,35,38,40,41,47,49,52,55,56 and needle passing (35%, n=13) 21,23,25,28,29,35,38,41,47,49,52,55,56 .…”

Section: Settings and Tasksmentioning

confidence: 99%

“…Three different types of input data were used throughout the 37 studies: video data (49%, n=18) 20,22,27,30,31,33,34,[37][38][39]42,[44][45][46][47]51,52,54 , kinematic data (46%, n=17) 21,[23][24][25][26]28,29,35,40,41,43,[48][49][50]53,55,56 and functional near-infrared spectroscopy (fNIRS) data (5%, n=2) 32,36 . Video recordings either from endoscopic laparoscopic/robotic camera or external cameras are used in 18 studies (49%).…”

Section: Input Data and Datasetsmentioning

confidence: 99%

“…Of those, the JIGSAWS (Johns Hopkins University and Intuitive Surgical, Inc. Gesture and Skill Assessment Working Set) 59 dataset was most frequently used (n=15, 41%) 21,23,25,26,28,29,31,35,38,41,47,49,52,55,56 . It contains video and kinematic data together with human annotated skill ratings of eight surgeons performing three surgical tasks in five-fold repetition in a robotic box model trainer.…”

Section: Input Data and Datasetsmentioning

confidence: 99%

“…Technical surgical skills can be assessed using expert levels (ordinal scale) or proficiency scores (interval scale) (Figure 1). In 27 of the studies (73%) an ordinal scale was applied 20,21,[25][26][27][28][29][30][31][35][36][37][38][40][41][42][43][44][45]48,49,[51][52][53][54][55][56] . In twelve studies (32%) participants were categorized in two different skill levels 20,26,30,[35][36][37]41,42,44,48,51,53 and in 14 studies (38%) into three different expert levels (novice, intermediate, expert) 21,25,28,29,31,38,40,43,…”

Section: Assessmentmentioning

confidence: 99%

See 4 more Smart Citations

Technical Skill Assessment in Minimally Invasive Surgery Using Artificial Intelligence: A Systematic Review

Pedrett

Mascagni

Beldi

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective: To review artificial intelligence (AI) based applications for the assessment of technical skills in minimally invasive surgery. Background: As technical skill assessment in surgery relies on expert opinion, it is time-consuming, costly, and often lacks objectivity. Analysis of routinely generated data by AI methods has the potential for automatic technical skill assessment in minimally invasive surgery. Methods: A systematic search of Medline, Embase, Web of Science and IEEE Xplore was performed to identify original articles reporting the use of AI in the assessment of technical skill in minimally invasive surgery. Risk of bias (RoB) and quality of included studies were analyzed according to Quality Assessment of Diagnostic Accuracy Studies criteria and the modified Joanna Briggs Institute checklists, respectively. Findings were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. Results: In total, 1467 articles were identified, 37 articles met eligibility criteria and were analyzed. Motion data extracted from surgical videos (49%) or kinematic data from robotic systems or sensors (46%) were the most frequent input data for AI. Most studies used deep learning (73%) and predicted technical skills using an ordinal assessment scale (73%) with good accuracies in simulated settings. However, all proposed models were in development stage, only 8% were externally validated and 16% showed a low RoB. Conclusion: AI is promising to automate technical skill assessment in minimally invasive surgery. However, models should be benchmarked on representative datasets using predefined performance metrics and tested in clinical implementation studies.

show abstract

Section: Settings and Tasksmentioning

confidence: 99%

Section: Settings and Tasksmentioning

confidence: 99%

Section: Input Data and Datasetsmentioning

confidence: 99%

Section: Input Data and Datasetsmentioning

confidence: 99%

Section: Assessmentmentioning

confidence: 99%

See 3 more Smart Citations

Technical Skill Assessment in Minimally Invasive Surgery Using Artificial Intelligence: A Systematic Review

Pedrett

Mascagni

Beldi

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Technical skill assessment in minimally invasive surgery using artificial intelligence: a systematic review

et al. 2023

View full text Add to dashboard Cite

Background Technical skill assessment in surgery relies on expert opinion. Therefore, it is time-consuming, costly, and often lacks objectivity. Analysis of intraoperative data by artificial intelligence (AI) has the potential for automated technical skill assessment. The aim of this systematic review was to analyze the performance, external validity, and generalizability of AI models for technical skill assessment in minimally invasive surgery. Methods A systematic search of Medline, Embase, Web of Science, and IEEE Xplore was performed to identify original articles reporting the use of AI in the assessment of technical skill in minimally invasive surgery. Risk of bias (RoB) and quality of the included studies were analyzed according to Quality Assessment of Diagnostic Accuracy Studies criteria and the modified Joanna Briggs Institute checklists, respectively. Findings were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. Results In total, 1958 articles were identified, 50 articles met eligibility criteria and were analyzed. Motion data extracted from surgical videos (n = 25) or kinematic data from robotic systems or sensors (n = 22) were the most frequent input data for AI. Most studies used deep learning (n = 34) and predicted technical skills using an ordinal assessment scale (n = 36) with good accuracies in simulated settings. However, all proposed models were in development stage, only 4 studies were externally validated and 8 showed a low RoB. Conclusion AI showed good performance in technical skill assessment in minimally invasive surgery. However, models often lacked external validity and generalizability. Therefore, models should be benchmarked using predefined performance metrics and tested in clinical implementation studies.

show abstract

Clinical applications of artificial intelligence in robotic surgery

Knudsen,

Ghaffar,

et al. 2024

J Robotic Surg

View full text Add to dashboard Cite

Artificial intelligence (AI) is revolutionizing nearly every aspect of modern life. In the medical field, robotic surgery is the sector with some of the most innovative and impactful advancements. In this narrative review, we outline recent contributions of AI to the field of robotic surgery with a particular focus on intraoperative enhancement. AI modeling is allowing surgeons to have advanced intraoperative metrics such as force and tactile measurements, enhanced detection of positive surgical margins, and even allowing for the complete automation of certain steps in surgical procedures. AI is also Query revolutionizing the field of surgical education. AI modeling applied to intraoperative surgical video feeds and instrument kinematics data is allowing for the generation of automated skills assessments. AI also shows promise for the generation and delivery of highly specialized intraoperative surgical feedback for training surgeons. Although the adoption and integration of AI show promise in robotic surgery, it raises important, complex ethical questions. Frameworks for thinking through ethical dilemmas raised by AI are outlined in this review. AI enhancements in robotic surgery is some of the most groundbreaking research happening today, and the studies outlined in this review represent some of the most exciting innovations in recent years.

show abstract

Machine Learning based Classification of Local Robotic Surgical Skills in a Training Tasks Set

Cited by 3 publications

References 8 publications

Technical Skill Assessment in Minimally Invasive Surgery Using Artificial Intelligence: A Systematic Review

Technical Skill Assessment in Minimally Invasive Surgery Using Artificial Intelligence: A Systematic Review

Technical skill assessment in minimally invasive surgery using artificial intelligence: a systematic review

Clinical applications of artificial intelligence in robotic surgery

Contact Info

Product

Resources

About