Automatic assessment of laparoscopic surgical skill competence based on motion metrics

Exploring the Role of Artificial Intelligence (AI)-Driven Training in Laparoscopic Suturing: A Systematic Review of Skills Mastery, Retention, and Clinical Performance in Surgical Education

Background: Artificial Intelligence (AI)-driven training systems are becoming increasingly important in surgical education, particularly in the context of laparoscopic suturing. This systematic review aims to assess the impact of AI on skill acquisition, long-term retention, and clinical performance, with a specific focus on the types of machine learning (ML) techniques applied to laparoscopic suturing training and their associated advantages and limitations. Methods: A comprehensive search was conducted across multiple databases, including PubMed, IEEE Xplore, Cochrane Library, and ScienceDirect, for studies published between 2005 and 2024. Following the PRISMA guidelines, 1200 articles were initially screened, and 33 studies met the inclusion criteria. This review specifically focuses on ML techniques such as deep learning, motion capture, and video segmentation and their application in laparoscopic suturing training. The quality of the included studies was assessed, considering factors such as sample size, follow-up duration, and potential biases. Results: AI-based training systems have shown notable improvements in the laparoscopic suturing process, offering clear advantages over traditional methods. These systems enhance precision, efficiency, and long-term retention of key suturing skills. The use of personalized feedback and real-time performance tracking allows learners to gain proficiency more rapidly and ensures that skills are retained over time. These technologies are particularly beneficial for novice surgeons and provide valuable support in resource-limited settings, where access to expert instructors and advanced equipment may be scarce. Key machine learning techniques, including deep learning, motion capture, and video segmentation, have significantly improved specific suturing tasks, such as needle manipulation, insertion techniques, knot tying, and grip control, all of which are critical to mastering laparoscopic suturing. Conclusions: AI-driven training tools are reshaping laparoscopic suturing education by improving skill acquisition, providing real-time feedback, and enhancing long-term retention. Deep learning, motion capture, and video segmentation techniques have proven most effective in refining suturing tasks such as needle manipulation and knot tying. While AI offers significant advantages, limitations in accuracy, scalability, and integration remain. Further research, particularly large-scale, high-quality studies, is necessary to refine these tools and ensure their effective implementation in real-world clinical settings.

Artificial intelligence integration in surgery through hand and instrument tracking: a systematic literature review

Objective

This systematic literature review of the integration of artificial intelligence (AI) applications in surgical practice through hand and instrument tracking provides an overview of recent advancements and analyzes current literature on the intersection of surgery with AI. Distinct AI algorithms and specific applications in surgical practice are also examined.

Methods

An advanced search using medical subject heading terms was conducted in Medline (via PubMed), SCOPUS, and Embase databases for articles published in English. A strict selection process was performed, adhering to PRISMA guidelines.

Results

A total of 225 articles were retrieved. After screening, 77 met inclusion criteria and were included in the review. Use of AI algorithms in surgical practice was uncommon during 2013-2017 but has gained significant popularity since 2018. Deep learning algorithms (n = 62) are increasingly preferred over traditional machine learning algorithms (n = 15). These technologies are used in surgical fields such as general surgery (n = 19), neurosurgery (n = 10), and ophthalmology (n = 9). The most common functional sensors and systems used were prerecorded videos (n = 29), cameras (n = 21), and image datasets (n = 7). The most common applications included laparoscopic (n = 13), robotic-assisted (n = 13), basic (n = 12), and endoscopic (n = 8) surgical skills training, as well as surgical simulation training (n = 8).

Conclusion

AI technologies can be tailored to address distinct needs in surgical education and patient care. The use of AI in hand and instrument tracking improves surgical outcomes by optimizing surgical skills training. It is essential to acknowledge the current technical and social limitations of AI and work toward filling those gaps in future studies.

A Comparative Study of Laparoscopic Skills Between Novices and Experts: How to Steepen the Learning Curve

Introduction and aim Laparoscopic surgery has revolutionized the field of surgery over the past few decades. The learning curve in laparoscopy is known to be slow, flat, and complex. This study aims to conduct a comparative analysis of laparoscopic skills, specifically focusing on suturing, knot tying, and needle handling, between novices and experts. The purpose is to objectively quantify the disparities in skill proficiency, identify specific areas needing improvement in training curricula, and contribute to the development of more effective training methodologies for emerging laparoscopic surgeons. Methods Residents from different specialties and institutions had their laparoscopic training and evaluation sessions recorded during their curriculum and compared with the performance of experienced surgeons from the Hôtel-Dieu de France University Hospital (Beirut, LBN) during live surgeries. This comparative study was based on the universally recognized Global Operative Assessment of Laparoscopic Skills (GOALS) score and an assessment of a detailed set of laparoscopic skills and techniques used during needle handling and knot tying. Results Twenty-one tasks performed by novices and 11 tasks performed by experts were considered. A significant difference was found in the GOALS score between the two groups (experts: 23.4/25; novices: 15.9/25). Moreover, a statistically significant difference was found to be present in favor of the experts in the following skills/techniques: using thread handling and forceps rotation for needle manipulation, laying the needle on a fixed driver arm before grasping it, using needle curvature for knot tying, using upward-facing forceps convexity when tying, using an open thread loop before tying, thread handling capacity, knot tying capacity, and number of needle skills performed per task. Conclusion This study demonstrates that many micro-steps in laparoscopic suturing are more prevalent among expert surgeons than among trainees. Incorporating these micro-steps into training could significantly accelerate learning curves, enabling trainees to refine their skills more efficiently and keep pace with the latest surgical advancements in their specialties.

Validation and motion analyses of laparoscopic radical nephrectomy with Thiel-embalmed cadavers

PURPOSE

Our aim was to develop practical training for laparoscopic surgery using Thielembalmed cadavers. Furthermore, in order to verbalize experts' motion characteristics and provide objective feedback to trainees, we initiated motion capture analyses of multiple surgical instruments simultaneously during the cadaveric trainings. In the present study, we report our preliminary results.

METHODS

Participants voluntarily joined the present cadaveric simulation trainings, and performed laparoscopic radical nephrectomy. After the trainings, scores for tissue similarity (face validity) and impression of educational merit (content validity) were collected from participants based on a 5-point Likert scale (tissue similarity: 5: very similar, 3: average, 1: very different; educational merit: 5: very high, 3: average, 1: very low). In addition, after the additional IRB approval, we started motion capture (Mocap) analyses of 6 surgical instruments (scissors, vessel sealing system, grasping forceps, clip applier, right-angled forceps, and suction), using an infrared trinocular camera (120-Hz location record). Mocap-metrics were compared according to the previous surgical experiences (experts: ≧50 laparoscopic surgeries, intermediates: 10-49, novices: 0-9), using the Kruskal-Wallis test.

RESULTS

A total of 9 experts, 19 intermediates, and 15 novices participated in the present study. In terms of face validity, the mean scores were higher than 3, other than for the Vena cava(mean score of 2.89). Participants agreed with the training value (usefulness for future skill improvement: mean score of 4.57). In terms of Mocap analysis, faster speed-related metrics (e.g., velocity, the distribution of tip velocity, acceleration, and jerk) in the scissors and vessel sealing system, a shorter path length of grasping forceps, and fewer dimensionless squared jerks, which indicated more purposeful motion of 4 surgical instruments (vessel sealing system, grasping forceps, clip applier and suction), were observed in the more experienced group.

CONCLUSIONS

The Thiel-embalmed cadaver provides an excellent training opportunity for complex laparoscopic procedures with participants' high level of satisfaction, and may become a promising tool for a better objective understanding of surgical dexterity. In order to enrich formative feedback to trainees, we are now proceeding with Mocap analysis.

Surgical skill analysis focused on tissue traction in laparoscopic wet lab training

Background

Tissue handling is one of the pivotal parts of surgical procedures. We aimed to elucidate the characteristics of experts' left-hand during laparoscopic tissue dissection.

Methods

Participants performed tissue dissection around the porcine aorta. The grasping force/point of the grasping forceps were measured using custom-made sensor forceps, and the forceps location was also recorded by motion capture system (Mocap). According to the global operative assessment of laparoscopic skills (GOALS), two experts scored the recorded movies, and based on the mean scores, participants were divided into three groups: novice (<10), intermediate (10≤ to <20), and expert (≤20). Force-based metrics were compared among the three groups using the Kruskal-Wallis test. Principal component analysis (PCA) using significant metrics was also performed.

Results

A total of 42 trainings were successfully recorded. The statistical test revealed that novices frequently regrasped a tissue (median total number of grasps, novices: 268.0 times, intermediates: 89.5, experts: 52.0, p < 0.0001), the traction angle became stable against the aorta (median weighted standard deviation of traction angle, novices: 30.74°, intermediates: 26.80, experts: 23.75, p = 0.0285), and the grasping point moved away from the aorta according to skill competency [median percentage of grasping force applied in close zone (0 to 2.0 cm from aorta), novices: 34.96 %, intermediates: 21.61 %, experts: 10.91 %, p = 0.0032]. PCA showed that the efficiency-related (total number of grasps) and effective tissue traction-related (weighted average grasping position in Y-axis and distribution of grasping area) metrics mainly contributed to the skill difference (proportion of variance of first principal component: 60.83 %).

Conclusion

The present results revealed experts' left-hand characteristics, including correct tissue grasping, sufficient tissue traction from the aorta, and stable traction angle. Our next challenge is the provision of immediate and visual feedback onsite after the present wet-lab training, and shortening the learning curve of trainees.

A surgical instrument motion measurement system for skill evaluation in practical laparoscopic surgery training

This study developed and validated a surgical instrument motion measurement system for skill evaluation during practical laparoscopic surgery training. Owing to the various advantages of laparoscopic surgery including minimal invasiveness, this technique has been widely used. However, expert surgeons have insufficient time for providing training to beginners due to the shortage of surgeons and limited working hours. Skill transfer efficiency has to be improved for which there is an urgent need to develop objective surgical skill evaluation methods. Therefore, a simple motion capture-based surgical instrument motion measurement system that could be easily installed in an operating room for skill assessment during practical surgical training was developed. The tip positions and orientations of the instruments were calculated based on the marker positions attached to the root of the instrument. Because the patterns of these markers are individual, this system can track multiple instruments simultaneously and detect exchanges. However due to the many obstacles in the operating room, the measurement data included noise and outliers. In this study, the effect of this decrease in measurement accuracy on feature calculation was determined. Accuracy verification experiments were conducted during wet-lab training to demonstrate the capability of this system to measure the motion of surgical instruments with practical accuracy. A surgical training experiment on a cadaver was conducted, and the motions of six surgical instruments were measured in 36 cases of laparoscopic radical nephrectomy. Outlier removal and smoothing methods were also developed and applied to remove the noise and outliers in the obtained data. The questionnaire survey conducted during the experiment confirmed that the measurement system did not interfere with the surgical operation. Thus, the proposed system was capable of making reliable measurements with minimal impact on surgery. The system will facilitate surgical education by enabling the evaluation of skill transfer of surgical skills.

Surgeon Upper Extremity Kinematics During Error and Error-Free Retropubic Trocar Passage

INTRODUCTION AND HYPOTHESIS

Surgeon kinematics play a significant role in the prevention of patient injury. We hypothesized that elbow extension and ulnar wrist deviation are associated with bladder injury during simulated midurethral sling (MUS) procedures.

METHODS

We used motion capture technology to measure surgeons' flexion/extension, abduction/adduction, and internal/external rotation angular time series for shoulder, elbow, and wrist joints. Starting and ending angles, minimum and maximum angles, and range of motion (ROM) were extracted from each time series. We created anatomical multibody models and applied linear mixed modeling to compare kinematics between trials with versus without bladder penetration and attending versus resident surgeons. A total of 32 trials would provide 90% power to detect a difference.

RESULTS

Out of 85 passes, 62 were posterior to the suprapubic bone and 20 penetrated the bladder. Trials with versus without bladder penetration were associated with more initial wrist dorsiflexion (-27.32 vs -9.03°, p = 0.01), less final elbow flexion (39.49 vs 60.81, p = 0.03), and greater ROM in both the wrist (27.48 vs 14.01, p = 0.02), and elbow (20.45 vs 12.87, p = 0.04). Wrist deviation and arm pronation were not associated with bladder penetration. Compared with attendings, residents had more ROM in elbow flexion (14.61 vs 8.35°, p < 0.01), but less ROM in wrist dorsiflexion (13.31 vs 20.33, p = 0.02) and arm pronation (4.75 vs 38.46, p < 0.01).

CONCLUSIONS

Bladder penetration during MUS is associated with wrist dorsiflexion and elbow flexion but not internal wrist deviation and arm supination. Attending surgeons exerted control with the wrist and forearm, surgical trainees with the elbow. Our findings have direct implications for MUS teaching.