Artificial intelligence and automation in endoscopy and surgery

Chadebecq, François; Lovat, Laurence; Stoyanov, Danail

doi:10.1038/s41575-022-00701-y

Cited by 51 publications

(20 citation statements)

References 157 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Endoscopy is trending towards miniaturization and high resolution to cope with the development of modern healthcare. [1][2][3] As one of the most important components, endoscopic illumination is realized by coupling a white light source into smalldiameter optical fibre bundles, where the directionality of white light source largely determines the coupling efficiency. Compared to commercial endoscopic light sources, such as white light-emitting diodes (LEDs) and xenon lamps, laser-driven white light, which is realized by pumping laser phosphor converters with blue laser diodes (LDs), possesses advantages of high directionality, high collimation and superior brightness, showing great potential for endoscopic illumination.…”

Section: Introductionmentioning

confidence: 99%

A super-high brightness and excellent colour quality laser-driven white light source enables miniaturized endoscopy

Li¹,

Huang²,

Guo³

et al. 2023

Mater. Horiz.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A super-high brightness and excellent colour quality laser-driven white light source enables miniaturized endoscopy

Li¹,

Huang²,

Guo³

et al. 2023

Mater. Horiz.

View full text Add to dashboard Cite

show abstract

“…If recordings are to be made available to patients, protocols will need to be developed for education, 3 debriefing, and clear communication explaining the content of surgical video recordings, as well as resources to equip surgeons for these discussions. There is potential for streamlining this process as artificial intelligence applications for automated markup and annotation of surgical videos 5 become reliable for most surgical procedures.…”

Section: Pathways Forwardmentioning

confidence: 99%

Navigating a Path Towards Routine Recording in the Operating Room

et al. 2023

View full text Add to dashboard Cite

S urgical video recording has shown promise in identifying best practices, documenting errors, and establishing an objective record of surgical activities for patient care, education, training, and research. 1,2 These opportunities have fueled an increasing number of academic studies, commercial enterprises, and proposed legislation to increase the utilization of recording in the operating room. As recording becomes more routine and expands from intracorporeal images to full room video and audio capture, important ethical, legal, and social issues grow in importance and must now be addressed. This is complex due to phenomena inherent in the surgical process. Patients are unaware of what happens once they are anesthetized, and the modern operating room is closed to nonmedical observers, making the introduction of surveillance and transparency a significant shift in practice. Further, the multisubject nature of procedural recordings-depicting both the patient's body and the surgical team's performance-is a novel consideration for medical data protection and ownership policies. Herein we address uncertainties regarding ownership, liability risk, and privacy, and offer strategies to overcome barriers to routine recording.

show abstract

“…Automated surgical skill evaluation Automated surgical skill evaluation is an active research area, with various approaches proposed for analyzing surgical data using computer vision and machine learning [40,7,21,16,3]. A popular approach is to use hand-crafted features, such as motion analysis or tool usage, to train classifiers for surgical skill assessment.…”

Section: Related Workmentioning

confidence: 99%

OR Vision: Objective, explainable assessment of surgical skill with deep learning

Khalid¹,

Palter²,

Grantcharov³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Currently, evaluating surgical technical performance is inefficient and subjective [1,2,3,4] and the established rubrics for assessing surgical ability are open to interpretation. To power programs for surgical training and Maintenance of Certification (MOC), a reliable and validated solution is required. To this end, we draw upon recent advances in machine learning and propose a framework for objective and scalable assessment of technical proficiency.Methods Different machine learning models were trained to predict surgical performance on the public EndoVis19 and JIGSAWS datasets. The most important features were extracted by probing each machine learning model, and these features form the basis of the proposed algorithm. We internally tested the performance of this model on proprietary datasets from Surgical Safety Technologies (SST) and the University of Texas Southwestern (UTSW). The performance of these models was assessed according to various statistical techniques such as precision, recall, f1-scores and the area under the receiver operating characteristic curve (AUC). Results OR Vision is a statistically-driven multi-stage machine learning tool that quantifies surgical skill objectively and explainably. Instrument motion, control, and coordination are quantified in terms of 150 objective metrics, extracted from tool motion tracked by the deep learning model. The N most highly correlated of these metrics (p<0.05) model surgical performance with quantifiable objective metrics (fine-motor precision, fluidity, tremor, disorder, etc.). These metrics are combined into clinically-weighted composite scores that represent the category-wise technical performance of surgeons. The OR Vision score discriminates between expert and novice surgeons with high precision (0.82-0.84) and provides constructive feedback in the form of a concise report for every participating member of the cohort. Each report provides a breakdown of user performance on statistically relevant categories.ConclusionA machine learning-based approach for identifying surgical skill is effective and meaningful and provides the groundwork for objective, precise, repeatable, cost-effective, clinically-meaningful assessments.

show abstract

Artificial intelligence and automation in endoscopy and surgery

Cited by 51 publications

References 157 publications

A super-high brightness and excellent colour quality laser-driven white light source enables miniaturized endoscopy

A super-high brightness and excellent colour quality laser-driven white light source enables miniaturized endoscopy

Navigating a Path Towards Routine Recording in the Operating Room

OR Vision: Objective, explainable assessment of surgical skill with deep learning

Contact Info

Product

Resources

About