Dataset Information

ClipAssistNet: bringing real-time safety feedback to operating rooms.

ABSTRACT:

Purpose

Cholecystectomy is one of the most common laparoscopic procedures. A critical phase of laparoscopic cholecystectomy consists in clipping the cystic duct and artery before cutting them. Surgeons can improve the clipping safety by ensuring full visibility of the clipper, while enclosing the artery or the duct with the clip applier jaws. This can prevent unintentional interaction with neighboring tissues or clip misplacement. In this article, we present a novel real-time feedback to ensure safe visibility of the instrument during this critical phase. This feedback incites surgeons to keep the tip of their clip applier visible while operating.

Methods

We present a new dataset of 300 laparoscopic cholecystectomy videos with frame-wise annotation of clipper tip visibility. We further present ClipAssistNet, a neural network-based image classifier which detects the clipper tip visibility in single frames. ClipAssistNet ensembles predictions from 5 neural networks trained on different subsets of the dataset.

Results

Our model learns to classify the clipper tip visibility by detecting its presence in the image. Measured on a separate test set, ClipAssistNet classifies the clipper tip visibility with an AUROC of 0.9107, and 66.15% specificity at 95% sensitivity. Additionally, it can perform real-time inference (16 FPS) on an embedded computing board; this enables its deployment in operating room settings.

Conclusion

This work presents a new application of computer-assisted surgery for laparoscopic cholecystectomy, namely real-time feedback on adequate visibility of the clip applier. We believe this feedback can increase surgeons' attentiveness when departing from safe visibility during the critical clipping of the cystic duct and artery.

SUBMITTER: Aspart F

PROVIDER: S-EPMC8739308 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundPrevious systematic reviews have failed to find an association between the use of real-time feedback during cardiopulmonary resuscitation (CPR) and patient outcomes. However, these reviews excluded studies examining feedback with other system changes. As part of the International Liaison Committee on Resuscitation (ILCOR) continuous evidence evaluation process, we conducted a scoping review to examine the current state of this literature and the use of real-time feedback in this form.Methods/data sourcesA protocol and search strategy was developed. We searched Medline, EMBASE, and Allied Health Literature (CINAHL) from inception to May 2024. Cochrane (Cochrane (specifically, the Cochrane Database of Systematic Reviews) is contained in Medline so was not searched separately. Studies were eligible for inclusion if they were published or unpublished (grey-literature) studies involving children or adults that examined the effect of real-time feedback or prompting on the quality of CPR following cardiac arrest. Data were extracted and audited independently. For each study, the following information were extracted: the author(s); year of publication; timeframe; study design; country; population; intervention and comparator; type of feedback or prompt; outcomes measured; main findings for CPR quality, and; main findings for patient outcomes. Reviewers also allocated key themes to each study and held a series of consensus discussions to consolidate themes across the included studies.ResultsWe screened 2,657 titles and included 60 studies. Our analysis identified five overlapping themes in the extended literature: system change and quality improvement; impact on patient outcomes; better CPR quality without improved patient outcome; CPR feedback as a generator of other CPR metrics; and CPR feedback as a potential harm. Results revealed a substantial adjacent literature, particularly on implementing high-performance CPR as part of quality improvement programs.ConclusionsThis scoping review has identified a large body of literature and specific themes of interest in relation to feedback for CPR quality. Future systematic reviews should include studies examining real-time feedback with other system changes.