Surgical Innovation最新文献

{"title":"Automatic Detection and Counting of Surgical Instruments in Surgery Using AI-Based Computer Vision Model.","authors":"Yile Zhu, Yun Wu, Xingyu Lai, Shuyi Wang, Yao Zhang, Bin Zheng","doi":"10.1177/15533506261501665","DOIUrl":"https://doi.org/10.1177/15533506261501665","url":null,"abstract":"<p><p>IntroductionCounting surgical instruments during surgical procedures is critical for ensuring patient safety. Our goal is to develop a machine learning-based computer vision algorithm to create a reliable, automated surgical instrument counting support system. We hypothesize that our machine learning algorithm, based on the YOLO (You Only Look Once) model, can effectively perform instrument counting in surgery videos, providing real-time feedback to the surgical team.MethodsYOLO is a real-time object detection algorithm built on a convolutional neural network (CNN). To train the model, we record 100 minutes of open surgery video in simulation, including 600 instrument transfer events. Additionally, we collected 500 images of 6 different surgical instruments and obtained another 500 images from online surgeries. All images were annotated by a human expert to mark the name and locations of instruments. 80% data was allocated for model training and 20% for validation. Trained YOLO model was tested in a new surgical video for counting surgical instruments.ResultsThe model achieved a satisfactory accuracy rate for instrument detection and counting. In a validation session, the model demonstrated a 72.7% success rate. In addition, the model classified large instruments more successfully than smaller instruments, such as small hemostats and needles, within the defined ROI.ConclusionYOLOv11-based computer vision model can accurately detect and count surgical instruments within a predefined region of interest in a simulated open surgical environment. Future research should focus on improving detection of small instruments, validating the system in real operating room environments.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506261501665"},"PeriodicalIF":2.2,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149228707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surgeon-Derived Design Insights Regarding Real-Time Artificial Intelligence Decision Support for Endoscopic Cancer Surgery.","authors":"Cathleen A McCarrick, Samo Erzen, Antonello Forgione, Jacques Marescaux, Ronan A Cahill","doi":"10.1177/15533506261498412","DOIUrl":"https://doi.org/10.1177/15533506261498412","url":null,"abstract":"<p><p>IntroductionReal-time artificial intelligence (AI) decision-support systems are increasingly proposed for use in endoscopic and minimally invasive surgery although how best to present such information intraoperatively is unclear. This study explored surgeon perspectives regarding the user-interface, interpretation and workflow integration of a prototype AI system (CLASSICA-OR) for real-time endoscopic cancer characterization during surgery.MethodsSurgeons specialising in minimally invasive gastrointestinal surgery were asked for their first impressions in their evaluation of the CLASSICA-OR system within a high-fidelity surgical simulation environment. For this, participants viewed prerecorded colonoscopic imagery of significant rectal neoplasia while the AI analysis was applied in real-time to the video. Commentary and responses to semi-structured interview were recorded audiovisually for transcription and analysis using qualitative thematic analysis supported by NVivo (Lumivero).ResultsEighteen surgeons participated, generating rich qualitative data. Four major themes emerged: (1) AI was viewed as a valuable but evolving decision-support tool; (2) institutional culture, governance and commercial realities were recognised as important determinants of adoption; (3) real-time perfusion-based lesion characterisation (foundational to CLASSICA-OR) was considered promising but with specific challenges; and (4) clarity, usability, transparency and workflow compatibility are surgeon priorities in decision-support displays. Participants emphasised minimised cognitive load, preserved surgeon autonomy, clear communication of uncertainty and seamless workflow integration. Preferences differed between simplified binary outputs and more detailed numerical displays supporting the need for adaptable interfaces.ConclusionsSurgeons perceive real-time intraoperative AI decision support as promising but requiring thoughtful user-centred design. They articulate practical development and implementation insights for intraoperative AI systems.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506261498412"},"PeriodicalIF":2.2,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PEEK Pectus Bar: Evaluation of a New Material for Pectus Excavatum Repair in Children and Teenagers.","authors":"Lukas Wolff, Javier Castro, Ilan Rosenberg, Patricio Herrera, Alvaro Paul","doi":"10.1177/15533506261494881","DOIUrl":"https://doi.org/10.1177/15533506261494881","url":null,"abstract":"<p><p>The Nuss procedure for Pectus Excavatum repair has relied on metallic bars for the past 3 decades. The technical efforts have focused on the improvement of stability and the reduction of the associated risks. However, some challenges still remain, like metal ion release, thoracic wall mechanic behavior, and the need for implant remotion. In other areas of surgery, polyetheretherketone (PEEK), a polymer that allows 3D printing, has shown mechanical properties closer to human bone and excellent biocompatibility, becoming an alternative material for medical implants. Herein, we present the mechanic evaluation of a novel PEEK Pectus Bar (PPB) that was manufactured via fused deposition modeling with 100% infill density. Mechanical validation included quasi-static bending tests, cyclic loading, and finite element analysis (FEA). Dynamic impact simulations replicated anterior-posterior thoracic loading to assess energy absorption capacity. The PPB demonstrated linear mechanical response with experimental-FEA correlation using an elastic modulus of 1500 MPa. Cyclic tests revealed characteristic viscoelastic behavior with energy dissipation stabilization and no progressive structural damage. Dynamic impact simulation yielded energy absorption of 14.55 J, comparable to human ribs under similar loading conditions. The 3D-printed PPB exhibits mechanical behavior aligned with human rib compliance while maintaining structural integrity under physiological and high-rate loading, supporting clinical investigation as an alternative to metallic implants.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506261494881"},"PeriodicalIF":2.2,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optical Flow-Derived Motion Biomarkers and Explainable Artificial Intelligence for Quantitative Assessment of Robotic Surgical Expertise.","authors":"Sergey A Shvetsov, Mahsa Kamali","doi":"10.1177/15533506261495652","DOIUrl":"https://doi.org/10.1177/15533506261495652","url":null,"abstract":"<p><p>BackgroundObjective surgical skill evaluation remains challenging in robotic-assisted surgery. Existing artificial intelligence frameworks often depend on robotic telemetry or \"black-box\" deep learning models that reduce interpretability and translational accessibility.MethodsThe present study developed an interpretable computer vision framework for quantitative analysis of robotic surgical motion using dense optical flow-derived biomarkers extracted directly from surgical video recordings. Robotic suturing videos from the publicly available JIGSAWS dataset were analyzed using a Python/OpenCV-based pipeline. Quantitative motion biomarkers, including motion magnitude, temporal variability, jerk-related parameters, and smoothness indices, were extracted and evaluated across expert, intermediate, and novice surgical groups. The paired left and right stereo views were averaged to produce one feature vector for each independent trial. Statistical comparisons were performed using the Kruskal-Wallis test. Skill classification was evaluated using a class-weighted Random Forest classifier with Leave-One-User-Out cross-validation. Model predictions were interpreted using SHapley Additive exPlanations (SHAP).ResultsOptical flow analysis successfully extracted reproducible motion biomarkers associated with surgical expertise. Significant differences were observed in mean motion magnitude (<i>P</i> = .0035), mean absolute jerk (<i>P</i> = .00074), and the unnormalized smoothness index (<i>P</i> = .00074). Motion variability did not differ significantly among the groups after trial-level aggregation (<i>P</i> = .0769). SPARC showed the expected ordering of normalized smoothness, with the highest values among experts, but the group difference was not statistically significant (<i>P</i> = .0647). Principal component analysis demonstrated partial clustering of surgical expertise groups based on extracted motion dynamics. Under Leave-One-User-Out cross-validation, the Random Forest classifier achieved an overall accuracy of 38.5%, a balanced accuracy of 29.5%, a macro-average AUC of 0.401, and a weighted-average AUC of 0.430. Genuine out-of-fold SHAP analysis identified the smoothness index, mean absolute jerk, and mean absolute acceleration as the largest contributors to the model outputs.ConclusionsOptical flow-derived motion biomarkers provide an interpretable characterization of robotic surgical movement directly from video recordings without requiring robotic telemetry. However, the modest performance under user-independent validation indicates that these biomarkers should not yet be used as a standalone measure of surgical expertise. The proposed framework provides a transparent basis for developing and externally validating video-based surgical skill assessment methods.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506261495652"},"PeriodicalIF":2.2,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149138335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short-Term Lower Urinary Tract Symptom Trajectories After Hysterectomy With the Hugo™ RAS System: An Exploratory Secondary Analysis of a Prospective Cohort.","authors":"Ikumi Wada, Hiroaki Komatsu, Yuki Hiratsuka, Koji Yamamoto, Kohei Hikino, Masayo Okawa, Yuki Iida, Mayumi Sawada, Shinya Sato, Fuminori Taniguchi","doi":"10.1177/15533506261495657","DOIUrl":"https://doi.org/10.1177/15533506261495657","url":null,"abstract":"<p><p>BackgroundEvidence for newer robotic platforms has focused primarily on perioperative feasibility. Patient-reported urinary recovery after Hugo™ robotic-assisted surgery (RAS) hysterectomy remains insufficiently characterized.MethodsWe performed an exploratory secondary analysis of prospectively collected outcomes from 45 consecutive Hugo RAS hysterectomies. Operative and learning-curve results from 43 overlapping cases were reported previously and were not reanalyzed. Verified outcomes were OABSS, ICIQ-SF, IPSS, and IPSS-QOL, assessed before surgery and at 1 and 3 months. Complete-case changes were evaluated with Friedman tests and Holm adjustment across four instruments. Eight paired Wilcoxon comparisons were exploratory and Holm-adjusted. Missing values were not imputed.ResultsThe outcome worksheet contained 24 records; scorable baseline data were available for 23 patients, 1-month data for 16-18, and 3-month data for 12-13. Median OABSS was 2.0, 1.0, and 1.0 at baseline, 1 month, and 3 months. Corresponding medians were 0, 0, and 0 for ICIQ-SF; 3.0, 4.5, and 1.5 for IPSS; and 2.0, 2.0, and 1.0 for IPSS-QOL. No global test remained significant after Holm adjustment. The largest exploratory signal was a 1.5-point IPSS increase at 1 month (n = 16; unadjusted <i>P</i> = .013; adjusted <i>P</i> = .101).ConclusionsAmong respondents, urinary symptom burden was low, with no multiplicity-adjusted evidence of persistent change through 3 months. Attrition, absence of a comparator, and cohort overlap preclude platform-specific claims. Larger comparative studies require complete, auditable patient-reported outcomes.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506261495657"},"PeriodicalIF":2.2,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149128608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comment on: Three Versus Two-Rows Circular Stapler in Colorectal Anastomosis: Short Term Outcomes.","authors":"Jeremy Meyer","doi":"10.1177/15533506261425317","DOIUrl":"10.1177/15533506261425317","url":null,"abstract":"<p><p>This letter comments on a recent study comparing two-row and three-row circular staplers in colorectal cancer surgery. We highlight methodological limitations related to the use of historical controls, evolving perioperative practices, and limited event numbers, which may confound the observed reduction in anastomotic leakage. Current evidence does not conclusively support the superiority of triple-row staplers, underscoring the need for prospective studies using standardized modern protocols.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"535-536"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146165919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy of Moth-Eye Technology in Preventing Surgical Loupe Lens Fogging.","authors":"Shinji Tanishima, Katsunori Kimura, Masaru Ueki, Atsuro Koga, Kazutake Uehara, Naofumi Saiki, Hideki Nagashima","doi":"10.1177/15533506261438187","DOIUrl":"10.1177/15533506261438187","url":null,"abstract":"<p><p>Background/NeedSurgical loupe fogging caused by exhaled humid air significantly impairs operative visibility and precision. Existing surfactant-based antifogging agents provide only temporary effects and require repeated application.Methodology and Device DescriptionMoth-eye nanostructure technology was applied to the optical surface using a transparent processed film. The nanoscale pillar array induces superhydrophilicity through a purely physical mechanism, allowing condensed moisture to spread uniformly rather than forming light-scattering droplets.Preliminary ResultsUnder high-humidity conditions, untreated lenses showed marked loss of visual clarity. In contrast, moth-eye-processed lenses consistently preserved transparency, as supported by objective image-based \"color count\" assessment.Current StatusThis technology remains at the proof-of-concept stage and is not commercially available. Ongoing development focuses on direct nanoimprinting onto medical-grade optical devices and evaluation of long-term durability and clinical usability.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"531-534"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147522067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"General Surgery 4.0 - A Systematic Review of Extended Reality Interventions in General Surgery.","authors":"Mikolaj R Kowal, Thomas Williams, Alexios Dosis, Samir Pathak, Shahid Farid, Deborah D Stocken, Peter Lodge, Sharib Ali, Damian Tolan, David G Jayne","doi":"10.1177/15533506251415440","DOIUrl":"10.1177/15533506251415440","url":null,"abstract":"<p><p>BackgroundSurgery is a central component of healthcare but involves significant risks, with complications occurring in 16.4% patients, accounting for 7.7% of worldwide fatalities. \"Surgery 4.0\" or digitisation of surgery, has introduced extended reality (XR) technology, offering opportunities to enhance peri-operative care. This study explored the current uses of XR to improve outcomes for general surgery patients.MethodA systematic search of MEDLINE, EMBASE, and Cochrane databases was performed in August 2024 to include studies using XR for pre-operative planning, navigation or patient experience for adult patients undergoing general surgery. Data on pre-operative planning, post-operative complications, patient experience, image segmentation and study reporting were presented using a narrative approach.ResultsThe search returned 966 articles. 26 studies were included featuring 1142 patients. The most investigated procedure was liver resection (n = 11, 42%), with XR interventions showing significant reductions in length of stay, blood loss, operative time and complication rates. Improved outcomes were only seen for patients undergoing liver resection. For patient experience (n = 5, 19%), XR systems were shown to significantly improve anxiety, pain and mood scores. Most studies (n = 11, 73%%) utilised manual methods for image segmentation, costing up to €650 and taking 3-6 hours per model. Reporting of the XR technology, assessment and future development was variable.ConclusionThe benefits of XR technology to improve patient outcomes in liver surgery are emerging but are yet to materialise in other general surgical procedures. Future research should focus on automatic image segmentation to improve workflow efficiency and innovation frameworks to generate robust evidence.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"517-530"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13428073/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145959609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Video Analysis in Surgery: Lessons From the Pitch?","authors":"Kyle Lam, Andrew Yiu","doi":"10.1177/15533506261437287","DOIUrl":"10.1177/15533506261437287","url":null,"abstract":"","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"537-538"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147491766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Environmental Implications of Discretionary Single-Use Devices in Sleeve Gastrectomy: Exploring the Impact of Inter-Surgeon Variability in a Retrospective Pilot Study.","authors":"Chen Lew, Chunxiao Zhang, Arun Dhir, Dean McKenzie, Laven Padayachee, Hayden Snow, Ben Dunne, Gary Foo","doi":"10.1177/15533506261436861","DOIUrl":"10.1177/15533506261436861","url":null,"abstract":"<p><p>IntroductionOperating theatres contribute disproportionately to healthcare's carbon footprint, with single-use devices (SUDs) representing a major source of waste and emissions. While life cycle assessments (LCAs) quantify product-specific impact, they are often impractical for routine use. This pilot study introduces a framework for assessing inter-surgeon variability in SUD use as a pragmatic consumption-based surrogate marker for environmental burden, offering a scalable and actionable alternative to product-level carbon foot printing.MethodA retrospective study of 125 elective laparoscopic sleeve gastrectomy (LSG) procedures performed by five bariatric surgeons was conducted. Discretionary equipment (DE) use, operative time, and length of stay (LOS) were analysed using Analysis of Means (ANOM) with 99.9% decision limits to assess inter-surgeon variability.ResultsPatient demographics were comparable across surgeons. Mean DE use ranged from 1.9-6.0 items per case, with corresponding cost variation (mean $827.40 overall), and no surgeon's mean fell within decision limits. Operative time varied across surgeons, while LOS ranged from 1.9-3.2 days. Higher discretionary device use was not associated with shorter operative times or reduced LOS.ConclusionSubstantial inter-surgeon variability in discretionary SUD use was observed within a standardised elective procedure. These findings suggest that resource consumption may be driven by individual practice patterns than clinical necessity, identifying a tangible opportunity for sustainability-focused audit and benchmarking. By adopting consumption-based procedural metrics as a practical alternative to product-level carbon foot printing, surgical teams can begin addressing environmental impact using routine workflows. Future studies incorporating complication rates and direct environmental measurements will clarify the long-term implications of lower-intensity device utilisation.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"466-474"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147504779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}