SAGES video acquisition framework-analysis of available OR recording technologies by the SAGES AI task force.

BACKGROUND: Surgical video recording provides the opportunity to acquire intraoperative data that can subsequently be used for a variety of quality improvement, research, and educational applications. Various recording devices are available for standard operating room camera systems. Some allow for collateral data acquisition including activities of the OR staff, kinematic measurements (motion of surgical instruments), and recording of the endoscopic video streams. Additional analysis through computer vision (CV), which allows software to understand and perform predictive tasks on images, can allow for automatic phase segmentation, instrument tracking, and derivative performance-geared metrics. With this survey, we summarize available surgical video acquisition technologies and associated performance analysis platforms. METHODS: In an effort promoted by the SAGES Artificial Intelligence Task Force, we surveyed the available video recording technology companies. Of thirteen companies approached, nine were interviewed, each over an hour-long video conference. A standard set of 17 questions was administered. Questions spanned from data acquisition capacity, quality, and synchronization of video with other data, availability of analytic tools, privacy, and access. RESULTS: Most platforms (89%) store video in full-HD (1080p) resolution at a frame rate of 30 fps. Most (67%) of available platforms store data in a Cloud-based databank as opposed to institutional hard drives. CV powered analysis is featured in some platforms: phase segmentation in 44% platforms, out of body blurring or tool tracking in 33%, and suture time in 11%. Kinematic data are provided by 22% and perfusion imaging in one device. CONCLUSION: Video acquisition platforms on the market allow for in depth performance analysis through manual and automated review. Most of these devices will be integrated in upcoming robotic surgical platforms. Platform analytic supplementation, including CV, may allow for more refined performance analysis to surgeons and trainees. Most current AI features are related to phase segmentation, instrument tracking, and video blurring.

A systematic review of annotation for surgical process model analysis in minimally invasive surgery based on video.

BACKGROUND: Annotated data are foundational to applications of supervised machine learning. However, there seems to be a lack of common language used in the field of surgical data science. The aim of this study is to review the process of annotation and semantics used in the creation of SPM for minimally invasive surgery videos. METHODS: For this systematic review, we reviewed articles indexed in the MEDLINE database from January 2000 until March 2022. We selected articles using surgical video annotations to describe a surgical process model in the field of minimally invasive surgery. We excluded studies focusing on instrument detection or recognition of anatomical areas only. The risk of bias was evaluated with the Newcastle Ottawa Quality assessment tool. Data from the studies were visually presented in table using the SPIDER tool. RESULTS: Of the 2806 articles identified, 34 were selected for review. Twenty-two were in the field of digestive surgery, six in ophthalmologic surgery only, one in neurosurgery, three in gynecologic surgery, and two in mixed fields. Thirty-one studies (88.2%) were dedicated to phase, step, or action recognition and mainly relied on a very simple formalization (29, 85.2%). Clinical information in the datasets was lacking for studies using available public datasets. The process of annotation for surgical process model was lacking and poorly described, and description of the surgical procedures was highly variable between studies. CONCLUSION: Surgical video annotation lacks a rigorous and reproducible framework. This leads to difficulties in sharing videos between institutions and hospitals because of the different languages used. There is a need to develop and use common ontology to improve libraries of annotated surgical videos.

Evolution of the digital operating room: the place of video technology in surgery.

PURPOSE: The aim of this review was to collate current evidence wherein digitalisation, through the incorporation of video technology and artificial intelligence (AI), is being applied to the practice of surgery. Applications are vast, and the literature investigating the utility of surgical video and its synergy with AI has steadily increased over the last 2 decades. This type of technology is widespread in other industries, such as autonomy in transportation and manufacturing. METHODS: Articles were identified primarily using the PubMed and MEDLINE databases. The MeSH terms used were "surgical education", "surgical video", "video labelling", "surgery", "surgical workflow", "telementoring", "telemedicine", "machine learning", "deep learning" and "operating room". Given the breadth of the subject and the scarcity of high-level data in certain areas, a narrative synthesis was selected over a meta-analysis or systematic review to allow for a focussed discussion of the topic. RESULTS: Three main themes were identified and analysed throughout this review, (1) the multifaceted utility of surgical video recording, (2) teleconferencing/telemedicine and (3) artificial intelligence in the operating room. CONCLUSIONS: Evidence suggests the routine collection of intraoperative data will be beneficial in the advancement of surgery, by driving standardised, evidence-based surgical care and personalised training of future surgeons. However, many barriers stand in the way of widespread implementation, necessitating close collaboration between surgeons, data scientists, medicolegal personnel and hospital policy makers.

Combined telovelar posterolateral (far lateral) approach for the resection of a large posterior fossa ependymoma: how I do it.

BACKGROUND: Ependymomas are glial cell tumors whose recommended treatment, according to the recent European guidelines, is surgical. Patient outcomes, in terms of progression-free survival and overall survival, are strongly related to the extent of resection. However, in some cases, critical locations and/or large dimensions could make a gross total resection challenging. In this article, we describe the surgical anatomy and technique of a combined telovelar-posterolateral approach for the resection of a giant posterior fossa ependymoma. METHODS: A 24-year-old patient who presented to our institution complaining of a 3-month history of headache, vertigo, and imbalance. Preoperative MRI scans showed a large mass within the fourth ventricle, extending towards the left cerebellopontine angle and perimedullary space through the homolateral Luschka foramen. Surgical treatment was proposed with the aims of releasing the preoperative symptoms, obtaining the tumor's histopathological and molecular definition, and preventing any future neurological deterioration. The patient gave his written consent for surgery and consented to the publication of his images. A combined telovelar-posterolateral approach was then performed to maximize the tumor's exposure and resection. Surgical technique and anatomical exposure have been extensively described, and a 2-dimensional operative video has been included. RESULTS: The postoperative MRI scan demonstrated an almost complete resection of the lesion, with only a millimetric tumor remnant infiltrating the uppermost portion of the inferior medullary velum. Histo-molecular analysis revealed a grade 2 ependymoma. The patient was discharged home neurologically intact. CONCLUSIONS: The combined telovelar-posterolateral approach allowed to achieve a near total resection of a giant multicompartimental mass within the posterior fossa in a single surgical stage.

Learning Surgical Skills Through Video-Based Education: A Systematic Review.

BACKGROUND: Educational videos are a potent resource for the learning of surgical skills among different study cohorts. However, there is limited evidence on the effectiveness of different educational video interventions and their features.A systematic search of MEDLINE (via PubMed), Embase (via OVID), Cochrane libraries and Clinicaltrials.gov was performed from inception to 28/02/21. Studies included were not limited by date of publication, studies aiming to assess the impact of video-based interventions in the direct acquisition of surgical skill were included. Eligible studies were analysed based on study type, type of video intervention, method of assessment and period of education. The educational impact of the studies was also assessed as per Messick's framework for testing validity of evaluation methods and McGhagie's model for analysing translational outcomes.22 studies were deemed suitable for inclusion, of which 14/22 (63.6%) demonstrated a significant improvement in knowledge/skills following the video-based teaching interventions, 3/22 (13.6%) studies demonstrated an improvement in trainee satisfaction scores. A recurrent limitation of the included studies was the lack of validation of selected assessment methods. None of the included studies scored on all 5 parameters of validity as defined by Messicks validity framework. Furthermore, none of the included trials were conducted for long enough to indicate direct changes to patient outcomes resultant from educational methods. CONCLUSION: Video-based surgical education is effective in learning surgical skills within different levels of surgical training; however, superior study quality and follow-up is required to determine which aspects of video-based interventions are most impactful.

Code-free machine learning for object detection in surgical video: a benchmarking, feasibility, and cost study.

OBJECTIVE: While the utilization of machine learning (ML) for data analysis typically requires significant technical expertise, novel platforms can deploy ML methods without requiring the user to have any coding experience (termed AutoML). The potential for these methods to be applied to neurosurgical video and surgical data science is unknown. METHODS: AutoML, a code-free ML (CFML) system, was used to identify surgical instruments contained within each frame of endoscopic, endonasal intraoperative video obtained from a previously validated internal carotid injury training exercise performed on a high-fidelity cadaver model. Instrument-detection performances using CFML were compared with two state-of-the-art ML models built using the Python coding language on the same intraoperative video data set. RESULTS: The CFML system successfully ingested surgical video without the use of any code. A total of 31,443 images were used to develop this model; 27,223 images were uploaded for training, 2292 images for validation, and 1928 images for testing. The mean average precision on the test set across all instruments was 0.708. The CFML model outperformed two standard object detection networks, RetinaNet and YOLOv3, which had mean average precisions of 0.669 and 0.527, respectively, in analyzing the same data set. Significant advantages to the CFML system included ease of use, relatively low cost, displays of true/false positives and negatives in a user-friendly interface, and the ability to deploy models for further analysis with ease. Significant drawbacks of the CFML model included an inability to view the structure of the trained model, an inability to update the ML model once trained with new examples, and the inability for robust downstream analysis of model performance and error modes. CONCLUSIONS: This first report describes the baseline performance of CFML in an object detection task using a publicly available surgical video data set as a test bed. Compared with standard, code-based object detection networks, CFML exceeded performance standards. This finding is encouraging for surgeon-scientists seeking to perform object detection tasks to answer clinical questions, perform quality improvement, and develop novel research ideas. The limited interpretability and customization of CFML models remain ongoing challenges. With the further development of code-free platforms, CFML will become increasingly important across biomedical research. Using CFML, surgeons without significant coding experience can perform exploratory ML analyses rapidly and efficiently.

The age of surgical operative video big data - My bicycle or our park?

BACKGROUND: Surgery is a major component of health-care provision. Operative intervention often employs minimally invasive approaches incorporating digital cameras creating a 'digital twin' of both intracorporeal appearances and operative performance. Video recordings provide richer detail than the traditional operative note and can couple with advanced computer technology to unlock new analytic capabilities capable of driving surgical advancement via quality improvement initiatives and new technology design. Surgical video is however an under-utilized technology resource, in part, because ownership along with broader issues including purpose, privacy, confidentiality, copyright and inclusion in outputs have been poorly considered using outdated categorisation. METHOD: A first principles perspective on operative video classification as a useful public interest resource enshrining fundamental stakeholder (patients, physicians, institutions, industry and society) rights, roles and responsibilities. RESULT: A facility of noble purpose, understandable to all, for fair, accountable, safe and transparent access to large volumes of anonymised surgical videos of intracorporeal operations that enables advances through cross-disciplinary research is proposed. Technology can be exploited to protect all relevant parties respecting both citizen data-rights and the special status doctor-patient relationship. Through general consensus, the capability can be understood, established and iterated to perfection. CONCLUSION: Overall we argue that new and specific classification of surgical video enables responsible curation and serves the public good better than the current model. Rather than being thought of as a bicycle where discrete ownership is ascribed, such data are better viewed as being more like a park, a regulated amenity we should preserve for better human life.

How to Shoot and Edit High-Quality Surgical Videos for Hand and Upper Extremity Surgery.

A surgical video can improve patient care, surgical education, as well as scientific presentations and publications. Previous authors have outlined a basic understanding of how to produce high-quality surgical videos. With continuous technological improvements in video-filming hardware and editing software, multiple options for producing high-quality surgical videos are available. This article described important aspects of filming and editing videos to create a video that the surgeon can watch before performing the procedure. The authors reviewed camera terminology, including resolution, optical and digital zoom, shutter speed, and frame rate, as well as equipment options or setup for recording high-quality surgical videos. We provided information regarding computer requirements and editing on Windows and Macintosh operating systems, optimizing educational value for the viewer.

Evaluation of the educational quality and reliability of YouTube videos addressing eyelid ptosis surgery.

PURPOSE: To evaluate the educational content, quality, and reliability of YouTube videos addressing anterior approach ptosis surgery. METHODS: A search on YouTube using the term "ptosis surgery" was performed between March 20 and March 26 2021. The quality, reliability, and accuracy of the contents of 38 videos meeting the inclusion criteria were evaluated by two independent ophthalmologists using the DISCERN questionnaire and the Journal of the American Medical Association (JAMA) benchmark criteria. The Global Quality Score (GQS) and a surgical scoring system were used to assess the educational value of the content. RESULTS: The mean DISCERN score was 32.8 ± 10, and the mean JAMA score was 1.3 ± 0.5, indicating poor quality; the mean global quality score was 3.1 ± 1.1, indicating moderate quality; and the mean surgical score was 7.5 ± 2.7, indicating moderate to good quality. The surgical, DISCERN, and GQS scores of the videos uploaded by physicians were significantly higher than those of the videos uploaded by private clinics (p = .015, p= .049, and p= .01, respectively). There was a significant positive correlation between the surgical, DISCERN, JAMA, and GQS scores (p< .001). A significant positive correlation was found between video duration and surgical score (p= .013), DISCERN score (p ˂0.001), and GQS score (p ˂0.001). CONCLUSION: Videos with known sources, uploaded by physicians, and supported by audio narration may be useful in obtaining educational information. However, the available videos are not a reliable source of educational information about ptosis surgery.

SAGES consensus recommendations on an annotation framework for surgical video.

BACKGROUND: The growing interest in analysis of surgical video through machine learning has led to increased research efforts; however, common methods of annotating video data are lacking. There is a need to establish recommendations on the annotation of surgical video data to enable assessment of algorithms and multi-institutional collaboration. METHODS: Four working groups were formed from a pool of participants that included clinicians, engineers, and data scientists. The working groups were focused on four themes: (1) temporal models, (2) actions and tasks, (3) tissue characteristics and general anatomy, and (4) software and data structure. A modified Delphi process was utilized to create a consensus survey based on suggested recommendations from each of the working groups. RESULTS: After three Delphi rounds, consensus was reached on recommendations for annotation within each of these domains. A hierarchy for annotation of temporal events in surgery was established. CONCLUSIONS: While additional work remains to achieve accepted standards for video annotation in surgery, the consensus recommendations on a general framework for annotation presented here lay the foundation for standardization. This type of framework is critical to enabling diverse datasets, performance benchmarks, and collaboration.

Surgical Video Tutorial: Treatment of Congenital Vaginal Agenesis: Laparoscopic Modified Davydov in 8 Steps.

OBJECTIVE: To describe the different steps of the Davydov surgical technique for creating a neovagina, emphasizing visualization of the rectovesical cleavage and peritoneal-vaginal anastomosis by laparoscopic and vaginal approaches. DESIGN: Production of a step-by-step surgical video tutorial with narrative video footage. SETTING: Uterovaginal agenesis is a rare congenital defect, observed in 1 case per 4000 to 5000 newborn female infants [1]. Vaginal agenesis treatment can be performed by different nonsurgical and surgical techniques that are based on neocavity creation. The Davydov intervention uses the pelvic peritoneum as "covering" tissue for a neocavity and avoids the use of allogenic or autologous transplants, traction devices, or specialized surgical equipment. It is a minimally invasive technique that provides long-term functionality and anatomically satisfying results [2]. INTERVENTIONS: We treated an 18-year-old patient with Mayer-Rokitansky-Küster-Hauser syndrome who underwent the Davydov procedure after dissatisfaction with the Franck self-expansion method. We created a neovagina using peritoneal flaps that were obtained after rectovesical cleavage by laparoscopic approach and were then fastened to the introitus by vaginal approach. Finally, the vaginal vault was reconstructed laparoscopically, and an intravaginal dilator was left in place. The result after 1 year showed the transition from a narrow vaginal dimple 2 cm in length to a neovagina 10 cm in length, permeable, well epithelialized, and correctly healed without associated stenosis. Sexual intercourse is satisfying for both partners. CONCLUSION: The Davydov technique is less invasive than other surgical techniques and allows good outcomes [3,4] without the invasive use of sigmoidal grafts, cutaneous flaps, or prostheses. It should be proposed to patients experiencing failure with the Franck nonsurgical method.

A new technique of laparoscopic fixation of the uterus to the anterior abdominal wall with the use of overfascial mesh in the treatment of pelvic organ prolapse.

INTRODUCTION AND HYPOTHESIS: Pelvic organ prolapse is one of the most common pathological conditions in postmenopausal women. There is still a lack of fully effective and safe surgical techniques, especially in the advanced stages of apical defects. The purpose of the video is to present a new technique of laparoscopic treatment in women with an advanced stage of genital prolapse, stage III and IV according to the POP-Q scale. The technique involves uterine fixation for the anterior abdominal wall using overfascial mesh. METHODS: We used a live-action surgical demonstration to describe laparoscopic fixation of the uterus to the anterior abdominal wall with the use of overfascial mesh. RESULTS: This video provides a step-by-step approach to laparoscopic fixation of the uterus to the anterior abdominal wall with the use of overfascial mesh. The video can be used to educate and train those performing female pelvic reconstructive surgery. CONCLUSIONS: Based on our experience, this technique of laparoscopic suspension of the uterus to the anterior abdominal wall with the use of overfascial mesh is an effective, safe, and easy procedure for the treatment of advanced stages of pelvic organ prolapse.

Ventral-onlay buccal mucosal graft urethroplasty for the treatment of female urethral stricture: a step-by-step video for Female Pelvic Reconstructive Surgeons.

INTRODUCTION AND HYPOTHESIS: Female urethral stricture is a relatively uncommon disease. Conservative management with repeated urethral dilation often leads to unsatisfactory results. Although treatment of female urethral stricture with urethral reconstruction using a variety of surgical techniques is a surgical option, female pelvic reconstructive surgeons have limited exposure to these procedures in their training. The purpose of this video is to demonstrate a step-by-step ventral-onlay buccal mucosal graft urethroplasty in a patient with female urethral stricture disease. METHODS: We use a live action surgical video to describe the harvest of a buccal mucosal graft and ventral-onlay urethroplasty. RESULTS: This video provides a step-by-step approach to a ventral urethroplasty using a buccal mucosal graft. It can be used to educate and train those performing female pelvic reconstructive surgery. CONCLUSION: Pelvic surgeons should be familiar with the management of female urethral stricture, including surgical treatment options such as urethral reconstruction. This video may be used to facilitate the reproducibility and comprehension of the ventral urethroplasty procedure.

Transvaginal bladder-neck closure: a step-by-step video for female pelvic surgeons.

INTRODUCTION AND HYPOTHESIS: Transvaginal bladder-neck closure is a definitive surgical option for urethral erosion due chronic bladder catheterization in patients with neurogenic bladder. Surgeons who perform female pelvic reconstructive surgery have limited exposure to this procedure in their training. The purpose of this video is to demonstrate a transvaginal bladder-neck closure due to urethral erosion in a patient with neurogenic bladder due to persistent neuropathy from Guillain-Barré syndrome managed with prolonged catheter drainage. METHODS: We used a live-action surgical demonstration to describe transvaginal bladder-neck closure with urinary diversion. RESULTS: This video provides a step-by-step approach to transvaginal bladder-neck closure as treatment for urethral erosion from chronic catheterization. This video can be used to educate and train those performing female pelvic reconstructive surgery. CONCLUSIONS: Surgeons who perform female pelvic surgery should be familiar with the complications of chronic Foley catheterization and treatment options that include transvaginal bladder-neck closure. This video may be used to facilitate reproducibility and comprehension of this procedure.

How I do it: total uncinatectomy during anterior diskectomy and fusion for cervical radiculopathy caused by uncovertebral joint hypertrophy.

BACKGROUND: Cervical radiculopathy from uncovertebral joint hypertrophy and foraminal stenosis is a common indication for anterior cervical diskectomy and fusion (ACDF). Often, the uncinate hypertrophy extends lateral to the foramen and impinges on the nerve close to the vertebral artery as it travels in between the transverse foramina. METHOD: Using an injected cadaveric specimen to highlight the vital neurovascular and bony structures pertinent to this procedure, we demonstrate the technical details of complete uncinatectomy for cervical foraminal stenosis. CONCLUSION: Total uncinatectomy is a useful adjunct during ACDF for complete foraminal decompression in cases of uncovertebral joint hypertrophy.

Video Technologies for Recording Open Surgery: A Systematic Review.

Video recording of surgical procedures is an important tool for surgical education, performance enhancement, and error analysis. Technology for video recording open surgery, however, is limited. The objective of this article is to provide an overview of the available literature regarding the various technologies used for intraoperative video recording of open surgery. A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines using the MEDLINE, Cochrane Central, and EMBASE databases. Two authors independently screened the titles and abstracts of the retrieved articles, and those that satisfied the defined inclusion criteria were selected for a full-text review. A total of 2275 publications were initially identified, and 110 were included in the final review. The included articles were categorized based on type of article, surgical subspecialty, type and positioning of camera, and limitations identified with their use. The most common article type was primary-technical (29%), and the dominant specialties were general surgery (22%) and plastic surgery (18%). The most commonly cited camera used was the GoPro (30%) positioned in a head-mount configuration (60%). Commonly cited limitations included poor video quality, inadequate battery life, light overexposure, obstruction by surgical team members, and excessive motion. Open surgery remains the mainstay of many surgical specialties today, and technological innovation is absolutely critical to fulfill the unmet need for better video capture of open surgery. The findings of this article will be valuable for guiding future development of novel technology for this purpose.

Mobile technology for recording surgical procedures.

Mobile technology has been advancing in countless directions, and in particular medicine has been an attractive place for mobile technology innovators. The recording of surgical procedures, however, has not been one of those directions, possibly because there is a lack of software specifically designed for recording open surgical procedures. Using an iPhone SE as the device to record video along with an app devised by one of the authors, five cases of various neck surgeries (two submandibular gland resections, two neck dissections, one neck dissection and supraglottic laryngectomy) were recorded. The authors were able to completely record four out of the five cases. One case was not recorded due to storage insufficiency on the device. The recorded images were evaluated by a jury comprised of three people, and according to their findings the image quality was of an acceptable level. The authors conclude that, with a specifically devised app and a smartphone with sufficient storage capacity, surgical video recordings are possible. Specific precautions will need to be taken to ensure the privacy of these medical records. Once that is done, it is possible to use a smartphone to provide a convenient and affordable way of recording surgical procedures.

Ergonomics: making the OR a comfortable place.

INTRODUCTION: The objective of this video is to highlight strategies to improve operating room (OR) ergonomics, which will result in increased surgeon comfort during minimally invasive gynecologic surgery and decreased risk of musculoskeletal injury. METHODS: Work-related musculoskeletal disorders (WMSDs) are prevalent among surgeons, including those who perform minimally invasive gynecologic surgery. WMSDs are repetitive strain injuries that can damage a surgeon's muscles, nerves, and/or joints and commonly affect the neck, back, wrist, and hands. In addition to chronic pain, these injuries can lead to decreased job satisfaction and productivity. RESULTS: This video will discuss general ergonomic principles and demonstrate ergonomic techniques in conventional laparoscopic, vaginal, and robotic surgery. CONCLUSIONS: Minimally invasive gynecologic surgery can be physically taxing on the surgeon. Understanding principles and utilizing techniques of OR ergonomics can minimize these physical demands and result in a long, healthy, and pain-free surgical career.

LeFort colpocleisis: a step-by-step simulation video for Female Pelvic Surgeons.

INTRODUCTION AND HYPOTHESIS: LeFort colpocleisis is a minimally invasive surgical option for patients with pelvic organ prolapse who no longer desire sexual activity. Pelvic surgeons have limited exposure to this procedure during their training, and are therefore less likely to offer this procedure to their patients. METHODS: We use a split screen live action surgery, side by side with a low cost 3D model of a prolapse to describe a LeFort colpocleisis step by step. RESULTS: This video is an easily reproducible guide to the steps and surgical techniques necessary to successfully perform a LeFort colpocleisis. The simulation model can be used to educate and train those performing female pelvic surgery. CONCLUSION: Pelvic surgeons should be able to offer LeFort colpocleisis to their patients. This video may be used to facilitate the understanding and reproducibility of the procedure.