Barriers to the adoption of routine surgical video recording: a mixed-methods qualitative study of a real-world implementation of a video recording platform.

BACKGROUND: Routine surgical video recording has multiple benefits. Video acts as an objective record of the operative record, allows video-based coaching and is integral to the development of digital technologies. Despite these benefits, adoption is not widespread. To date, only questionnaire studies have explored this failure in adoption. This study aims to determine the barriers and provide recommendations for the implementation of routine surgical video recording. MATERIALS AND METHODS: A pre- and post-pilot questionnaire surrounding a real-world implementation of a C-SATS©, an educational recording and surgical analytics platform, was conducted in a university teaching hospital trust. Usage metrics from the pilot study and descriptive analyses of questionnaire responses were used with the non-adoption, abandonment, scale-up, spread, sustainability (NASSS) framework to create topic guides for semi-structured interviews. Transcripts of interviews were evaluated in an inductive thematic analysis. RESULTS: Engagement with the C-SATS© platform failed to reach consistent levels with only 57 videos uploaded. Three attending surgeons, four surgical residents, one scrub nurse, three patients, one lawyer, and one industry representative were interviewed, all of which perceived value in recording. Barriers of 'change,' 'resource,' and 'governance,' were identified as the main themes. Resistance was centred on patient misinterpretation of videos. Participants believed availability of infrastructure would facilitate adoption but integration into surgical workflow is required. Regulatory uncertainty was centred around anonymity and data ownership. CONCLUSION: Barriers to the adoption of routine surgical video recording exist beyond technological barriers alone. Priorities for implementation include integration recording into the patient record, engaging all stakeholders to ensure buy-in, and formalising consent processes to establish patient trust.

Non-relevant segment recognition via hard example mining under sparsely distributed events.

We propose on/offline hard example mining (HEM) techniques to alleviate the degradation of the generalization performance in the sparse distribution of events in non-relevant segment (NRS) recognition and to examine their utility for long-duration surgery. Through on/offline HEM, higher recognition performance can be achieved by extracting hard examples that help train NRS events, for a given training dataset. Furthermore, we provide two performance measurement metrics to quantitatively evaluate NRS recognition in the clinical field. The existing precision and recall-based performance measurement method provides accurate quantitative statistics. However, it is not an efficient evaluation metric in tasks where false positive recognition errors are fatal, such as NRS recognition. We measured the false discovery rate (FDR) and threat score (TS) to provide quantitative values that meet the needs of the clinical setting. Finally, unlike previous studies, the utility of NRS recognition was improved by applying our model to long-duration surgeries, instead of short-length surgical operations such as cholecystectomy. In addition, the proposed training methodology was applied to robotic and laparoscopic surgery datasets to verify that it can be robustly applied to various clinical environments.

Surgical technique: Posterior retropleural thoracotomy for resection of a T10 dumbbell schwannoma.

Background: Myelopathy and nerve root dysfunction resulting from the imperceptible growth of intraspinal schwannomas have been well documented.[1] Thoracic spine schwannomas, in particular, have exceptional growth potential due to the presence of the posterior mediastinum and retropleural spaces accommodating insidious and often subclinical tumor expansion.[5] Extraspinal extension of these lesions, however, poses a distinct challenge for surgeons.[3,4]. Case Description: Here, we provide a two-dimensional intraoperative video demonstrating the technical nuances concerning maximally safe resection of a partially cystic thoracic dumbbell schwannoma having extraspinal extension with associated bony remodeling of the T10 vertebral body and neural foramen in a middle-aged male. A posterolateral approach with T8-T12 fusion, retropleural thoracotomy, facetectomies, and pediculectomies allowed for gross total resection. No intraoperative or postoperative complications were observed, and the parietal pleura was kept intact throughout the surgery. In addition, the patient continued to have improved symptoms and was ambulatory at 6-month follow-up. Conclusion: Gross total resection of a partially cystic thoracic dumbbell schwannoma was achieved without complications. Our use of a preoperative three-dimensional reconstruction for surgical planning,[2] intraoperative ultrasound,[6] and a durable instrumentation construct were essential for a successful outcome. Moreover, great care was taken to avoid violating the tumor-parietal pleura plane, which would have resulted in postoperative respiratory complications.

An Automated Video Analysis System for Retrospective Assessment and Real-Time Monitoring of Endoscopic Procedures (with Video).

BACKGROUND AND AIMS: Accurate recognition of endoscopic instruments facilitates quantitative evaluation and quality control of endoscopic procedures. However, no relevant research has been reported. In this study, we aimed to develop a computer-assisted system, EndoAdd, for automated endoscopic surgical video analysis based on our dataset of endoscopic instrument images. METHODS: Large training and validation datasets containing 45,143 images of 10 different endoscopic instruments and a test dataset of 18,375 images collected from several medical centers were used in this research. Annotated image frames were used to train the state-of-the-art object detection model, YOLO-v5, to identify the instruments. Based on the frame-level prediction results, we further developed a hidden Markov model to perform video analysis and generate heatmaps to summarize the videos. RESULTS: EndoAdd achieved high accuracy (>97%) on the test dataset for all 10 endoscopic instrument types. The mean average accuracy, precision, recall, and F1-score were 99.1%, 92.0%, 88.8%, and 89.3%, respectively. The area under the curve values exceeded 0.94 for all instrument types. Heatmaps of endoscopic procedures were generated for both retrospective and real-time analyses. CONCLUSIONS: We successfully developed an automated endoscopic video analysis system, EndoAdd, which supports retrospective assessment and real-time monitoring. It can be used for data analysis and quality control of endoscopic procedures in clinical practice.

Bilateral Singapore fasciocutaneous flap after anterior vulvectomy and distal urethrectomy for localized recurrent vulvar carcinoma.

Introduction: Vulvar cancer has an overall low incidence, accounting for approximately 3-5% of all gynecological malignancies.Case: We present a case of locally recurrent Stage IIIA squamous cell carcinoma of the vulva in a 51-year-old healthy African American female. She was initially treated with primary chemoradiation with cisplatin sensitization and boost to primary tumor up to 70 Gray. Post-treatment biopsies revealed complete pathologic response. She later presented with local recurrence to the primary site of the clitoris and vulva, with no evidence of metastasis on imaging, with progressive disease despite treatment with immunotherapy. Methods: Biopsy-proven disease progression was present on the clitoris, entire left labia minora, and a portion of the right labia minora with no evidence of metastasis on imaging. Surgical resection for localized recurrence was recommended, and she underwent radical anterior vulvectomy, distal urethrectomy, and vulvar reconstruction with bilateral Singapore fasciocutaneous flap as part of a multidisciplinary team. Patient underwent several prophylactic hyperbaric oxygen treatments. There were no issues with postoperative wound healing. Conclusion: Treatment with radical excision often requires multidisciplinary teams for complex reconstructions to restore vulvar anatomy in the setting of prior radiation, especially for those patients desiring the ability to have penetrative intercourse in the future. There are few surgical videos that describe these types of vulvar excisions and subsequent reconstructions. This video provides a unique approach to vulvar reconstruction in a previously irradiated field.

Optimizing latent graph representations of surgical scenes for unseen domain generalization.

PURPOSE: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and patient demographics. Recently, object-centric learning has emerged as a promising approach for improved surgical scene understanding, capturing and disentangling visual and semantic properties of surgical tools and anatomy to improve downstream task performance. In this work, we conduct a multicentric performance benchmark of object-centric approaches, focusing on critical view of safety assessment in laparoscopic cholecystectomy, then propose an improved approach for unseen domain generalization. METHODS: We evaluate four object-centric approaches for domain generalization, establishing baseline performance. Next, leveraging the disentangled nature of object-centric representations, we dissect one of these methods through a series of ablations (e.g., ignoring either visual or semantic features for downstream classification). Finally, based on the results of these ablations, we develop an optimized method specifically tailored for domain generalization, LG-DG, that includes a novel disentanglement loss function. RESULTS: Our optimized approach, LG-DG, achieves an improvement of 9.28% over the best baseline approach. More broadly, we show that object-centric approaches are highly effective for domain generalization thanks to their modular approach to representation learning. CONCLUSION: We investigate the use of object-centric methods for unseen domain generalization, identify method-agnostic factors critical for performance, and present an optimized approach that substantially outperforms existing methods.

Parameter-efficient framework for surgical action triplet recognition.

PURPOSE: Surgical action triplet recognition is a clinically significant yet challenging task. It provides surgeons with detailed information about surgical scenarios, thereby facilitating clinical decision-making. However, the high similarity among action triplets presents a formidable obstacle to recognition. To enhance accuracy, prior methods necessitated the utilization of larger models, thereby incurring a considerable computational burden. METHODS: We propose a novel framework known as the Lite and Mega Models (LAM). It comprises a CNN-based fully fine-tuned model (LAM-Lite) and a parameter-efficient fine-tuned model based on the foundation model using Transformer architecture (LAM-Mega). Temporal multi-label data augmentation is introduced for extracting robust class-level features. RESULTS: Our study demonstrates that LAM outperforms prior methods across various parameter scales on the CholecT50 dataset. Using fewer tunable parameters, LAM achieves a mean average precision (mAP) of 42.1%, a 3.6% improvement over the previous state of the art. CONCLUSION: Leveraging effective structural design and robust capabilities of the foundational model, our proposed approach successfully strikes a balance between accuracy and computational efficiency. The source code is accessible at https://github.com/Lycus99/LAM .

Adoption of routine surgical video recording: a nationwide freedom of information act request across England and Wales.

Background: Surgical video contains data with significant potential to improve surgical outcome assessment, quality assurance, education, and research. Current utilisation of surgical video recording is unknown and related policies/governance structures are unclear. Methods: A nationwide Freedom of Information (FOI) request concerning surgical video recording, technology, consent, access, and governance was sent to all acute National Health Service (NHS) trusts/boards in England/Wales between 20th February and 20th March 2023. Findings: 140/144 (97.2%) trusts/boards in England/Wales responded to the FOI request. Surgical procedures were routinely recorded in 22 trusts/boards. The median estimate of consultant surgeons routinely recording their procedures was 20%. Surgical video was stored on internal systems (n = 27), third-party products (n = 29), and both (n = 9). 32/140 (22.9%) trusts/boards ask for consent to record procedures as part of routine care. Consent for recording included non-clinical purposes in 55/140 (39.3%) trusts/boards. Policies for surgeon/patient access to surgical video were available in 48/140 (34.3%) and 32/140 (22.9%) trusts/boards, respectively. Surgical video was used for non-clinical purposes in 64/140 (45.7%) trusts/boards. Governance policies covering surgical video recording, use, and/or storage were available from 59/140 (42.1%) trusts/boards. Interpretation: There is significant heterogeneity in surgical video recording practices in England and Wales. A minority of trusts/boards routinely record surgical procedures, with large variation in recording/storage practices indicating scope for NHS-wide coordination. Revision of surgical video consent, accessibility, and governance policies should be prioritised by trusts/boards to protect key stakeholders. Increased availability of surgical video is essential for patients and surgeons to maximally benefit from the ongoing digital transformation of surgery. Funding: KL is supported by an NIHR Academic Clinical Fellowship and acknowledges infrastructure support for this research from the National Institute for Health Research (NIHR) Imperial Biomedical Research Centre (BRC).

A Systematic Review on the Impact of Quality Assurance Programs on Outcomes after Radical Prostatectomy.

BACKGROUND AND OBJECTIVE: The implementation of quality assurance programs (QAPs) within urological practice has gained prominence; yet, their impact on outcomes after radical prostatectomy (RP) remains uncertain. This paper aims to systematically review the current literature regarding the implementation of QAPs and their impact on outcomes after robot-assisted RP, laparoscopic RP, and open prostatectomy, collectively referred to as RP. METHODS: A systematic Embase, Medline (OvidSP), and Scopus search was conducted, according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) process, on January 12, 2024. Studies were identified and included if these covered implementation of QAPs and their impact on outcomes after RP. QAPs were defined as any intervention seeking quality improvement through critically reviewing, analyzing, and discussing outcomes. Included studies were assessed critically using the Risk of Bias in Nonrandomized Studies of Interventions (ROBINS-I) tool, with results summarized narratively. KEY FINDINGS AND LIMITATIONS: Ten included studies revealed two methodological strategies: periodic performance feedback and surgical video assessments. Despite conceptual variability, QAPs improved outcomes consistently (ie, surgical margins, urine continence, erectile function, and hospital readmissions). Of the two strategies, video assessments better identified suboptimal surgical practice and technical errors. Although the extent of quality improvements did not appear to correlate with the frequency of QAPs, there was an apparent correlation with whether or not outcomes were evaluated collectively. CONCLUSIONS AND CLINICAL IMPLICATIONS: Current findings suggest that QAPs have a positive impact on outcomes after RP. Caution in interpretation due to limited data is advised. More extensive research is required to explore how conceptual differences impact the extent of quality improvements. PATIENT SUMMARY: In this paper, we review the available scientific literature regarding the implementation of quality assurance programs and their impact on outcomes after radical prostatectomy. The included studies offered substantial support for the implementation of quality assurance programs as an incentive to improve the quality of care continuously.

An analysis on the effect of body tissues and surgical tools on workflow recognition in first person surgical videos.

PURPOSE: Analysis of operative fields is expected to aid in estimating procedural workflow and evaluating surgeons' procedural skills by considering the temporal transitions during the progression of the surgery. This study aims to propose an automatic recognition system for the procedural workflow by employing machine learning techniques to identify and distinguish elements in the operative field, including body tissues such as fat, muscle, and dermis, along with surgical tools. METHODS: We conducted annotations on approximately 908 first-person-view images of breast surgery to facilitate segmentation. The annotated images were used to train a pixel-level classifier based on Mask R-CNN. To assess the impact on procedural workflow recognition, we annotated an additional 43,007 images. The network, structured on the Transformer architecture, was then trained with surgical images incorporating masks for body tissues and surgical tools. RESULTS: The instance segmentation of each body tissue in the segmentation phase provided insights into the trend of area transitions for each tissue. Simultaneously, the spatial features of the surgical tools were effectively captured. In regard to the accuracy of procedural workflow recognition, accounting for body tissues led to an average improvement of 3 % over the baseline. Furthermore, the inclusion of surgical tools yielded an additional increase in accuracy by 4 % compared to the baseline. CONCLUSION: In this study, we revealed the contribution of the temporal transition of the body tissues and surgical tools spatial features to recognize procedural workflow in first-person-view surgical videos. Body tissues, especially in open surgery, can be a crucial element. This study suggests that further improvements can be achieved by accurately identifying surgical tools specific to each procedural workflow step.

Microsurgery for brain aneurysms in an accessory A2 and basilar arteries: a rare case presentation and surgical video.

We present the case of a 58-year-old male with a 3-day history of sudden onset headache, loss of consciousness, and uncontrolled vomiting. The patient had 3/5 quadriparesis and a Glasgow coma scale (GCS) score of 8, which merited neurocritical intensive care. Brain imaging suggested the presence of two lesions: (i) a fusiform aneurysm of 12 × 7 mm in an accessory A2 artery of the anterior cerebral artery and (ii) an unruptured saccular aneurysm of 3.3 × 2.8 mm in the distal segment of the basilar artery. He was deemed a candidate for microsurgical management. Postoperatively, he had 4/5 quadriparesis, paresis of the right oculomotor nerve, and a GCS score of 13. A 3-month follow-up showed a significant improvement in neurological function with a score of 2 on the modified Rankin scale. The presented case illustrates the relevance of a nuanced acquaintance to operate in diseased anatomical variants and complex pathologies of narrow corridors.

[Evaluation of the GeSRU-Steps educational video concept (German Society of Residents in Urology e. V.)]. / Evaluierung des GeSRU-Steps-Lehrvideokonzepts (German Society of Residents in Urology e. V.).

BACKGROUND: Surgical educational videos represent a contemporary, multimedia supplement to surgical education and training. The German Society of Residents in Urology e. V. (GeSRU) developed an educational video platform (steps.GeSRU.de) with free, quality-assured educational videos for urologists, especially for residents. OBJECTIVES: The purpose of this study was to evaluate the GeSRU Steps teaching videos. MATERIALS AND METHODS: Prospectively, 29 GeSRU Steps training videos were made available (03/2019-05/2023) via amboss.com, and an online questionnaire was inserted following the videos. This comprised 12 items on medical, technical, and didactic quality, usefulness for own knowledge acquisition, and sociodemographic data of respondents. Aspects of video quality were assessed with the Acceptability E­scale and the Global Quality Score. RESULTS: During the survey period, the GeSRU Steps videos implemented on the amboss.com website were viewed 49,698 times. A total of 474 questionnaires were answered (rate 0.25%). The collective of respondents consisted of 419 (88%) students, 47 (10%) physicians in training, and 5 (1%) specialists; 351 (74%) were female, 107 (23%) were male, and 4 (1%) were diverse. Each educational video was rated a median of 10 times (range 5-65). The six questions of the Acceptability E­scale and the Global Quality Score were rated good and very good (81.6-95.8%), respectively. CONCLUSIONS: GeSRU teaching videos achieved a very good rating with high user satisfaction. By specific promotion of these teaching videos, which are quality-assured through supervision, the portfolio of surgical videos available at a low threshold can be expanded and can serve as a contemporary education tool.

Real-time auto-segmentation of the ureter in video sequences of gynaecological laparoscopic surgery.

BACKGROUND: Ureteral injury is common during gynaecological laparoscopic surgery. Real-time auto-segmentation can assist gynaecologists in identifying the ureter and reduce intraoperative injury risk. METHODS: A deep learning segmentation model was crafted for ureter recognition in surgical videos, utilising 3368 frames from 11 laparoscopic surgeries. Class activation maps enhanced the model's interpretability, showing its areas. The model's clinical relevance was validated through an End-User Turing test and verified by three gynaecological surgeons. RESULTS: The model registered a Dice score of 0.86, a Hausdorff 95 distance of 22.60, and processed images in 0.008 s on average. In complex surgeries, it pinpointed the ureter's position in real-time. Fifty five surgeons across eight institutions found the model's accuracy, specificity, and sensitivity comparable to human performance. Yet, artificial intelligence experience influenced some subjective ratings. CONCLUSIONS: The model offers precise real-time ureter segmentation in laparoscopic surgery and can be a significant tool for gynaecologists to mitigate ureteral injuries.

Role of live streaming surgical video in CVTS residency program in India: a strategy to improve learning curve of surgical residents.

Recording surgical video is not new in medicine. But not many surgical residency programs in India have this facility. The coronavirus disease (COVID) pandemic made us search for new ways to progress ahead in our surgical careers. We present a way to record surgical videos and live stream them to a select audience comprising surgical residents and faculty, wherever they may be. This may become a standard of teaching once adopted by all top surgical residency programs across the country.

Enhancing surgical precision and efficiency: a study and comparison of a three-dimensional surgical video system in proliferative diabetic retinopathy surgery.

Purpose: This study aimed to investigate the safety and efficacy of three-dimensional (3D) surgical video systems for proliferative diabetic retinopathy (PDR). Methods: This retrospective clinical case study included 30 patients (30 eyes) with PDR. Patients were divided into two groups: one underwent surgery using a 3D surgical video system (14 cases, 14 eyes), while the other underwent traditional microscope surgery (16 cases, 16 eyes). Safety and efficacy were assessed through predetermined surgical parameters, including surgical duration, intraoperative membrane removal rate, and occurrences during intraoperative and postoperative phases. Results: Our study revealed noteworthy differences in various aspects between the 3D surgical video system group and the traditional microscope surgery group. Specifically, the mean surgical time was 30.25 ± 14.43 mins in the 3D surgical video system group, while it was 38.56 ± 18.71 mins in the traditional microscope surgery group (p = 0.051). Furthermore, the mean membrane removal time was significantly shorter in the 3D group at 2.53 ± 1.52 mins, as compared to 3.23 ± 1.76 mins in the traditional group (p = 0.042). Importantly, the membrane removal rate also displayed a significant difference, with the 3D group at 0.55 ± 0.07 and the traditional group at 0.41 ± 0.11 (p = 0.018). However, no notable differences were observed between the two groups in terms of intraoperative and postoperative incidences. Conclusion: The safety and efficacy obtained using the 3D surgical video system in PDR surgery were comparable to those obtained in traditional microscopic surgery.

Technical nuances for the resection of cervical dumbbell schwannomas.

The majority of spinal nerve sheath tumors are within the intradural/extramedullary compartment. A subset of these tumors develop extraforaminal components that gradually expand into potential spaces. Herein, the authors provide a 2D video demonstrating the technical nuances concerning resection of cervical dumbbell schwannomas with extraspinal extension. Although nerve sheath tumors with large extraforaminal extension are often associated with complications and pose unique challenges to surgeons, circumferential exposure with intradural exploration allows for gross-total resection and nerve root preservation, without need for adjuvant treatments. The use of intraoperative ultrasound, neurophysiological monitoring, Doppler imaging, and meticulous surgical techniques aided to circumvent complications.

Illustrative resection of mixed intra- and extramedullary thoracic spinal cord capillary hemangioma.

Background: Capillary hemangiomas are typically superficial benign tumors of the cutaneous and mucosal tissues of the face and neck in pediatric patients. In adults, they typically occur in middle-aged males who present with pain, myelopathy, radiculopathy, paresthesias, and bowel/bladder dysfunction. The optimal treatment for intramedullary spinal cord capillary hemangiomas is gross total/en bloc resection. Methods: Here, we present a 63-year-old male with increasing right greater than left lower extremity numbness/ weakness, attributed to a T8-9 mixed intra- and extramedullary capillary hemangioma. Results: One year following complete lesion resection, the patient used an assistive device to ambulate and continued to improve neurologically. Conclusion: We presented a 63-year-old male whose paraparesis was attributed to a T8-9 mixed intra- and extramedullary capillary hemangioma who did well following total en bloc lesion resection. In addition to this case study/technical note, we provide a 2-D intraoperative video detailing the resection technique.

Live laparoscopic video retrieval with compressed uncertainty.

Searching through large volumes of medical data to retrieve relevant information is a challenging yet crucial task for clinical care. However the primitive and most common approach to retrieval, involving text in the form of keywords, is severely limited when dealing with complex media formats. Content-based retrieval offers a way to overcome this limitation, by using rich media as the query itself. Surgical video-to-video retrieval in particular is a new and largely unexplored research problem with high clinical value, especially in the real-time case: using real-time video hashing, search can be achieved directly inside of the operating room. Indeed, the process of hashing converts large data entries into compact binary arrays or hashes, enabling large-scale search operations at a very fast rate. However, due to fluctuations over the course of a video, not all bits in a given hash are equally reliable. In this work, we propose a method capable of mitigating this uncertainty while maintaining a light computational footprint. We present superior retrieval results (3%-4% top 10 mean average precision) on a multi-task evaluation protocol for surgery, using cholecystectomy phases, bypass phases, and coming from an entirely new dataset introduced here, surgical events across six different surgery types. Success on this multi-task benchmark shows the generalizability of our approach for surgical video retrieval.

A methodology for the annotation of surgical videos for supervised machine learning applications.

PURPOSE: Surgical data science is an emerging field focused on quantitative analysis of pre-, intra-, and postoperative patient data (Maier-Hein et al. in Med Image Anal 76: 102306, 2022). Data science approaches can decompose complex procedures, train surgical novices, assess outcomes of actions, and create predictive models of surgical outcomes (Marcus et al. in Pituitary 24: 839-853, 2021; Røadsch et al. in Nat Mach Intell, 2022). Surgical videos contain powerful signals of events that may impact patient outcomes. A necessary step before the deployment of supervised machine learning methods is the development of labels for objects and anatomy. We describe a complete method for annotating videos of transsphenoidal surgery. METHODS: Endoscopic video recordings of transsphenoidal pituitary tumor removal surgeries were collected from a multicenter research collaborative. These videos were anonymized and stored in a cloud-based platform. Videos were uploaded to an online annotation platform. Annotation framework was developed based on a literature review and surgical observations to ensure proper understanding of the tools, anatomy, and steps present. A user guide was developed to trained annotators to ensure standardization. RESULTS: A fully annotated video of a transsphenoidal pituitary tumor removal surgery was produced. This annotated video included over 129,826 frames. To prevent any missing annotations, all frames were later reviewed by highly experienced annotators and a surgeon reviewer. Iterations to annotated videos allowed for the creation of an annotated video complete with labeled surgical tools, anatomy, and phases. In addition, a user guide was developed for the training of novice annotators, which provides information about the annotation software to ensure the production of standardized annotations. CONCLUSIONS: A standardized and reproducible workflow for managing surgical video data is a necessary prerequisite to surgical data science applications. We developed a standard methodology for annotating surgical videos that may facilitate the quantitative analysis of videos using machine learning applications. Future work will demonstrate the clinical relevance and impact of this workflow by developing process modeling and outcome predictors.

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.