1
|
De Backer P, Simoens J, Mestdagh K, Hofman J, Eckhoff JA, Jobczyk M, Van Eetvelde E, D’Hondt M, Moschovas MC, Patel V, Van Praet C, Fuchs HF, Debbaut C, Decaestecker K, Mottrie A. Privacy-proof Live Surgery Streaming: Development and Validation of a Low-cost, Real-time Robotic Surgery Anonymization Algorithm. Ann Surg 2024; 280:13-20. [PMID: 38390732 PMCID: PMC11161223 DOI: 10.1097/sla.0000000000006245] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/24/2024]
Abstract
OBJECTIVE Develop a pioneer surgical anonymization algorithm for reliable and accurate real-time removal of out-of-body images validated across various robotic platforms. BACKGROUND The use of surgical video data has become a common practice in enhancing research and training. Video sharing requires complete anonymization, which, in the case of endoscopic surgery, entails the removal of all nonsurgical video frames where the endoscope can record the patient or operating room staff. To date, no openly available algorithmic solution for surgical anonymization offers reliable real-time anonymization for video streaming, which is also robotic-platform and procedure-independent. METHODS A data set of 63 surgical videos of 6 procedures performed on four robotic systems was annotated for out-of-body sequences. The resulting 496.828 images were used to develop a deep learning algorithm that automatically detected out-of-body frames. Our solution was subsequently benchmarked against existing anonymization methods. In addition, we offer a postprocessing step to enhance the performance and test a low-cost setup for real-time anonymization during live surgery streaming. RESULTS Framewise anonymization yielded a receiver operating characteristic area under the curve score of 99.46% on unseen procedures, increasing to 99.89% after postprocessing. Our Robotic Anonymization Network outperforms previous state-of-the-art algorithms, even on unseen procedural types, despite the fact that alternative solutions are explicitly trained using these procedures. CONCLUSIONS Our deep learning model, Robotic Anonymization Network, offers reliable, accurate, and safe real-time anonymization during complex and lengthy surgical procedures regardless of the robotic platform. The model can be used in real time for surgical live streaming and is openly available.
Collapse
Affiliation(s)
- Pieter De Backer
- ORSI Academy, Belgium
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, Belgium
- IBiTech-Biommeda, Faculty of Engineering and Architecture, CRIG, Ghent University, Belgium
- Urology Department, Ghent University Hospital, Belgium
| | | | - Kenzo Mestdagh
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, Belgium
| | | | - Jennifer A. Eckhoff
- Robotic Innovation Laboratory, Department of General, University Hospital Cologne, Visceral, Tumor and Transplantsurgery, Germany
| | - Mateusz Jobczyk
- Urology Department, Salve Medica Hospital Lodz, Lodz, Poland
| | | | - Mathieu D’Hondt
- Department of Digestive and Hepatobiliary/Pancreatic Surgery, AZ Groeninge Hospital Kortrijk, Belgium
| | | | - Vipul Patel
- Urology Department, AdventHealth Global Robotics Institute, Celebration, FL
| | | | - Hans F. Fuchs
- Robotic Innovation Laboratory, Department of General, University Hospital Cologne, Visceral, Tumor and Transplantsurgery, Germany
| | - Charlotte Debbaut
- IBiTech-Biommeda, Faculty of Engineering and Architecture, CRIG, Ghent University, Belgium
| | - Karel Decaestecker
- Urology Department, Ghent University Hospital, Belgium
- Urology Department, AZ Maria Middelares Hospital Ghent, Ghent, Belgium
| | - Alexandre Mottrie
- ORSI Academy, Belgium
- Urology Department, OLV Hospital Aalst-Asse-Ninove, Belgium
| |
Collapse
|
2
|
Bashary M, Eltyeb D, Hassan S, Eltyeb M, Mohamedahmed AY, Eltyeb H. Scalpel and strife: Assessing the impact of Sudan's ongoing civil war on surgical practice and healthcare delivery. Surgeon 2024:S1479-666X(24)00047-7. [PMID: 38744575 DOI: 10.1016/j.surge.2024.04.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2024] [Revised: 04/22/2024] [Accepted: 04/30/2024] [Indexed: 05/16/2024]
Abstract
BACKGROUND This study aims to shed light on the profound ramifications of the military conflict that started in April 2023 on surgical practice in Sudan. METHODS This is a survey-based study. The survey link was disseminated to Sudanese medical practitioners via various social media (WhatsApp, Telegram, X (previously twitter) and Facebook) channels. We included only responses from medical practitioners working in the surgical specialities. RESULTS A total of 90 responses have been collected. All participants were working in surgical service provision institutes. Sixty per cent of the responses were from the age group 25-35 years old, and two-thirds of the total cohort either left Sudan or was internally displaced because of the conflict. Moreover, 51% are no longer practising because they had to flee the conflict area (75%) or because the hospital is out of service (20%). There was a significant drop in the average number of emergency and elective lists. CONCLUSION The military conflict affected Sudan's already strained health system. There was a significant drop in the average number of emergency and elective lists with surgeons out of practice because they had to flee the conflict area and hospitals were out of service.
Collapse
Affiliation(s)
- Mahmoud Bashary
- St Peter's Hospital, Ashford and St. Peter's Hospitals NHS Foundation Trust, Guildford Rd, Lyne, Chertsey KT16 0PZ, UK.
| | - Dana Eltyeb
- St Peter's Hospital, Ashford and St. Peter's Hospitals NHS Foundation Trust, Guildford Rd, Lyne, Chertsey KT16 0PZ, UK.
| | - Samar Hassan
- Queen Elizabeth Hospital, Queen Elizabeth Ave, Gateshead NE9 6SX, UK.
| | | | - Ali Yasen Mohamedahmed
- University Hospitals of Derby and Burton, Burton On Trent, Uttoxeter Road, Derby, Derbyshire DE22 3NE, UK.
| | - Hazim Eltyeb
- Queen Elizabeth Hospital, Queen Elizabeth Ave, Gateshead NE9 6SX, UK.
| |
Collapse
|
3
|
Yiu A, Lam K, Simister C, Clarke J, Kinross J. Adoption of routine surgical video recording: a nationwide freedom of information act request across England and Wales. EClinicalMedicine 2024; 70:102545. [PMID: 38685926 PMCID: PMC11056472 DOI: 10.1016/j.eclinm.2024.102545] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Revised: 02/28/2024] [Accepted: 02/28/2024] [Indexed: 05/02/2024] Open
Abstract
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).
Collapse
Affiliation(s)
- Andrew Yiu
- Department of Surgery and Cancer, Imperial College London, UK
| | - Kyle Lam
- Department of Surgery and Cancer, Imperial College London, UK
| | | | - Jonathan Clarke
- Department of Surgery and Cancer, Imperial College London, UK
| | - James Kinross
- Department of Surgery and Cancer, Imperial College London, UK
| |
Collapse
|
4
|
Cekic E, Pinar E, Pinar M, Dagcinar A. Deep Learning-Assisted Segmentation and Classification of Brain Tumor Types on Magnetic Resonance and Surgical Microscope Images. World Neurosurg 2024; 182:e196-e204. [PMID: 38030068 DOI: 10.1016/j.wneu.2023.11.073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 11/15/2023] [Accepted: 11/16/2023] [Indexed: 12/01/2023]
Abstract
OBJECTIVE The primary aim of this research was to harness the capabilities of deep learning to enhance neurosurgical procedures, focusing on accurate tumor boundary delineation and classification. Through advanced diagnostic tools, we aimed to offer surgeons a more insightful perspective during surgeries, improving surgical outcomes and patient care. METHODS The study deployed the Mask R-convolutional neural network (CNN) architecture, leveraging its sophisticated features to process and analyze data from surgical microscope videos and preoperative magnetic resonance images. Resnet101 and Resnet50 backbone networks are used in the Mask R-CNN method, and experimental results are given. We subsequently tested its performance across various metrics, such as accuracy, precision, recall, dice coefficient (DICE), and Jaccard index. Deep learning models were trained from magnetic resonance imaging and surgical microscope images, and the classification result obtained for each patient was combined with the weighted average. RESULTS The algorithm exhibited remarkable capabilities in distinguishing among meningiomas, metastases, and high-grade glial tumors. Specifically, for the Mask R-CNN Resnet 101 architecture, precision, recall, DICE, and Jaccard index values were recorded as 96%, 93%, 91%, and 84%, respectively. Conversely, for the Mask R-CNN Resnet 50 architecture, these values stood at 94%, 89%, 89%, and 82%. Additionally, the model achieved an impressive DICE score range of 94%-95% and an accuracy of 98% in pathology estimation. CONCLUSIONS As illustrated in our study, the confluence of deep learning with neurosurgical procedures marks a transformative phase in medical science. The results are promising but underscore diverse data sets' significance for training and refining these deep learning models.
Collapse
Affiliation(s)
- Efecan Cekic
- Department of Neurosurgery, Polatli Duatepe State Hospital, Ankara, Turkey.
| | - Ertugrul Pinar
- Department of Neurosurgery, Private Pendik Yuzyil Hospital, İstanbul, Turkey
| | - Merve Pinar
- Department of Computer Engineering, Marmara University, İstanbul, Turkey
| | - Adnan Dagcinar
- Department of Neurosurgery, Marmara University, İstanbul, Turkey
| |
Collapse
|
5
|
Ferrari L, Nicolaou S, Adams K. Implementation of a robotic surgical practice in inflammatory bowel disease. J Robot Surg 2024; 18:57. [PMID: 38281204 DOI: 10.1007/s11701-023-01750-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2023] [Accepted: 12/02/2023] [Indexed: 01/30/2024]
Abstract
Robotics adoption has increased in colorectal surgery. While there are well-established advantages and standardised techniques for cancer patients, the use of robotic surgery in inflammatory bowel disease (IBD) has not been studied yet. To evaluate the feasibility and safety of robotic surgery for IBD patients. Prospectively data in IBD patients having robotic resection at Guy's and St Thomas' hospital. All resections performed by a single colorectal surgeon specialised in IBD, utilising DaVinci platform. July 2021 to January 2023, 59 robotic IBD cases performed, 14 ulcerative colitis (UC) and 45 Crohn's disease (CD). Average age; CD patients 35, UC 33 years. Average Body mass index (BMI); 23 for CD and 26.9 for UC patients. In total, we performed 31 ileo-caecal resections (ICR) with primary anastomosis (18 Kono-S anastomosis, 6 mechanical anastomosis and 7 ileo-colostomy), of those 4 had multivisceral resections (large bowel, bladder, ovary). Furthermore, 14 subtotal colectomy (1 emergency), 8 proctectomy, 3 panproctocolectomy and 3 ileoanal J pouch. 18 of the 45 patients (45.0%) with Crohn's disease had ongoing fistulating disease to other parts of the GI tract (small or large bowel). ICR were performed using different three ports position, depending on the anatomy established prior to surgery with magnetic resonance images (MRI). One patient had conversion to open due to anaesthetic problems and one patient required re-operation to refashion stoma. 98.0% cases completed robotically. Median Length of hospital stay (LOS) was 7 days for CD and 7 for UC cases, including LOS in patients on pre-operative parenteral nutrition. Robotic colorectal techniques can be safely used for patients with IBD, even with fistulating disease. Future research and collaborations are necessary to standardize technique within institutions.
Collapse
Affiliation(s)
- Linda Ferrari
- Pelvic Floor Unit, Mitchener Ward, St Thomas' Hospital, Guy's and St Thomas NHS Foundation Trust, Westminster Bridge Road, London, SE17EH, UK.
| | - Stella Nicolaou
- Pelvic Floor Unit, Mitchener Ward, St Thomas' Hospital, Guy's and St Thomas NHS Foundation Trust, Westminster Bridge Road, London, SE17EH, UK
| | - Katie Adams
- Pelvic Floor Unit, Mitchener Ward, St Thomas' Hospital, Guy's and St Thomas NHS Foundation Trust, Westminster Bridge Road, London, SE17EH, UK
| |
Collapse
|
6
|
Wei Y, Li L, Xie C, Wei Y, Huang C, Wang Y, Zhou J, Jia C, Junlin L. Current Status of Auricular Reconstruction Strategy Development. J Craniofac Surg 2023:00001665-990000000-01239. [PMID: 37983309 DOI: 10.1097/scs.0000000000009908] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Accepted: 10/27/2023] [Indexed: 11/22/2023] Open
Abstract
Microtia has severe physical and psychological impacts on patients, and auricular reconstruction offers improved esthetics and function, alleviating psychological issues. Microtia is a congenital disease caused by a multifactorial interaction of environmental and genetic factors, with complex clinical manifestations. Classification assessment aids in determining treatment strategies. Auricular reconstruction is the primary treatment for severe microtia, focusing on the selection of auricular scaffold materials, the construction of auricular morphology, and skin and soft tissue scaffold coverage. Autologous rib cartilage and synthetic materials are both used as scaffold materials for auricular reconstruction, each with advantages and disadvantages. Methods for achieving skin and soft tissue scaffold coverage have been developed to include nonexpansion and expansion techniques. In recent years, the application of digital auxiliary technology such as finite element analysis has helped optimize surgical outcomes and reduce complications. Tissue-engineered cartilage scaffolds and 3-dimensional bioprinting technology have rapidly advanced in the field of ear reconstruction. This article discusses the prevalence and classification of microtia, the selection of auricular scaffolds, the evolution of surgical methods, and the current applications of digital auxiliary technology in ear reconstruction, with the aim of providing clinical physicians with a reference for individualized ear reconstruction surgery. The focus of this work is on the current applications and challenges of tissue engineering and 3-dimensional bioprinting technology in the field of ear reconstruction, as well as future prospects.
Collapse
Affiliation(s)
- Yi Wei
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Li Li
- Department of Obstetrics and Gynecology, The First Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan
| | - Cong Xie
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Yangchen Wei
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Chufei Huang
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Yiping Wang
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Jianda Zhou
- Departments of Plastic and Reconstructive Surgery, The Third Xiangya Hospital, Central South University, Changsha, China
| | - Chiyu Jia
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| | - Liao Junlin
- Center of Burn and Plastic and Wound Healing Surgery, The First Affiliated Hospital, Hengyang Medical School, University of South China
| |
Collapse
|
7
|
De Backer P, Peraire Lores M, Demuynck M, Piramide F, Simoens J, Oosterlinck T, Bogaert W, Shan CV, Van Regemorter K, Wastyn A, Checcucci E, Debbaut C, Van Praet C, Farinha R, De Groote R, Gallagher A, Decaestecker K, Mottrie A. Surgical Phase Duration in Robot-Assisted Partial Nephrectomy: A Surgical Data Science Exploration for Clinical Relevance. Diagnostics (Basel) 2023; 13:3386. [PMID: 37958283 PMCID: PMC10650909 DOI: 10.3390/diagnostics13213386] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 10/29/2023] [Accepted: 11/03/2023] [Indexed: 11/15/2023] Open
Abstract
(1) Background: Surgical phases form the basic building blocks for surgical skill assessment, feedback, and teaching. The phase duration itself and its correlation with clinical parameters at diagnosis have not yet been investigated. Novel commercial platforms provide phase indications but have not been assessed for accuracy yet. (2) Methods: We assessed 100 robot-assisted partial nephrectomy videos for phase durations based on previously defined proficiency metrics. We developed an annotation framework and subsequently compared our annotations to an existing commercial solution (Touch Surgery, Medtronic™). We subsequently explored clinical correlations between phase durations and parameters derived from diagnosis and treatment. (3) Results: An objective and uniform phase assessment requires precise definitions derived from an iterative revision process. A comparison to a commercial solution shows large differences in definitions across phases. BMI and the duration of renal tumor identification are positively correlated, as are tumor complexity and both tumor excision and renorrhaphy duration. (4) Conclusions: The surgical phase duration can be correlated with certain clinical outcomes. Further research should investigate whether the retrieved correlations are also clinically meaningful. This requires an increase in dataset sizes and facilitation through intelligent computer vision algorithms. Commercial platforms can facilitate this dataset expansion and help unlock the full potential, provided that the phase annotation details are disclosed.
Collapse
Affiliation(s)
- Pieter De Backer
- ORSI Academy, 9090 Melle, Belgium
- IbiTech-Biommeda, Department of Electronics and Information Systems, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
- Young Academic Urologist—Urotechnology Working Group, NL-6803 Arnhem, The Netherlands
- Department of Urology, ERN eUROGEN Accredited Centre, Ghent University Hospital, 9000 Ghent, Belgium
| | | | - Meret Demuynck
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
| | - Federico Piramide
- ORSI Academy, 9090 Melle, Belgium
- Department of Surgery, Candiolo Cancer Institute, FPO-IRCCS, 10060 Turin, Italy
| | | | | | - Wouter Bogaert
- IbiTech-Biommeda, Department of Electronics and Information Systems, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
| | - Chi Victor Shan
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
| | - Karel Van Regemorter
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
| | - Aube Wastyn
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
| | - Enrico Checcucci
- Young Academic Urologist—Urotechnology Working Group, NL-6803 Arnhem, The Netherlands
- Department of Surgery, Candiolo Cancer Institute, FPO-IRCCS, 10060 Turin, Italy
| | - Charlotte Debbaut
- IbiTech-Biommeda, Department of Electronics and Information Systems, Faculty of Engineering and Architecture, Ghent University, 9000 Ghent, Belgium
| | - Charles Van Praet
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
- Department of Urology, ERN eUROGEN Accredited Centre, Ghent University Hospital, 9000 Ghent, Belgium
| | | | - Ruben De Groote
- Department of Urology, Onze-Lieve Vrouwziekenhuis Hospital, 9300 Aalst, Belgium
| | | | - Karel Decaestecker
- Department of Human Structure and Repair, Faculty of Medicine and Health Sciences, Ghent University, 9000 Ghent, Belgium (C.V.P.)
- Department of Urology, ERN eUROGEN Accredited Centre, Ghent University Hospital, 9000 Ghent, Belgium
- Department of Urology, AZ Maria Middelares Hospital, 9000 Ghent, Belgium
| | - Alexandre Mottrie
- ORSI Academy, 9090 Melle, Belgium
- Department of Urology, Onze-Lieve Vrouwziekenhuis Hospital, 9300 Aalst, Belgium
| |
Collapse
|
8
|
Ortenzi M, Rapoport Ferman J, Antolin A, Bar O, Zohar M, Perry O, Asselmann D, Wolf T. A novel high accuracy model for automatic surgical workflow recognition using artificial intelligence in laparoscopic totally extraperitoneal inguinal hernia repair (TEP). Surg Endosc 2023; 37:8818-8828. [PMID: 37626236 PMCID: PMC10615930 DOI: 10.1007/s00464-023-10375-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Accepted: 07/30/2023] [Indexed: 08/27/2023]
Abstract
INTRODUCTION Artificial intelligence and computer vision are revolutionizing the way we perceive video analysis in minimally invasive surgery. This emerging technology has increasingly been leveraged successfully for video segmentation, documentation, education, and formative assessment. New, sophisticated platforms allow pre-determined segments chosen by surgeons to be automatically presented without the need to review entire videos. This study aimed to validate and demonstrate the accuracy of the first reported AI-based computer vision algorithm that automatically recognizes surgical steps in videos of totally extraperitoneal (TEP) inguinal hernia repair. METHODS Videos of TEP procedures were manually labeled by a team of annotators trained to identify and label surgical workflow according to six major steps. For bilateral hernias, an additional change of focus step was also included. The videos were then used to train a computer vision AI algorithm. Performance accuracy was assessed in comparison to the manual annotations. RESULTS A total of 619 full-length TEP videos were analyzed: 371 were used to train the model, 93 for internal validation, and the remaining 155 as a test set to evaluate algorithm accuracy. The overall accuracy for the complete procedure was 88.8%. Per-step accuracy reached the highest value for the hernia sac reduction step (94.3%) and the lowest for the preperitoneal dissection step (72.2%). CONCLUSIONS These results indicate that the novel AI model was able to provide fully automated video analysis with a high accuracy level. High-accuracy models leveraging AI to enable automation of surgical video analysis allow us to identify and monitor surgical performance, providing mathematical metrics that can be stored, evaluated, and compared. As such, the proposed model is capable of enabling data-driven insights to improve surgical quality and demonstrate best practices in TEP procedures.
Collapse
Affiliation(s)
- Monica Ortenzi
- Theator Inc., Palo Alto, CA, USA.
- Department of General and Emergency Surgery, Polytechnic University of Marche, Ancona, Italy.
| | | | | | - Omri Bar
- Theator Inc., Palo Alto, CA, USA
| | | | | | | | | |
Collapse
|