1
|
Morris MX, Fiocco D, Caneva T, Yiapanis P, Orgill DP. Current and future applications of artificial intelligence in surgery: implications for clinical practice and research. Front Surg 2024; 11:1393898. [PMID: 38783862 PMCID: PMC11111929 DOI: 10.3389/fsurg.2024.1393898] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/29/2024] [Accepted: 04/29/2024] [Indexed: 05/25/2024] Open
Abstract
Surgeons are skilled at making complex decisions over invasive procedures that can save lives and alleviate pain and avoid complications in patients. The knowledge to make these decisions is accumulated over years of schooling and practice. Their experience is in turn shared with others, also via peer-reviewed articles, which get published in larger and larger amounts every year. In this work, we review the literature related to the use of Artificial Intelligence (AI) in surgery. We focus on what is currently available and what is likely to come in the near future in both clinical care and research. We show that AI has the potential to be a key tool to elevate the effectiveness of training and decision-making in surgery and the discovery of relevant and valid scientific knowledge in the surgical domain. We also address concerns about AI technology, including the inability for users to interpret algorithms as well as incorrect predictions. A better understanding of AI will allow surgeons to use new tools wisely for the benefit of their patients.
Collapse
Affiliation(s)
- Miranda X. Morris
- Duke University School of Medicine, Duke University Hospital, Durham, NC, United States
| | - Davide Fiocco
- Department of Artificial Intelligence, Frontiers Media SA, Lausanne, Switzerland
| | - Tommaso Caneva
- Department of Artificial Intelligence, Frontiers Media SA, Lausanne, Switzerland
| | - Paris Yiapanis
- Department of Artificial Intelligence, Frontiers Media SA, Lausanne, Switzerland
| | - Dennis P. Orgill
- Harvard Medical School, Brigham and Women’s Hospital, Boston, MA, United States
| |
Collapse
|
2
|
Zhai Y, Chen Z, Zheng Z, Wang X, Yan X, Liu X, Yin J, Wang J, Zhang J. Artificial intelligence for automatic surgical phase recognition of laparoscopic gastrectomy in gastric cancer. Int J Comput Assist Radiol Surg 2024; 19:345-353. [PMID: 37914911 DOI: 10.1007/s11548-023-03027-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Accepted: 10/02/2023] [Indexed: 11/03/2023]
Abstract
PURPOSE This study aimed to classify laparoscopic gastric cancer phases. We also aimed to develop a transformer-based artificial intelligence (AI) model for automatic surgical phase recognition and to evaluate the model's performance using laparoscopic gastric cancer surgical videos. METHODS One hundred patients who underwent laparoscopic surgery for gastric cancer were included in this study. All surgical videos were labeled and classified into eight phases (P0. Preparation. P1. Separate the greater gastric curvature. P2. Separate the distal stomach. P3. Separate lesser gastric curvature. P4. Dissect the superior margin of the pancreas. P5. Separation of the proximal stomach. P6. Digestive tract reconstruction. P7. End of operation). This study proposed an AI phase recognition model consisting of a convolutional neural network-based visual feature extractor and temporal relational transformer. RESULTS A visual and temporal relationship network was proposed to automatically perform accurate surgical phase prediction. The average time for all surgical videos in the video set was 9114 ± 2571 s. The longest phase was at P1 (3388 s). The final research accuracy, F1, recall, and precision were 90.128, 87.04, 87.04, and 87.32%, respectively. The phase with the highest recognition accuracy was P1, and that with the lowest accuracy was P2. CONCLUSION An AI model based on neural and transformer networks was developed in this study. This model can identify the phases of laparoscopic surgery for gastric cancer accurately. AI can be used as an analytical tool for gastric cancer surgical videos.
Collapse
Affiliation(s)
- Yuhao Zhai
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Zhen Chen
- Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong SAR, China
| | - Zhi Zheng
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Xi Wang
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Xiaosheng Yan
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Xiaoye Liu
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Jie Yin
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China
- State Key Lab of Digestive Health, Beijing, China
| | - Jinqiao Wang
- Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong SAR, China.
- National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Haidian District, Beijing, China.
- Wuhan AI Research, Wuhan, China.
| | - Jun Zhang
- Department of General Surgery, Beijing Friendship Hospital, Capital Medical University, 95 Yong'an Road, Xicheng District, Beijing, China.
- State Key Lab of Digestive Health, Beijing, China.
| |
Collapse
|
3
|
Kostiuchik G, Sharan L, Mayer B, Wolf I, Preim B, Engelhardt S. Surgical phase and instrument recognition: how to identify appropriate dataset splits. Int J Comput Assist Radiol Surg 2024:10.1007/s11548-024-03063-9. [PMID: 38285380 DOI: 10.1007/s11548-024-03063-9] [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: 09/01/2023] [Accepted: 01/08/2024] [Indexed: 01/30/2024]
Abstract
PURPOSE Machine learning approaches can only be reliably evaluated if training, validation, and test data splits are representative and not affected by the absence of classes. Surgical workflow and instrument recognition are two tasks that are complicated in this manner, because of heavy data imbalances resulting from different length of phases and their potential erratic occurrences. Furthermore, sub-properties like instrument (co-)occurrence are usually not particularly considered when defining the split. METHODS We present a publicly available data visualization tool that enables interactive exploration of dataset partitions for surgical phase and instrument recognition. The application focuses on the visualization of the occurrence of phases, phase transitions, instruments, and instrument combinations across sets. Particularly, it facilitates assessment of dataset splits, especially regarding identification of sub-optimal dataset splits. RESULTS We performed analysis of the datasets Cholec80, CATARACTS, CaDIS, M2CAI-workflow, and M2CAI-tool using the proposed application. We were able to uncover phase transitions, individual instruments, and combinations of surgical instruments that were not represented in one of the sets. Addressing these issues, we identify possible improvements in the splits using our tool. A user study with ten participants demonstrated that the participants were able to successfully solve a selection of data exploration tasks. CONCLUSION In highly unbalanced class distributions, special care should be taken with respect to the selection of an appropriate dataset split because it can greatly influence the assessments of machine learning approaches. Our interactive tool allows for determination of better splits to improve current practices in the field. The live application is available at https://cardio-ai.github.io/endovis-ml/ .
Collapse
Affiliation(s)
- Georgii Kostiuchik
- Department of Cardiac Surgery, Heidelberg University Hospital, Heidelberg, Germany.
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany.
| | - Lalith Sharan
- Department of Cardiac Surgery, Heidelberg University Hospital, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany
| | - Benedikt Mayer
- Department of Simulation and Graphics, University of Magdeburg, Magdeburg, Germany
| | - Ivo Wolf
- Department of Computer Science, Mannheim University of Applied Sciences, Mannheim, Germany
| | - Bernhard Preim
- Department of Simulation and Graphics, University of Magdeburg, Magdeburg, Germany
| | - Sandy Engelhardt
- Department of Cardiac Surgery, Heidelberg University Hospital, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany
| |
Collapse
|
4
|
Men Y, Zhao Z, Chen W, Wu H, Zhang G, Luo F, Yu M. Research on workflow recognition for liver rupture repair surgery. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2024; 21:1844-1856. [PMID: 38454663 DOI: 10.3934/mbe.2024080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/09/2024]
Abstract
Liver rupture repair surgery serves as one tool to treat liver rupture, especially beneficial for cases of mild liver rupture hemorrhage. Liver rupture can catalyze critical conditions such as hemorrhage and shock. Surgical workflow recognition in liver rupture repair surgery videos presents a significant task aimed at reducing surgical mistakes and enhancing the quality of surgeries conducted by surgeons. A liver rupture repair simulation surgical dataset is proposed in this paper which consists of 45 videos collaboratively completed by nine surgeons. Furthermore, an end-to-end SA-RLNet, a self attention-based recurrent convolutional neural network, is introduced in this paper. The self-attention mechanism is used to automatically identify the importance of input features in various instances and associate the relationships between input features. The accuracy of the surgical phase classification of the SA-RLNet approach is 90.6%. The present study demonstrates that the SA-RLNet approach shows strong generalization capabilities on the dataset. SA-RLNet has proved to be advantageous in capturing subtle variations between surgical phases. The application of surgical workflow recognition has promising feasibility in liver rupture repair surgery.
Collapse
Affiliation(s)
- Yutao Men
- Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
- National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, China
| | - Zixian Zhao
- Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
- Medical Support Technology Research Department, Systems Engineering Institute, Academy of Military Sciences, People's Liberation Army, Tianjin 300161, China
- National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, China
| | - Wei Chen
- Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
- National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, China
| | - Hang Wu
- Medical Support Technology Research Department, Systems Engineering Institute, Academy of Military Sciences, People's Liberation Army, Tianjin 300161, China
| | - Guang Zhang
- Medical Support Technology Research Department, Systems Engineering Institute, Academy of Military Sciences, People's Liberation Army, Tianjin 300161, China
| | - Feng Luo
- Medical Support Technology Research Department, Systems Engineering Institute, Academy of Military Sciences, People's Liberation Army, Tianjin 300161, China
| | - Ming Yu
- Medical Support Technology Research Department, Systems Engineering Institute, Academy of Military Sciences, People's Liberation Army, Tianjin 300161, China
| |
Collapse
|
5
|
Demir KC, Schieber H, Weise T, Roth D, May M, Maier A, Yang SH. Deep Learning in Surgical Workflow Analysis: A Review of Phase and Step Recognition. IEEE J Biomed Health Inform 2023; 27:5405-5417. [PMID: 37665700 DOI: 10.1109/jbhi.2023.3311628] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/06/2023]
Abstract
OBJECTIVE In the last two decades, there has been a growing interest in exploring surgical procedures with statistical models to analyze operations at different semantic levels. This information is necessary for developing context-aware intelligent systems, which can assist the physicians during operations, evaluate procedures afterward or help the management team to effectively utilize the operating room. The objective is to extract reliable patterns from surgical data for the robust estimation of surgical activities performed during operations. The purpose of this article is to review the state-of-the-art deep learning methods that have been published after 2018 for analyzing surgical workflows, with a focus on phase and step recognition. METHODS Three databases, IEEE Xplore, Scopus, and PubMed were searched, and additional studies are added through a manual search. After the database search, 343 studies were screened and a total of 44 studies are selected for this review. CONCLUSION The use of temporal information is essential for identifying the next surgical action. Contemporary methods used mainly RNNs, hierarchical CNNs, and Transformers to preserve long-distance temporal relations. The lack of large publicly available datasets for various procedures is a great challenge for the development of new and robust models. As supervised learning strategies are used to show proof-of-concept, self-supervised, semi-supervised, or active learning methods are used to mitigate dependency on annotated data. SIGNIFICANCE The present study provides a comprehensive review of recent methods in surgical workflow analysis, summarizes commonly used architectures, datasets, and discusses challenges.
Collapse
|
6
|
Zhang J, Zhou S, Wang Y, Shi S, Wan C, Zhao H, Cai X, Ding H. Laparoscopic Image-Based Critical Action Recognition and Anticipation With Explainable Features. IEEE J Biomed Health Inform 2023; 27:5393-5404. [PMID: 37603480 DOI: 10.1109/jbhi.2023.3306818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/23/2023]
Abstract
Surgical workflow analysis integrates perception, comprehension, and prediction of the surgical workflow, which helps real-time surgical support systems provide proper guidance and assistance for surgeons. This article promotes the idea of critical actions, which refer to the essential surgical actions that progress towards the fulfillment of the operation. Fine-grained workflow analysis involves recognizing current critical actions and previewing the moving tendency of instruments in the early stage of critical actions. Aiming at this, we propose a framework that incorporates operational experience to improve the robustness and interpretability of action recognition in in-vivo situations. High-dimensional images are mapped into an experience-based explainable feature space with low dimensions to achieve critical action recognition through a hierarchical classification structure. To forecast the instrument's motion tendency, we model the motion primitives in the polar coordinate system (PCS) to represent patterns of complex trajectories. Given the laparoscopy variance, the adaptive pattern recognition (APR) method, which adapts to uncertain trajectories by modifying model parameters, is designed to improve prediction accuracy. The in-vivo dataset validations show that our framework fulfilled the surgical awareness tasks with exceptional accuracy and real-time performance.
Collapse
|
7
|
Cao J, Yip HC, Chen Y, Scheppach M, Luo X, Yang H, Cheng MK, Long Y, Jin Y, Chiu PWY, Yam Y, Meng HML, Dou Q. Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study. Nat Commun 2023; 14:6676. [PMID: 37865629 PMCID: PMC10590425 DOI: 10.1038/s41467-023-42451-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Accepted: 10/11/2023] [Indexed: 10/23/2023] Open
Abstract
Recent advancements in artificial intelligence have witnessed human-level performance; however, AI-enabled cognitive assistance for therapeutic procedures has not been fully explored nor pre-clinically validated. Here we propose AI-Endo, an intelligent surgical workflow recognition suit, for endoscopic submucosal dissection (ESD). Our AI-Endo is trained on high-quality ESD cases from an expert endoscopist, covering a decade time expansion and consisting of 201,026 labeled frames. The learned model demonstrates outstanding performance on validation data, including cases from relatively junior endoscopists with various skill levels, procedures conducted with different endoscopy systems and therapeutic skills, and cohorts from international multi-centers. Furthermore, we integrate our AI-Endo with the Olympus endoscopic system and validate the AI-enabled cognitive assistance system with animal studies in live ESD training sessions. Dedicated data analysis from surgical phase recognition results is summarized in an automatically generated report for skill assessment.
Collapse
Affiliation(s)
- Jianfeng Cao
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Hon-Chi Yip
- Department of Surgery, The Chinese University of Hong Kong, Hong Kong, China.
| | - Yueyao Chen
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Markus Scheppach
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Xiaobei Luo
- Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Hongzheng Yang
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Ming Kit Cheng
- Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Yonghao Long
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
| | - Yueming Jin
- Department of Biomedical Engineering, National University of Singapore, Singapore, Singapore
| | - Philip Wai-Yan Chiu
- Multi-scale Medical Robotics Center and The Chinese University of Hong Kong, Hong Kong, China.
| | - Yeung Yam
- Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Multi-scale Medical Robotics Center and The Chinese University of Hong Kong, Hong Kong, China.
- Centre for Perceptual and Interactive Intelligence and The Chinese University of Hong Kong, Hong Kong, China.
| | - Helen Mei-Ling Meng
- Centre for Perceptual and Interactive Intelligence and The Chinese University of Hong Kong, Hong Kong, China.
| | - Qi Dou
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
| |
Collapse
|
8
|
Zang C, Turkcan MK, Narasimhan S, Cao Y, Yarali K, Xiang Z, Szot S, Ahmad F, Choksi S, Bitner DP, Filicori F, Kostic Z. Surgical Phase Recognition in Inguinal Hernia Repair-AI-Based Confirmatory Baseline and Exploration of Competitive Models. Bioengineering (Basel) 2023; 10:654. [PMID: 37370585 DOI: 10.3390/bioengineering10060654] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 05/18/2023] [Accepted: 05/23/2023] [Indexed: 06/29/2023] Open
Abstract
Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia repair (RALIHR) collected from 8 surgeons, defined rigorous ground-truth annotation rules, then pre-processed and annotated the videos. We deployed seven deep learning models to establish the baseline accuracy for surgical phase recognition and explored four advanced architectures. For rapid execution of the studies, we initially engaged three dozen MS-level engineering students in a competitive classroom setting, followed by focused research. We unified the data processing pipeline in a confirmatory study, and explored a number of scenarios which differ in how the DL networks were trained and evaluated. For the scenario with 21 validation videos of all surgeons, the Video Swin Transformer model achieved ~0.85 validation accuracy, and the Perceiver IO model achieved ~0.84. Our studies affirm the necessity of close collaborative research between medical experts and engineers for developing automated surgical phase recognition models deployable in clinical settings.
Collapse
Affiliation(s)
- Chengbo Zang
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Mehmet Kerem Turkcan
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Sanjeev Narasimhan
- Department of Computer Science, Columbia University, New York, NY 10027, USA
| | - Yuqing Cao
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Kaan Yarali
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Zixuan Xiang
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Skyler Szot
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| | - Feroz Ahmad
- Department of Computer Science, Columbia University, New York, NY 10027, USA
| | - Sarah Choksi
- Intraoperative Performance Analytics Laboratory (IPAL), Lenox Hill Hospital, New York, NY 10021, USA
| | - Daniel P Bitner
- Intraoperative Performance Analytics Laboratory (IPAL), Lenox Hill Hospital, New York, NY 10021, USA
| | - Filippo Filicori
- Intraoperative Performance Analytics Laboratory (IPAL), Lenox Hill Hospital, New York, NY 10021, USA
- Zucker School of Medicine at Hofstra/Northwell Health, Hempstead, NY 11549, USA
| | - Zoran Kostic
- Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
| |
Collapse
|
9
|
Nyangoh Timoh K, Huaulme A, Cleary K, Zaheer MA, Lavoué V, Donoho D, Jannin P. A systematic review of annotation for surgical process model analysis in minimally invasive surgery based on video. Surg Endosc 2023:10.1007/s00464-023-10041-w. [PMID: 37157035 DOI: 10.1007/s00464-023-10041-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2022] [Accepted: 03/25/2023] [Indexed: 05/10/2023]
Abstract
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.
Collapse
Affiliation(s)
- Krystel Nyangoh Timoh
- Department of Gynecology and Obstetrics and Human Reproduction, CHU Rennes, Rennes, France.
- INSERM, LTSI - UMR 1099, University Rennes 1, Rennes, France.
- Laboratoire d'Anatomie et d'Organogenèse, Faculté de Médecine, Centre Hospitalier Universitaire de Rennes, 2 Avenue du Professeur Léon Bernard, 35043, Rennes Cedex, France.
- Department of Obstetrics and Gynecology, Rennes Hospital, Rennes, France.
| | - Arnaud Huaulme
- INSERM, LTSI - UMR 1099, University Rennes 1, Rennes, France
| | - Kevin Cleary
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, 20010, USA
| | - Myra A Zaheer
- George Washington University School of Medicine and Health Sciences, Washington, DC, USA
| | - Vincent Lavoué
- Department of Gynecology and Obstetrics and Human Reproduction, CHU Rennes, Rennes, France
| | - Dan Donoho
- Division of Neurosurgery, Center for Neuroscience, Children's National Hospital, Washington, DC, 20010, USA
| | - Pierre Jannin
- INSERM, LTSI - UMR 1099, University Rennes 1, Rennes, France
| |
Collapse
|
10
|
Zhang B, Goel B, Sarhan MH, Goel VK, Abukhalil R, Kalesan B, Stottler N, Petculescu S. Surgical workflow recognition with temporal convolution and transformer for action segmentation. Int J Comput Assist Radiol Surg 2023; 18:785-794. [PMID: 36542253 DOI: 10.1007/s11548-022-02811-z] [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: 08/08/2022] [Accepted: 12/09/2022] [Indexed: 12/24/2022]
Abstract
PURPOSE Automatic surgical workflow recognition enabled by computer vision algorithms plays a key role in enhancing the learning experience of surgeons. It also supports building context-aware systems that allow better surgical planning and decision making which may in turn improve outcomes. Utilizing temporal information is crucial for recognizing context; hence, various recent approaches use recurrent neural networks or transformers to recognize actions. METHODS We design and implement a two-stage method for surgical workflow recognition. We utilize R(2+1)D for video clip modeling in the first stage. We propose Action Segmentation Temporal Convolutional Transformer (ASTCFormer) network for full video modeling in the second stage. ASTCFormer utilizes action segmentation transformers (ASFormers) and temporal convolutional networks (TCNs) to build a temporally aware surgical workflow recognition system. RESULTS We compare the proposed ASTCFormer with recurrent neural networks, multi-stage TCN, and ASFormer approaches. The comparison is done on a dataset comprised of 207 robotic and laparoscopic cholecystectomy surgical videos annotated for 7 surgical phases. The proposed method outperforms the compared methods achieving a [Formula: see text] relative improvement in the average segmental F1-score over the state-of-the-art ASFormer method. Moreover, our proposed method achieves state-of-the-art results on the publicly available Cholec80 dataset. CONCLUSION The improvement in the results when using the proposed method suggests that temporal context could be better captured when adding information from TCN to the ASFormer paradigm. This addition leads to better surgical workflow recognition.
Collapse
Affiliation(s)
- Bokai Zhang
- Johnson & Johnson MedTech, 1100 Olive Way, Suite 1100, Seattle, 98101, WA, USA.
| | - Bharti Goel
- Johnson & Johnson MedTech, 5490 Great America Pkwy, Santa Clara, CA, 95054, USA
| | - Mohammad Hasan Sarhan
- Johnson & Johnson MedTech, Robert-Koch-Straße 1, 22851, Norderstedt, Schleswig-Holstein, Germany
| | - Varun Kejriwal Goel
- Johnson & Johnson MedTech, 5490 Great America Pkwy, Santa Clara, CA, 95054, USA
| | - Rami Abukhalil
- Johnson & Johnson MedTech, 5490 Great America Pkwy, Santa Clara, CA, 95054, USA
| | - Bindu Kalesan
- Johnson & Johnson MedTech, 5490 Great America Pkwy, Santa Clara, CA, 95054, USA
| | - Natalie Stottler
- Johnson & Johnson MedTech, 1100 Olive Way, Suite 1100, Seattle, 98101, WA, USA
| | - Svetlana Petculescu
- Johnson & Johnson MedTech, 1100 Olive Way, Suite 1100, Seattle, 98101, WA, USA
| |
Collapse
|
11
|
Fer D, Zhang B, Abukhalil R, Goel V, Goel B, Barker J, Kalesan B, Barragan I, Gaddis ML, Kilroy PG. An artificial intelligence model that automatically labels roux-en-Y gastric bypasses, a comparison to trained surgeon annotators. Surg Endosc 2023:10.1007/s00464-023-09870-6. [PMID: 36658282 DOI: 10.1007/s00464-023-09870-6] [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: 03/21/2022] [Accepted: 01/04/2023] [Indexed: 01/21/2023]
Abstract
INTRODUCTION Artificial intelligence (AI) can automate certain tasks to improve data collection. Models have been created to annotate the steps of Roux-en-Y Gastric Bypass (RYGB). However, model performance has not been compared with individual surgeon annotator performance. We developed a model that automatically labels RYGB steps and compares its performance to surgeons. METHODS AND PROCEDURES 545 videos (17 surgeons) of laparoscopic RYGB procedures were collected. An annotation guide (12 steps, 52 tasks) was developed. Steps were annotated by 11 surgeons. Each video was annotated by two surgeons and a third reconciled the differences. A convolutional AI model was trained to identify steps and compared with manual annotation. For modeling, we used 390 videos for training, 95 for validation, and 60 for testing. The performance comparison between AI model versus manual annotation was performed using ANOVA (Analysis of Variance) in a subset of 60 testing videos. We assessed the performance of the model at each step and poor performance was defined (F1-score < 80%). RESULTS The convolutional model identified 12 steps in the RYGB architecture. Model performance varied at each step [F1 > 90% for 7, and > 80% for 2]. The reconciled manual annotation data (F1 > 80% for > 5 steps) performed better than trainee's (F1 > 80% for 2-5 steps for 4 annotators, and < 2 steps for 4 annotators). In testing subset, certain steps had low performance, indicating potential ambiguities in surgical landmarks. Additionally, some videos were easier to annotate than others, suggesting variability. After controlling for variability, the AI algorithm was comparable to the manual (p < 0.0001). CONCLUSION AI can be used to identify surgical landmarks in RYGB comparable to the manual process. AI was more accurate to recognize some landmarks more accurately than surgeons. This technology has the potential to improve surgical training by assessing the learning curves of surgeons at scale.
Collapse
Affiliation(s)
- Danyal Fer
- University of California, San Francisco-East Bay, General Surgery, Oakland, CA, USA.,Johnson & Johnson MedTech, New Brunswick, NJ, USA
| | - Bokai Zhang
- Johnson & Johnson MedTech, New Brunswick, NJ, USA
| | - Rami Abukhalil
- Johnson & Johnson MedTech, New Brunswick, NJ, USA. .,, 5490 Great America Parkway, Santa Clara, CA, 95054, USA.
| | - Varun Goel
- University of California, San Francisco-East Bay, General Surgery, Oakland, CA, USA.,Johnson & Johnson MedTech, New Brunswick, NJ, USA
| | - Bharti Goel
- Johnson & Johnson MedTech, New Brunswick, NJ, USA
| | | | | | | | | | | |
Collapse
|
12
|
Morris MX, Rajesh A, Asaad M, Hassan A, Saadoun R, Butler CE. Deep Learning Applications in Surgery: Current Uses and Future Directions. Am Surg 2023; 89:36-42. [PMID: 35567312 DOI: 10.1177/00031348221101490] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Deep learning (DL) is a subset of machine learning that is rapidly gaining traction in surgical fields. Its tremendous capacity for powerful data-driven problem-solving has generated computational breakthroughs in many realms, with the fields of medicine and surgery becoming increasingly prominent avenues. Through its multi-layer architecture of interconnected neural networks, DL enables feature extraction and pattern recognition of highly complex and large-volume data. Across various surgical specialties, DL is being applied to optimize both preoperative planning and intraoperative performance in new and innovative ways. Surgeons are now able to integrate deep learning tools into their practice to improve patient safety and outcomes. Through this review, we explore the applications of deep learning in surgery and related subspecialties with an aim to shed light on the practical utilization of this technology in the present and near future.
Collapse
Affiliation(s)
- Miranda X Morris
- 12277Duke University School of Medicine, Durham, NC, USA.,101571Duke Pratt School of Engineering, Durham, NC, USA
| | - Aashish Rajesh
- Department of Surgery, 14742University of Texas Health Science Center at San Antonio, San Antonio, TX, USA
| | - Malke Asaad
- Department of Plastic Surgery, 6595University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - Abbas Hassan
- Department of Plastic Surgery, 571198The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Rakan Saadoun
- Department of Plastic Surgery, 6595University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - Charles E Butler
- Department of Plastic Surgery, 571198The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|
13
|
Zhang B, Sturgeon D, Shankar AR, Goel VK, Barker J, Ghanem A, Lee P, Milecky M, Stottler N, Petculescu S. Surgical instrument recognition for instrument usage documentation and surgical video library indexing. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING: IMAGING & VISUALIZATION 2022. [DOI: 10.1080/21681163.2022.2152371] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Affiliation(s)
- Bokai Zhang
- Digital Solutions, Johnson & Johnson MedTech, Seattle, WA, USA
| | - Darrick Sturgeon
- Digital Solutions, Johnson & Johnson MedTech, Santa Clara, CA, USA
| | | | | | - Jocelyn Barker
- Digital Solutions, Johnson & Johnson MedTech, Santa Clara, CA, USA
| | - Amer Ghanem
- Digital Solutions, Johnson & Johnson MedTech, Seattle, WA, USA
| | - Philip Lee
- Digital Solutions, Johnson & Johnson MedTech, Santa Clara, CA, USA
| | - Meghan Milecky
- Digital Solutions, Johnson & Johnson MedTech, Seattle, WA, USA
| | | | | |
Collapse
|