1
|
Tang M, Sugiyama T, Takahari R, Sugimori H, Yoshimura T, Ogasawara K, Kudo K, Fujimura M. Assessment of changes in vessel area during needle manipulation in microvascular anastomosis using a deep learning-based semantic segmentation algorithm: A pilot study. Neurosurg Rev 2024; 47:200. [PMID: 38722409 DOI: 10.1007/s10143-024-02437-6] [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: 07/18/2023] [Revised: 03/14/2024] [Accepted: 04/27/2024] [Indexed: 03/05/2025]
Abstract
Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety.
Collapse
Affiliation(s)
- Minghui Tang
- Department of Diagnostic Imaging, Hokkaido University Faculty of Medicine and Graduate School of Medicine, Sapporo, Japan
- Clinical AI Human Resources Development Program, Hokkaido University Graduate School of Biomedical Science and Engineering, Sapporo, Japan
- Medical AI Research and Development Center, Hokkaido University Hospital, Sapporo, Japan
| | - Taku Sugiyama
- Medical AI Research and Development Center, Hokkaido University Hospital, Sapporo, Japan.
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-ku, Sapporo, 060-8638, Japan.
| | - Ren Takahari
- Graduate School of Health Sciences, Hokkaido University, Sapporo, Japan
| | - Hiroyuki Sugimori
- Clinical AI Human Resources Development Program, Hokkaido University Graduate School of Biomedical Science and Engineering, Sapporo, Japan
- Medical AI Research and Development Center, Hokkaido University Hospital, Sapporo, Japan
- Department of Biomedical Science and Engineering, Faculty of Health Sciences, Hokkaido University, Sapporo, Japan
| | - Takaaki Yoshimura
- Department of Health Sciences and Technology, Faculty of Health Sciences, Hokkaido University, Sapporo, Japan
- Department of Medical Physics, Hokkaido University Hospital, Sapporo, Japan
| | - Katsuhiko Ogasawara
- Clinical AI Human Resources Development Program, Hokkaido University Graduate School of Biomedical Science and Engineering, Sapporo, Japan
- Department of Health Sciences and Technology, Faculty of Health Sciences, Hokkaido University, Sapporo, Japan
- Graduate School of Engineering, College of Information and Systems, Muroran Institute of Technology, Muroran, Japan
| | - Kohsuke Kudo
- Department of Diagnostic Imaging, Hokkaido University Faculty of Medicine and Graduate School of Medicine, Sapporo, Japan
- Clinical AI Human Resources Development Program, Hokkaido University Graduate School of Biomedical Science and Engineering, Sapporo, Japan
- Medical AI Research and Development Center, Hokkaido University Hospital, Sapporo, Japan
| | - Miki Fujimura
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-ku, Sapporo, 060-8638, Japan
| |
Collapse
|
2
|
Sugiyama T, Sugimori H, Tang M, Ito Y, Gekka M, Uchino H, Ito M, Ogasawara K, Fujimura M. Deep learning-based video-analysis of instrument motion in microvascular anastomosis training. Acta Neurochir (Wien) 2024; 166:6. [PMID: 38214753 DOI: 10.1007/s00701-024-05896-4] [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: 10/15/2023] [Accepted: 12/11/2023] [Indexed: 01/13/2024]
Abstract
PURPOSE Attaining sufficient microsurgical skills is paramount for neurosurgical trainees. Kinematic analysis of surgical instruments using video offers the potential for an objective assessment of microsurgical proficiency, thereby enhancing surgical training and patient safety. The purposes of this study were to develop a deep-learning-based automated instrument tip-detection algorithm, and to validate its performance in microvascular anastomosis training. METHODS An automated instrument tip-tracking algorithm was developed and trained using YOLOv2, based on clinical microsurgical videos and microvascular anastomosis practice videos. With this model, we measured motion economy (procedural time and path distance) and motion smoothness (normalized jerk index) during the task of suturing artificial blood vessels for end-to-side anastomosis. These parameters were validated using traditional criteria-based rating scales and were compared across surgeons with varying microsurgical experience (novice, intermediate, and expert). The suturing task was deconstructed into four distinct phases, and parameters within each phase were compared between novice and expert surgeons. RESULTS The high accuracy of the developed model was indicated by a mean Dice similarity coefficient of 0.87. Deep learning-based parameters (procedural time, path distance, and normalized jerk index) exhibited correlations with traditional criteria-based rating scales and surgeons' years of experience. Experts completed the suturing task faster than novices. The total path distance for the right (dominant) side instrument movement was shorter for experts compared to novices. However, for the left (non-dominant) side, differences between the two groups were observed only in specific phases. The normalized jerk index for both the right and left sides was significantly lower in the expert than in the novice groups, and receiver operating characteristic analysis showed strong discriminative ability. CONCLUSION The deep learning-based kinematic analytic approach for surgical instruments proves beneficial in assessing performance in microvascular anastomosis. Moreover, this methodology can be adapted for use in clinical settings.
Collapse
Affiliation(s)
- Taku Sugiyama
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan.
| | - Hiroyuki Sugimori
- Faculty of Health Sciences, Hokkaido University, Sapporo, 060-0812, Japan
| | - Minghui Tang
- Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| | - Yasuhiro Ito
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| | - Masayuki Gekka
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| | - Haruto Uchino
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| | - Masaki Ito
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| | | | - Miki Fujimura
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, North 15 West 7, Kita-Ku, Sapporo, 060-8638, Japan
| |
Collapse
|
3
|
Sugiyama T, Ito M, Sugimori H, Tang M, Nakamura T, Ogasawara K, Matsuzawa H, Nakayama N, Lama S, Sutherland GR, Fujimura M. Tissue Acceleration as a Novel Metric for Surgical Performance During Carotid Endarterectomy. Oper Neurosurg (Hagerstown) 2023; 25:343-352. [PMID: 37427955 DOI: 10.1227/ons.0000000000000815] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Accepted: 05/08/2023] [Indexed: 07/11/2023] Open
Abstract
BACKGROUND AND OBJECTIVES Gentle tissue handling to avoid excessive motion of affected fragile vessels during surgical dissection is essential for both surgeon proficiency and patient safety during carotid endarterectomy (CEA). However, a void remains in the quantification of these aspects during surgery. The video-based measurement of tissue acceleration is presented as a novel metric for the objective assessment of surgical performance. This study aimed to evaluate whether such metrics correlate with both surgeons' skill proficiency and adverse events during CEA. METHODS In a retrospective study including 117 patients who underwent CEA, acceleration of the carotid artery was measured during exposure through a video-based analysis. Tissue acceleration values and threshold violation error frequencies were analyzed and compared among the surgeon groups with different surgical experience (3 groups: novice , intermediate , and expert ). Multiple patient-related variables, surgeon groups, and video-based surgical performance parameters were compared between the patients with and without adverse events during CEA. RESULTS Eleven patients (9.4%) experienced adverse events after CEA, and the rate of adverse events significantly correlated with the surgeon group. The mean maximum tissue acceleration and number of errors during surgical tasks significantly decreased from novice, to intermediate, to expert surgeons, and stepwise discriminant analysis showed that the combined use of surgical performance factors could accurately discriminate between surgeon groups. The multivariate logistic regression analysis revealed that the number of errors and vulnerable carotid plaques were associated with adverse events. CONCLUSION Tissue acceleration profiles can be a novel metric for the objective assessment of surgical performance and the prediction of adverse events during surgery. Thus, this concept can be introduced into futuristic computer-aided surgeries for both surgical education and patient safety.
Collapse
Affiliation(s)
- Taku Sugiyama
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Masaki Ito
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | | | - Minghui Tang
- Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Toshitaka Nakamura
- Department of Neurosurgery, Sapporo Azabu Neurosurgical Hospital, Sapporo, Japan
| | | | - Hitoshi Matsuzawa
- Center for Integrated Human Brain Science, Brain Research Institute, University of Niigata, Niigata, Japan
- Department of Neurosurgery, Kashiwaba Neurosurgical Hospital, Sapporo, Japan
| | - Naoki Nakayama
- Department of Neurosurgery, Kashiwaba Neurosurgical Hospital, Sapporo, Japan
| | - Sanju Lama
- Department of Clinical Neurosciences and the Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
| | - Garnette R Sutherland
- Department of Clinical Neurosciences and the Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
| | - Miki Fujimura
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| |
Collapse
|
4
|
Sugiyama T, Clapp T, Nelson J, Eitel C, Motegi H, Nakayama N, Sasaki T, Tokairin K, Ito M, Kazumata K, Houkin K. Immersive 3-Dimensional Virtual Reality Modeling for Case-Specific Presurgical Discussions in Cerebrovascular Neurosurgery. Oper Neurosurg (Hagerstown) 2021; 20:289-299. [PMID: 33294936 DOI: 10.1093/ons/opaa335] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2020] [Accepted: 08/12/2020] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND Adequate surgical planning includes a precise understanding of patient-specific anatomy and is a necessity for neurosurgeons. Although the use of virtual reality (VR) technology is emerging in surgical planning and education, few studies have examined the effectiveness of immersive VR during surgical planning using a modern head-mounted display. OBJECTIVE To investigate if and how immersive VR aids presurgical discussions of cerebrovascular surgery. METHODS A multiuser immersive VR system, BananaVisionTM, was developed and used during presurgical discussions in a prospective patient cohort undergoing cerebrovascular surgery. A questionnaire/interview was administered to multiple surgeons after the surgeries to evaluate the effectiveness of the VR system compared to conventional imaging modalities. An objective assessment of the surgeon's knowledge of patient-specific anatomy was also conducted by rating surgeons' hand-drawn presurgical illustrations. RESULTS The VR session effectively enhanced surgeons' understanding of patient-specific anatomy in the majority of cases (83.3%). An objective assessment of surgeons' presurgical illustrations was consistent with this result. The VR session also effectively improved the decision-making process regarding minor surgical techniques in 61.1% of cases and even aided surgeons in making critical surgical decisions about cases involving complex and challenging anatomy. The utility of the VR system was rated significantly higher by trainees than by experts. CONCLUSION Although rated as more useful by trainees than by experts, immersive 3D VR modeling increased surgeons' understanding of patient-specific anatomy and improved surgical strategy in certain cases involving challenging anatomy.
Collapse
Affiliation(s)
- Taku Sugiyama
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Tod Clapp
- Department of Biomedical Sciences, Colorado State University, Fort Collins, Colorado
| | - Jordan Nelson
- Department of Biomedical Sciences, Colorado State University, Fort Collins, Colorado
| | - Chad Eitel
- Department of Biomedical Sciences, Colorado State University, Fort Collins, Colorado
| | - Hiroaki Motegi
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Naoki Nakayama
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Tsukasa Sasaki
- Department of Radiology, Hokkaido University Hospital, Sapporo, Japan
| | - Kikutaro Tokairin
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Masaki Ito
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Ken Kazumata
- Department of Neurosurgery, Hokkaido University Graduate School of Medicine, Sapporo, Japan
| | - Kiyohiro Houkin
- Department of Emergent Neurocognition, Faculty of Health Sciences, Hokkaido University, Sapporo, Japan
| |
Collapse
|
5
|
Development of a Deep Learning-Based Algorithm to Detect the Distal End of a Surgical Instrument. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10124245] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
This work aims to develop an algorithm to detect the distal end of a surgical instrument using object detection with deep learning. We employed nine video recordings of carotid endarterectomies for training and testing. We obtained regions of interest (ROI; 32 × 32 pixels), at the end of the surgical instrument on the video images, as supervised data. We applied data augmentation to these ROIs. We employed a You Only Look Once Version 2 (YOLOv2) -based convolutional neural network as the network model for training. The detectors were validated to evaluate average detection precision. The proposed algorithm used the central coordinates of the bounding boxes predicted by YOLOv2. Using the test data, we calculated the detection rate. The average precision (AP) for the ROIs, without data augmentation, was 0.4272 ± 0.108. The AP with data augmentation, of 0.7718 ± 0.0824, was significantly higher than that without data augmentation. The detection rates, including the calculated coordinates of the center points in the centers of 8 × 8 pixels and 16 × 16 pixels, were 0.6100 ± 0.1014 and 0.9653 ± 0.0177, respectively. We expect that the proposed algorithm will be efficient for the analysis of surgical records.
Collapse
|
6
|
Pradarelli JC, Pavuluri Quamme SR, Yee A, Faerber AE, Dombrowski JC, King C, Greenberg CC. Surgical coaching to achieve the ABMS vision for the future of continuing board certification. Am J Surg 2020; 221:4-10. [PMID: 32631596 DOI: 10.1016/j.amjsurg.2020.06.014] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Revised: 06/12/2020] [Accepted: 06/12/2020] [Indexed: 01/26/2023]
Abstract
In February 2019, the American Board of Medical Specialties (ABMS) released the final report of the Continuing Board Certification: Vision for the Future initiative, issuing strong recommendations to replace ineffective, traditional mechanisms for physicians' maintenance of certification with meaningful strategies that strengthen professional self-regulation and simultaneously engender public trust. The Vision report charges ABMS Member Boards, including the American Board of Surgery (ABS), to develop and implement a more formative, less summative approach to continuing certification. To realize the ABMS's Vision in surgery, new programs must support the assessment of surgeons' performance in practice, identification of individualized performance gaps, tailored goals to address those gaps, and execution of personalized action plans with accountability and longitudinal support. Peer surgical coaching, especially when paired with video-based assessment, provides a structured approach that can meet this need. Surgical coaching was one of the approaches to continuing professional development that was discussed at an ABS-sponsored retreat in January 2020; this commentary review provides an overview of that discussion. The professional surgical societies, in partnership with the ABS, are uniquely positioned to implement surgical coaching programs to support the continuing certification of their membership. In this article, we provide historical context for board certification in surgery, interpret how the ABMS's Vision applies to surgical performance, and highlight recent developments in video-based assessment and peer surgical coaching. We propose surgical coaching as a foundational strategy for accomplishing the ABMS's Vision for continuing board certification in surgery.
Collapse
Affiliation(s)
- Jason C Pradarelli
- The Academy for Surgical Coaching, Madison, WI, USA; Brigham and Women's Hospital Department of Surgery, Boston, MA, USA
| | - Sudha R Pavuluri Quamme
- The Academy for Surgical Coaching, Madison, WI, USA; University of Wisconsin Department of Surgery, Wisconsin Surgical Outcomes Research Program, Madison, WI, USA
| | - Andrew Yee
- The Academy for Surgical Coaching, Madison, WI, USA; Washington University Department of Surgery, St Louis, MO, USA
| | | | | | - Cara King
- The Academy for Surgical Coaching, Madison, WI, USA; Cleveland Clinic Obstetrics, Gynecology & Women's Health Institute, Cleveland, OH, USA
| | - Caprice C Greenberg
- The Academy for Surgical Coaching, Madison, WI, USA; University of Wisconsin Department of Surgery, Wisconsin Surgical Outcomes Research Program, Madison, WI, USA.
| |
Collapse
|