Top

Published in:

01-12-2024 | Artificial Intelligence | Original Article

Deep learning-based video-analysis of instrument motion in microvascular anastomosis training

Authors: Taku Sugiyama, Hiroyuki Sugimori, Minghui Tang, Yasuhiro Ito, Masayuki Gekka, Haruto Uchino, Masaki Ito, Katsuhiko Ogasawara, Miki Fujimura

Published in: Acta Neurochirurgica | Issue 1/2024

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.

Available only for authorised users

Aoun SG, El Ahmadieh TY, El Tecle NE, Daou MR, Adel JG, Park CS, Batjer HH, Bendok BR (2015) A pilot study to assess the construct and face validity of the Northwestern Objective Microanastomosis Assessment Tool. J Neurosurg 123(1):103–109CrossRefPubMed

Belykh E, Abramov I, Bardonova L et al (2022) Seven bypasses simulation set: description and validity assessment of novel models for microneurosurgical training. J Neurosurg 138(3):732–739CrossRefPubMed

Castillo-Segura P, Fernández-Panadero C, Alario-Hoyos C, Muñoz-Merino PJ, Delgado Kloos C (2021) Objective and automated assessment of surgical technical skills with IoT systems: a systematic literature review. Artif Intell Med 112:102007CrossRefPubMed

Chmarra MK, Kolkman W, Jansen FW, Grimbergen CA, Dankelman J (2007) The influence of experience and camera holding on laparoscopic instrument movements measured with the TrEndo tracking system. Surg Endosc Other Interv Tech Surg Endosc 2069–2075

Datta V, Mackay S, Mandalia M, Darzi A (2001) The use of electromagnetic motion tracking analysis to objectively measure open surgical skill in the laboratory-based model. J Am Coll Surg 193(5):479–485CrossRefPubMed

Davids J, Makariou SG, Ashrafian H, Darzi A, Marcus HJ, Giannarou S (2021) Automated vision-based microsurgical skill analysis in neurosurgery using deep learning: development and preclinical validation. World Neurosurg 149:e669–e686CrossRefPubMed

Fujimura M, Tominaga T, Kuroda S, Takahashi JC, Endo H, Ogasawara K, Miyamoto S (2022) 2021 Japanese guidelines for the management of moyamoya disease: guidelines from the Research Committee on Moyamoya Disease and Japan Stroke Society. Neurol Med Chir (Tokyo) 62(4):165–170CrossRefPubMed

Ghasemloonia A, Maddahi Y, Zareinia K, Lama S, Dort JC, Sutherland GR (2017) Surgical skill assessment using motion quality and smoothness. J Surg Educ 74(2):295–305CrossRefPubMed

Harada K, Morita A, Minakawa Y, Baek YM, Sora S, Sugita N, Kimura T, Tanikawa R, Ishikawa T, Mitsuishi M (2015) Assessing microneurosurgical skill with medico-engineering technology. World Neurosurg 84(4):964–971CrossRefPubMed

10.

Housley SB, Vakharia K, Gong AD, Waqas M, Rho K, Levy EI, Davies JM, Siddiqui AH (2022) Extracranial-to-intracranial bypass for distal internal carotid artery and/or proximal middle cerebral artery steno-occlusive disease: a case series of clinical outcomes at a single, high-volume cerebrovascular center. Oper Neurosurg 23(3):177–181CrossRef

11.

Khalid S, Goldenberg M, Grantcharov T, Taati B, Rudzicz F (2020) Evaluation of deep learning models for identifying surgical actions and measuring performance. JAMA Netw open 3(3):e201664CrossRefPubMed

12.

Lam K, Chen J, Wang Z, Iqbal FM, Darzi A, Lo B, Purkayastha S, Kinross JM (2022) Machine learning for technical skill assessment in surgery: a systematic review. npj Digit Med 5(1):24CrossRefPubMedPubMedCentral

13.

Lawton MT, Lang MJ (2019) The future of open vascular neurosurgery: perspectives on cavernous malformations, AVMs, and bypasses for complex aneurysms. J Neurosurg 130(5):1409–1425CrossRefPubMed

14.

Mackay S, Datta V, Mandalia M, Bassett P, Darzi A (2002) Electromagnetic motion analysis in the assessment of surgical skill: relationship between time and movement. ANZ J Surg 72(9):632–634CrossRefPubMed

15.

Martin JA, Regehr G, Reznick R, Macrae H, Murnaghan J, Hutchison C, Brown M (1997) Objective structured assessment of technical skill (OSATS) for surgical residents. Br J Surg 84(2):273–278PubMed

16.

McBeth PB, Louw DF, Yang F, Sutherland GR (2005) Quantitative measures of performance in microvascular anastomoses. Comput Aided Surg 10(3):173–180CrossRefPubMed

17.

McGoldrick RB, Davis CR, Paro J, Hui K, Nguyen D, Lee GK (2015) Motion analysis for microsurgical training: objective measures of dexterity, economy of movement, and ability. Plast Reconstr Surg 136(2):231e–240eCrossRefPubMed

18.

Mikami T, Suzuki H, Ukai R, Komatsu K, Kimura Y, Akiyama Y, Wanibuchi M, Mikuni N (2018) Surgical anatomy of rats for the training of microvascular anastomosis. World Neurosurg 120:e1310–e1318CrossRefPubMed

19.

Miyamoto S, Yoshimoto T, Hashimoto N et al (2014) Effects of extracranial-intracranial bypass for patients with hemorrhagic moyamoya disease: results of the Japan adult moyamoya trial. Stroke 45(5):1415–1421CrossRefPubMed

20.

Niveditha M, Sharma R, Suri A (2022) Microsurgical suturing assessment scores: a systematic review. Neurosurg Rev 45(1):119–124CrossRef

21.

Pines AR, Alghoul MS, Hamade YJ et al (2017) Assessment of the interrater reliability of the congress of neurological surgeons microanastomosis assessment scale. Oper Neurosurg 13(1):108–112CrossRef

22.

Rashad S, Fujimura M, Niizuma K, Endo H, Tominaga T (2016) Long-term follow-up of pediatric moyamoya disease treated by combined direct–indirect revascularization surgery: single institute experience with surgical and perioperative management. Neurosurg Rev 39(4):615–623CrossRefPubMed

23.

Reynolds MR, Grubb RL, Clarke WR, Powers WJ, Zipfel GJ, Adams HP, Derdeyn CP (2013) Investigating the mechanisms of perioperative ischemic stroke in the Carotid Occlusion Surgery Study. J Neurosurg 119(4):988–995CrossRefPubMed

24.

Satterwhite T, Son J, Carey J, Echo A, Spurling T, Paro J, Gurtner G, Chang J, Lee GK (2014) The stanford microsurgery and resident training (SMaRT) scale: validation of an on-line global rating scale for technical assessment. Ann Plast Surg 72(SUPPL. 1):S84–S88CrossRefPubMed

25.

Sekhar LN, Kalavakonda C (2002) Cerebral revascularization for aneurysms and tumors. Neurosurgery 50(2):321–331PubMed

26.

Sugimori H, Sugiyama T, Nakayama N, Yamashita A, Ogasawara K (2020) Development of a deep learning-based algorithm to detect the distal end of a surgical instrument. Appl Sci 10(12):4245CrossRef

27.

Sugiyama T (2017) Mastering intracranial microvascular anastomoses—basic techniques and surgical pearls. Medicus Shuppan, Publishers Co., Ltd

28.

Sugiyama T, Clapp T, Nelson J et al (2021) Immersive 3-dimensional virtual reality modeling for case-specific presurgical discussions in cerebrovascular neurosurgery. Oper Neurosurg 20(3):289–299CrossRef

29.

Sugiyama T, Gan LS, Zareinia K, Lama S, Sutherland GR (2017) Tool-tissue interaction forces in brain arteriovenous malformation surgery. World Neurosurg 102:221–228CrossRefPubMed

30.

Sugiyama T, Ito M, Sugimori H et al (2023) Tissue acceleration as a novel metric for surgical performance during carotid endarterectomy. Oper Neurosurg 25(4):343–352CrossRef

31.

Sugiyama T, Kazumata K, Asaoka K, Osanai T, Shimbo D, Uchida K, Yokoyama Y, Nakayama N, Itamoto K, Houkin K (2015) Reappraisal of microsurgical revascularization for anterior circulation ischemia in patients with progressive stroke. World Neurosurg 84(6):1579–1588CrossRefPubMed

32.

Sugiyama T, Lama S, Gan LS, Maddahi Y, Zareinia K, Sutherland GR (2018) Forces of tool-tissue interaction to assess surgical skill level. JAMA Surg 153(3):234–242CrossRefPubMed

33.

Sugiyama T, Nakamura T, Ito Y, Tokairin K, Kazumata K, Nakayama N, Houkin K (2019) A pilot study on measuring tissue motion during carotid surgery using video-based analyses for the objective assessment of surgical performance. World J Surg 43(9):2309–2319CrossRefPubMed

34.

Takagi Y, Kikuta KI, Nozaki K, Hashimoto N (2007) Histological features of middle cerebral arteries from patients treated for moyamoya disease. Neurol Med Chir (Tokyo) 47(1):1–4CrossRefPubMed

35.

Wolfswinkel EM, Landau MJ, Ravina K, Kokot NC, Russin JJ, Carey JN (2018) EC-IC bypass for cerebral revascularization following skull base tumor resection: current practices and innovations. J Surg Oncol 118(5):815–825CrossRefPubMed

36.

Zareinia K, Maddahi Y, Gan LS, Ghasemloonia A, Lama S, Sugiyama T, Yang FW, Sutherland GR (2016) A force-sensing bipolar forceps to quantify tool-tissue interaction forces in microsurgery. IEEE/ASME Trans Mechatron 21(5):2365–2377CrossRef

Title: Deep learning-based video-analysis of instrument motion in microvascular anastomosis training
Authors: Taku Sugiyama
Hiroyuki Sugimori
Minghui Tang
Yasuhiro Ito
Masayuki Gekka
Haruto Uchino
Masaki Ito
Katsuhiko Ogasawara
Miki Fujimura
Publication date: 01-12-2024
Publisher: Springer Vienna
Keyword: Artificial Intelligence
Published in: Acta Neurochirurgica / Issue 1/2024
Print ISSN: 0001-6268
Electronic ISSN: 0942-0940
DOI: https://doi.org/10.1007/s00701-024-05896-4

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Deep learning-based video-analysis of instrument motion in microvascular anastomosis training

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2024

Beyond fluorescence-guided resection: 5-ALA-based glioblastoma therapies

How I do it: dual operation channels percutaneous endoscopic far-lateral transforaminal lumbar interbody fusion

On the use of flexible endoscopes to aspirate intraventricular hemorrhage, off-label innovations, and regulations

Effect of the pipeline embolization device placement on branching vessels in anterior circulation: a systematic review and meta-analysis

The association between head injury and facial fracture treatment: an observational study of hospitalized bicyclists from a level 1 trauma centre

Risk factors for prolonged length of stay after first single-level lumbar microdiscectomy