Abstract
Background
Artificial intelligence (AI) holds tremendous potential to reduce surgical risks and improve surgical assessment. Machine learning, a subfield of AI, can be used to analyze surgical video and imaging data. Manual annotations provide veracity about the desired target features. Yet, methodological annotation explorations are limited to date. Here, we provide an exploratory analysis of the requirements and methods of instrument annotation in a multi-institutional team from two specialized AI centers and compile our lessons learned.
Methods
We developed a bottom-up approach for team annotation of robotic instruments in robot-assisted partial nephrectomy (RAPN), which was subsequently validated in robot-assisted minimally invasive esophagectomy (RAMIE). Furthermore, instrument annotation methods were evaluated for their use in Machine Learning algorithms. Overall, we evaluated the efficiency and transferability of the proposed team approach and quantified performance metrics (e.g., time per frame required for each annotation modality) between RAPN and RAMIE.
Results
We found a 0.05 Hz image sampling frequency to be adequate for instrument annotation. The bottom-up approach in annotation training and management resulted in accurate annotations and demonstrated efficiency in annotating large datasets. The proposed annotation methodology was transferrable between both RAPN and RAMIE. The average annotation time for RAPN pixel annotation ranged from 4.49 to 12.6 min per image; for vector annotation, we denote 2.92 min per image. Similar annotation times were found for RAMIE. Lastly, we elaborate on common pitfalls encountered throughout the annotation process.
Conclusions
We propose a successful bottom-up approach for annotator team composition, applicable to any surgical annotation project. Our results set the foundation to start AI projects for instrument detection, segmentation, and pose estimation. Due to the immense annotation burden resulting from spatial instrumental annotation, further analysis into sampling frequency and annotation detail needs to be conducted.
Graphical abstract
Similar content being viewed by others
References
Loftus TJ, Vlaar APJ, Hung AJ, Bihorac A, Dennis BM, Juillard C et al (2022) Executive summary of the artificial intelligence in surgery series. Surgery 171(5):1435–1439
Shvets AA, Rakhlin A, Kalinin AA, Iglovikov VI (2018) Automatic instrument segmentation in robot-assisted surgery using deep learning. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA). pp 624–628
Meireles OR, Rosman G, Altieri MS, Carin L, Hager G, Madani A et al (2021) SAGES consensus recommendations on an annotation framework for surgical video. Surg Endosc 35(9):4918–4929
Ward TM, Mascagni P, Ban Y, Rosman G, Padoy N, Meireles O et al (2021) Computer vision in surgery. Surgery 169(5):1253–1256
Ward TM, Fer DM, Ban Y, Rosman G, Meireles OR, Hashimoto DA (2021) Challenges in surgical video annotation. Comput Assist Surg (Abingdon) 26(1):58–68
Allan M, Kondo S, Bodenstedt S, Leger S, Kadkhodamohammadi R, Luengo I et al (2020) 2018 robotic scene segmentation challenge. arXiv [cs.CV]. Available from: http://arxiv.org/abs/2001.11190
Maier-Hein L, Mersmann S, Kondermann D, Bodenstedt S, Sanchez A, Stock C et al (2014) Can masses of non-experts train highly accurate image classifiers? A crowdsourcing approach to instrument segmentation in laparoscopic images. Med Image Comput Comput Assist Interv 17(Pt 2):438–445
Twinanda AP, Shehata S, Mutter D, Marescaux J, de Mathelin M, Padoy N (2017) EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imaging 36(1):86–97
Fuchs HF, Müller DT, Leers JM, Schröder W, Bruns CJ (2019) Modular step-up approach to robot-assisted transthoracic esophagectomy-experience of a German high volume center. Transl Gastroenterol Hepatol 4:62
Hashimoto DA, Rosman G, Meireles OR (2021) Artificial intelligence in surgery: understanding the role of AI in surgical practice. McGraw-Hill Education, New York
Maier-Hein L, Eisenmann M, Reinke A, Onogur S, Stankovic M, Scholz P et al (2018) Why rankings of biomedical image analysis competitions should be interpreted with care. Nat Commun 9(1):5217
Kornilov AS, Safonov IV (2018) An overview of watershed algorithm implementations in open source libraries. J Imaging 4(10):123
Reinke A, Tizabi MD, Sudre CH, Eisenmann M, Rädsch T, Baumgartner M et al (2021) Common limitations of image processing metrics: a picture story. arXiv [eess.IV]. Available from: http://arxiv.org/abs/2104.05642
Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder–decoder with atrous separable convolution for semantic image segmentation. arXiv [csCV]. Available from: https://arxiv.org/abs/1802.02611
Roß T, Reinke A, Full PM, Wagner M, Kenngott H, Apitz M et al (2021) Comparative validation of multi-instance instrument segmentation in endoscopy: results of the ROBUST-MIS 2019 challenge. Med Image Anal 70:101920
Maier-Hein L, Wagner M, Ross T, Reinke A, Bodenstedt S, Full PM et al (2020) Heidelberg colorectal data set for surgical data science in the sensor operating room. arXiv [cs.CV]. Available from: http://arxiv.org/abs/2005.03501
Rahman MM, Davis DN (2013) Addressing the class imbalance problem in medical datasets. Int J Mach Learn Comput 3:224–228
Madad Zadeh S, Francois T, Calvet L, Chauvet P, Canis M, Bartoli A et al (2020) SurgAI: deep learning for computerized laparoscopic image understanding in gynaecology. Surg Endosc 34(12):5377–5383
Mascagni P, Vardazaryan A, Alapatt D, Urade T, Emre T, Fiorillo C et al (2022) Artificial intelligence for surgical safety: automatic assessment of the critical view of safety in laparoscopic cholecystectomy using deep learning. Ann Surg 275(5):955–961
Acknowledgements
The authors are grateful to Francesco Cisternino, Esma Bensiali and Federica Ferraguti for their support in image post-processing. We also thank Joni Dambre for technical input in annotation methodolgies, and Saar Vermijs for general support in data collection. The authors are grateful for organizational help and support of Margot Troch and the initial annotation exploration by Matthias Boeykens. Lastly, the authors thank Flanders Innovation and Entrepreneurship for funding this research.
Funding
Flanders Innovation & Entrepreneurship Agency (Reference HBC.2020.2252).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Disclosures
Pieter De Backer has no conflict of interest or financial ties to disclose, funding by the Flanders Innovation & Entrepreneurship Agency—HBC.2020.2252. Jennifer A. Eckhoff has no conflict of interest or financial ties to disclose, Educational Funding Olympus Corporation, Japan. Jente Simoens, Dolores T. Müller, Charlotte Allaeys, Heleen Creemers, Amélie Hallemeesch, Kenzo Mestdagh, Charles Van Praet, Charlotte Debbaut, Karel Decaestecker, Christiane J. Bruns, Ozanan Meireles, Alexandre Mottrie, and Hans F. Fuchs have no conflict of interest or financial ties to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
De Backer, P., Eckhoff, J.A., Simoens, J. et al. Multicentric exploration of tool annotation in robotic surgery: lessons learned when starting a surgical artificial intelligence project. Surg Endosc 36, 8533–8548 (2022). https://doi.org/10.1007/s00464-022-09487-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00464-022-09487-1