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/.
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Introduction
Technologies that enable next-generation context-aware systems in the operating room are currently intensively researched in the domain of surgical workflow recognition [1]. Recent studies that apply machine learning algorithms to this task have shown highly promising results [2, 3]. To further support advances in this area, academic machine learning competitions are hosted regularly [4,32] which targets the analysis of set memberships of data elements. The centered bar charts which are arranged radially show the total number of frames a surgical instrument was visible in each set (i.e., individual instrument occurrence). Additionally, a bar chart that reflects the number of frames in which no instruments are visible, so-called idle frames, is also included in this view. The combinations of instruments (i.e., instrument co-occurrences) are displayed as nodes in the center of the instrument view. The nodes themselves are represented as pie charts, whereas each segment of the pie chart shows the prevalence of this instrument combination in the training, validation, and test set. The positioning of the nodes is determined by a force-directed layout algorithm implementation of the D3 library [30].
Instrument view of the proposed application with eight proctocolectomy surgeries from the “Surgical Workflow Analysis in the sensorOR 2017” challenge dataset [6] (A) and selected combination of Grasper and Ligasure (B)
To facilitate the exploration of the surgical instrument data, several interaction techniques are implemented in this view. By selecting an individual instrument, all instrument co-occurrence nodes that involve the selected instrument are highlighted in the Instrument view. Besides, co-occurrence nodes can be selected individually which reveals the proportion of co-occurrence frames in relation to the frames of the involved instruments (see Fig. 2B). Upon filtering of individual instruments or instrument co-occurrences, other views of the visual framework are updated accordingly to view the selected frames.
Supplementary views
The main views are enhanced by two supplementary views which provide a general overview of the dataset. The colors red, green, and blue encode the attributes of the training, validation, and test set, respectively. The first supplementary view represents a table that shows the partitioning of surgeries into the training, validation, and test sets. The individual surgeries can be interactively re-assigned to a different set via drag and drop. The second supplementary view encompasses two bar charts that display the total number of surgeries and frames for each set (see Fig. 3A). Additionally, a set of bar charts displaying the number of frames for each individual surgery are arranged on the right side of the view (see Fig. 3B). The average number of frames for each set is shown as dashed lines in the bar charts (see Fig. 3C).
Supplementary view of the proposed application. Two mirrored bar chars show the number of surgeries and the total number of video frames in the training, validation, and test set (A). A set of three bar charts display the duration (i.e., number of frames) of each surgery (B). The dashed lines show the average surgery duration per set (C)
Evaluation and results
The proposed visualization framework is evaluated through a user study using the Cholec80 dataset [7]. In addition to the user study, we use our framework to analyze splits of five popular datasets for the surgical phase and instrument recognition tasks, highlight problematic cases, and propose optimized splits.
User study
In total, ten participants with data science background have been recruited to participate in the evaluation study of the proposed visualization framework. After a brief introduction into the domain of surgical phase recognition and the features of the proposed application, the participants were asked to solve ten tasks covering a wide range of possible exploratory analyses that can arise during the preparation of Cholec80 dataset [7]. Further details on the user study are provided in the supplementary information. To measure the results of this study, task completion percentage was used, which has the value of 1 only if the participant solves the task correctly, 0 otherwise. Overall, the majority of the tasks were completed successfully by \(\ge 80\%\) of participants.
After completing the tasks, the participants were asked to fill out the System Usability Scale (SUS) [33] questionnaire. It consists of ten statements that the study participants ranked on a 5-point Likert scale ranging from 1 (strongly disagree) to 5 (strongly agree). The ranking of the statements is then used to calculate the SUS score which expresses the usability of the system. The value of the score ranges between 0 and 100, with higher values expressing better usability. The proposed application reached the SUS score of 81.25.
Analysis of dataset splits
In order to validate the proposed framework, we perform analysis of various dataset splits for the Cholec80 [7], CATARACTS [4A). Notably, all of the nine surgeries are assigned to the training set; therefore, the evaluation of the model’s performance on the test set does not include this special workflow. In addition, another unique workflow that only occurs in three surgeries (12, 14, 32) in the training set can be identified using the proposed visualization (see Fig. 4B). After the Gallbladder packaging phase, these three surgeries move on to the Gallbladder retraction, thus omitting the Cleaning coagulation phase. Subsequently, the surgeries return to the previously skipped Cleaning coagulation phase which is also the final phase of the three surgeries. Since this unique sequence of phases only appears in the training set, they are not included in the evaluation of the machine learning model. Proposed improvement: With this information at hand, the split can be optimized by re-assigning the surgeries 29, 32, 33, and 38 to the test set, as interactively determined in our tool. Accordingly, four randomly selected surgeries 58, 66, 71, 78 from the test set are assigned to the training set to retain the 40/-/40 split. As a result of this re-partition, the aforementioned cases of phase transitions now also appear in the test set.
Regarding the instrument use, the proposed visualization shows that all of the individual instruments are represented in all sets and also follow similar distributions. Nevertheless, there are several instrument combinations that do not occur in one of the sets (see Fig. 4C). However, these instruments combinations mostly represent rare cases, as they account for only a small fraction of the dataset and appear in single surgeries.
Characteristics and shortcomings of the 40/-/40 split of the Cholec80 dataset [7]. Surgeries starting in the Calot triangle dissection phase are only present in the training set (A). The ending sequence Gallbladder retraction to Cleaning coagulation occurs only in the training set (B). The instruments Bipolar and Scissors co-occur only in the training set (C)
32/8/40 split
To perform model selection or hyperparameter search, studies [11, 25, 37] use eight surgeries from the training set for validation, resulting in a 32/8/40 split [5B). This will presumably hinder the generalization of the model. Proposed improvement: This can be solved with our tool by re-assigning the surgery 14 to the validation set, surgeries 23, 29, 32 to the test set, and surgeries 37, 41, 57, 60 to the training set. Regarding the instruments, the co-occurrences of surgical instruments that are missing in one of the sets are more prevalent in this split due to the additional validation set. One considerable example is the simultaneous use of Grasper, Bipolar, and Irrigator occurring in 503 frames in the training set and in 154 frames in the test set (see Fig. 5C).
Characteristics and shortcomings of the 32/8/40 split of the Cholec80 dataset [7]. Surgeries from the validation set have fewer frames on average, compared to the training and test sets (A). The phase transitions (Gallbladder dissection, Cleaning coagulation) and (Cleaning coagulation, Gallbladder packaging) occur only once in the training set (B). The simultaneous occurrence of the instruments Grasper, Bipolar, and Irrigator is not represented in the validation set (C)
40/8/32 split
Instead of setting aside eight surgeries from the training set, some studies [11, Visualization of phase occurrences and transitions from the M2CAI-workflow dataset [7, Full size image Table 1 shows dataset splits of the five datasets as well as the number of phase transitions, and instrument combinations that are not represented in one of the sets. The improved dataset splits that are presented as part of this work are denoted with *.Summary of unrepresented cases
Discussion and future work
This work presents a publicly available visualization framework that facilitates interactive assessment of dataset splits for surgical phase and instrument recognition. The motivation for this has been previously outlined in some studies. Zisimopoulos et al. [9] report a high discrepancy of the model’s performance on validation and test sets which is attributed to some phases missing in the validation set. The problem of the inherent data imbalance of surgical workflow data has been previously highlighted in several works [7,8,9,10,11,12,13,14,15]. The visualization framework presented in this work is specifically designed to address these cases.
To validate the design of our application, we analyzed five common datasets using our tool. We were able to pinpoint several aspects of the dataset splits that can distort the evaluation of the model’s performance. Moreover, the application enabled us to eliminate some of these issues by interactively re-partitioning the sets. Nevertheless, the proposed visualization also bears certain limitations. The visualization of phase transitions solely shows the frequency each individual phase transition occurs in the dataset. While this visualization approach allows to successfully identify phase transitions that are unique, determining whether a particular sequence of transitions appears in a surgery can only be achieved by applying filtering in the Phase view. Therefore, unique workflow patterns may remain undiscovered by using the proposed application. The previous work by Blum et al. [27] presents a more suitable approach for the analysis of workflow patterns. Further, the visualization provides a heavily aggregated view of surgical phases and does not provide a visual representation of re-occurrences of phases, in case a phase has been repeated multiple times during a surgery. The work by Mayer et al. [28] allows for the understanding of the temporal relationships within surgical workflow data.
While the visualization of instruments displays total number of video frames per each individual instrument as well as the frames in which two or more instruments co-occur, it does not provide a clear visual representation of video frames in which only a single instrument is used. To view such cases, the user is required to perform filtering in the Instrument view, consequently making them less apparent. This issue should be addressed in the future work in order to provide a complete overview of the instrument usage data.
Using the insights from our visualization tool, we were able to successfully re-partition the datasets to achieve a better distribution of attributes across dataset splits. However, the re-partitioning was performed manually and likely does not represent the most optimal splitting. In future work, algorithms for the generation of optimal dataset splits [39] can be explored. Besides that, our analysis of dataset splits and the recommendations derived from it need to be supported by quantitative evaluations in the future work.
Further, the scope of this application is limited to the analysis of phase and instrument annotations. However, visual features, such as bad lighting conditions, over or underexposed instruments, and occlusions, have high influence on the performance of the model [22] and should be considered in the future work. Correspondingly, it can be also extended to support adjacent tasks including instrument and pathology detection or segmentation with bounding-box or pixel-level predictions to account for spatial relationships of the data. Finally, we also believe that integration of more fine-grained surgical activity information, such as action triplets [40], can provide a more sophisticated overview of surgical workflows.
Conclusion
In this work, we presented a publicly available application implemented for the research community that aims to facilitate visual exploration of dataset splits for surgical phase and instrument recognition. To validate the design of our application, we conducted a user study with ten participants. Further, we performed an analysis of common surgical phase and instrument recognition datasets and identified improvements in the splits using our tool. The results indicate that the proposed application can enhance the development process of machine learning models for surgical phase recognition by providing insights into the dataset splits, potentially resulting in more reliable performance evaluations. Furthermore, we believe that organizers of biomedical challenges can also greatly benefit from the proposed framework during the preparation of challenge datasets.
Code Availability
Source code is available at https://github.com/Cardio-AI/endovis-ml and the live application can be accessed at https://cardio-ai.github.io/endovis-ml/.
Change history
14 February 2024
Incorrect link in the code availability section has been updated.
References
Maier-Hein L, Vedula SS, Speidel S, Navab N, Kikinis R, Park A, Eisenmann M, Feussner H, Forestier G, Giannarou S, Hashizume M, Katic D, Kenngott H, Kranzfelder M, Malpani A, März K, Neumuth T, Padoy N, Pugh C, Schoch N, Stoyanov D, Taylor R, Wagner M, Hager GD, Jannin P (2017) Surgical data science for next-generation interventions. Nat Biomed Eng 1(9):691–696. https://doi.org/10.1038/s41551-017-0132-7
Garrow CR, Kowalewski K-F, Li L, Wagner M, Schmidt MW, Engelhardt S, Hashimoto DA, Kenngott HG, Bodenstedt S, Speidel S, Müller-Stich BP, Nickel F (2021) Machine learning for surgical phase recognition: a systematic review. Ann Surg 273(4):684. https://doi.org/10.1097/SLA.0000000000004425
Demir KC, Schieber H, Weise T, Roth D, May M, Maier A, Yang SH (2023) Deep learning in surgical workflow analysis: a review of phase and step recognition. IEEE J Biomed Health Inform 27(11):5405–5417. https://doi.org/10.1109/JBHI.2023.3311628
Nwoye CI, Yu T, Sharma S, Murali A, Alapatt D, Vardazaryan A, Yuan K, Hajek J, Reiter W, Yamlahi A, Smidt F-H, Zou X, Zheng G, Oliveira B, Torres HR, Kondo S, Kasai S, Holm F, Özsoy E, Gui S, Li H, Raviteja S, Sathish R, Poudel P, Bhattarai B, Wang Z, Rui G, Schellenberg M, Vilaça JL, Czempiel T, Wang Z, Sheet D, Thapa SK, Berniker M, Godau P, Morais P, Regmi S, Tran TN, Fonseca J, Nölke J-H, Lima E, Vazquez E, Maier-Hein L, Navab N, Mascagni P, Seeliger B, Gonzalez C, Mutter D, Padoy N (2023) CholecTriplet2022: show me a tool and tell me the triplet–an endoscopic vision challenge for surgical action triplet detection. Med Image Anal 89:102888. https://doi.org/10.1016/j.media.2023.102888
Huaulmé A, Harada K, Nguyen Q-M, Park B, Hong S, Choi M-K, Peven M, Li Y, Long Y, Dou Q, Kumar S, Lalithkumar S, Hongliang R, Matsuzaki H, Ishikawa Y, Harai Y, Kondo S, Mitsuishi M, Jannin P (April 2023) PEg TRAnsfer Workflow recognition challenge report: does multi-modal data improve recognition? Technical report. https://doi.org/10.48550/ar**v.2202.05821. ar**v:2202.05821 [cs] type: article
Maier-Hein L, Wagner M, Ross T, Reinke A, Bodenstedt S, Full PM, Hempe H, Mindroc-Filimon D, Scholz P, Tran TN, Bruno P, Kisilenko A, Müller B, Davitashvili T, Capek M, Tizabi MD, Eisenmann M, Adler TJ, Gröhl J, Schellenberg M, Seidlitz S, Lai TYE, Pekdemir B, Roethlingshoefer V, Both F, Bittel S, Mengler M, Mündermann L, Apitz M, Kopp-Schneider A, Speidel S, Nickel F, Probst P, Kenngott HG, Müller-Stich BP (2021) Heidelberg colorectal data set for surgical data science in the sensor operating room. Sci Data 8(1):101. https://doi.org/10.1038/s41597-021-00882-2
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. https://doi.org/10.1109/TMI.2016.2593957
Sahu M, Mukhopadhyay A, Szengel A, Zachow S (2017) Addressing multi-label imbalance problem of surgical tool detection using CNN. Int J Comput Assist Radiol Surg 12(6):1013–1020. https://doi.org/10.1007/s11548-017-1565-x
Zisimopoulos O, Flouty E, Luengo I, Giataganas P, Nehme J, Chow A, Stoyanov D (2018) DeepPhase: surgical phase recognition in CATARACTS videos. In: Medical image computing and computer assisted intervention—MICCAI 2018. Lecture notes in computer science. Springer, Cham, pp 265–272. https://doi.org/10.1007/978-3-030-00937-3_31
Al Hajj H, Lamard M, Conze P-H, Roychowdhury S, Hu X, Maršalkaitė G, Zisimopoulos O, Dedmari MA, Zhao F, Prellberg J, Sahu M, Galdran A, Araújo T, Vo DM, Panda C, Dahiya N, Kondo S, Bian Z, Vahdat A, Bialopetravičius J, Flouty E, Qiu C, Dill S, Mukhopadhyay A, Costa P, Aresta G, Ramamurthy S, Lee S-W, Campilho A, Zachow S, **a S, Conjeti S, Stoyanov D, Armaitis J, Heng P-A, Macready WG, Cochener B, Quellec G (2019) CATARACTS: challenge on automatic tool annotation for cataRACT surgery. Med Image Anal 52:24–41. https://doi.org/10.1016/j.media.2018.11.008
Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, Navab N (2020) TeCNO: surgical phase recognition with multi-stage temporal convolutional networks. In: Medical image computing and computer assisted intervention—MICCAI 2020. Lecture notes in computer science. Springer, Cham, pp 343–352. https://doi.org/10.1007/978-3-030-59716-0_33
Czempiel T, Paschali M, Ostler D, Kim ST, Busam B, Navab N (2021) OperA: attention-regularized transformers for surgical phase recognition. In: Medical image computing and computer assisted intervention—MICCAI 2021, vol 12904 , pp 604–614. https://doi.org/10.1007/978-3-030-87202-1_58
Ramesh S, Dall’Alba D, Gonzalez C, Yu T, Mascagni P, Mutter D, Marescaux J, Fiorini P, Padoy N (2021) Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures. Int J Comput Assist Radiol Surg 16(7):1111–1119. https://doi.org/10.1007/s11548-021-02388-z
Zhang B, Ghanem A, Simes A, Choi H, Yoo A (2021) Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy. Int J Comput Assist Radiol Surg 16(11):2029–2036. https://doi.org/10.1007/s11548-021-02473-3
Funke I, Rivoir D, Speidel S (May 2023) Metrics matter in surgical phase recognition. Technical report. https://doi.org/10.48550/ar**v.2305.13961
He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284. https://doi.org/10.1109/TKDE.2008.239
Zhang Y, Bano S, Page A-S, Deprest J, Stoyanov D, Vasconcelos F (2022) Large-scale surgical workflow segmentation for laparoscopic sacrocolpopexy. Int J Comput Assist Radiol Surg 17(3):467–477. https://doi.org/10.1007/s11548-021-02544-5
Neumuth T (2017) Surgical process modeling. Innov Surg Sci 2(3):123–137. https://doi.org/10.1515/iss-2017-0005
Ahmadi S-A, Sielhorst T, Stauder R, Horn M, Feussner H, Navab N (2006) Recovery of surgical workflow without explicit models. In: Larsen R, Nielsen M, Sporring J (eds) Medical image computing and computer-assisted intervention—MICCAI 2006. Lecture notes in computer science. Springer, Berlin, Heidelberg, pp 420–428. https://doi.org/10.1007/11866565_52
Padoy N, Blum T, Ahmadi S-A, Feussner H, Berger M-O, Navab N (2012) Statistical modeling and recognition of surgical workflow. Med Image Anal 16(3):632–641. https://doi.org/10.1016/j.media.2010.10.001
Wagner M, Müller-Stich B-P, Kisilenko A, Tran D, Heger P, Mündermann L, Lubotsky DM, Müller B, Davitashvili T, Capek M, Reinke A, Reid C, Yu T, Vardazaryan A, Nwoye CI, Padoy N, Liu X, Lee E-J, Disch C, Meine H, **a T, Jia F, Kondo S, Reiter W, ** Y, Long Y, Jiang M, Dou Q, Heng PA, Twick I, Kirtac K, Hosgor E, Bolmgren JL, Stenzel M, von Siemens B, Zhao L, Ge Z, Sun H, **e D, Guo M, Liu D, Kenngott HG, Nickel F, Frankenberg Mv, Mathis-Ullrich F, Kopp-Schneider A, Maier-Hein L, Speidel S, Bodenstedt S (2023) Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark. Med Image Anal 86:102770. https://doi.org/10.1016/j.media.2023.102770
** Y, Dou Q, Chen H, Yu L, Qin J, Fu C-W, Heng P-A (2018) SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans Med Imaging 37(5):1114–1126. https://doi.org/10.1109/TMI.2017.2787657
Gao X, ** Y, Long Y, Dou Q, Heng P-A (2021) Trans-SVNet: accurate phase recognition from surgical videos via hybrid embedding aggregation transformer. In: Medical image computing and computer assisted intervention—MICCAI 2021. Lecture notes in computer science. Springer, Cham, pp 593–603 (2021). https://doi.org/10.1007/978-3-030-87202-1_57
** Y, Long Y, Gao X, Stoyanov D, Dou Q, Heng P-A (2022) Trans-SVNet: hybrid embedding aggregation Transformer for surgical workflow analysis. Int J Comput Assist Radiol Surg 17(12):2193–2202. https://doi.org/10.1007/s11548-022-02743-8
Zou X, Liu W, Wang J, Tao R, Zheng G (2023) ARST: auto-regressive surgical transformer for phase recognition from laparoscopic videos. Comput Methods Biomech Biomed Eng Imaging Vis 11(4):1012–1018. https://doi.org/10.1080/21681163.2022.2145238
Pan X, Gao X, Wang H, Zhang W, Mu Y, He X (2023) Temporal-based Swin Transformer network for workflow recognition of surgical video. Int J Comput Assist Radiol Surg 18(1):139–147. https://doi.org/10.1007/s11548-022-02785-y
Blum T, Padoy N, Feußner H, Navab N (2008) Workflow mining for visualization and analysis of surgeries. Int J Comput Assist Radiol Surg 3(5):379–386. https://doi.org/10.1007/s11548-008-0239-0
Mayer B, Meuschke M, Chen J, Müller-Stich BP, Wagner M, Preim B, Engelhardt S (2023) Interactive visual exploration of surgical process data. Int J Comput Assist Radiol Surg 18(1):127–137. https://doi.org/10.1007/s11548-022-02758-1
Fox M, Schoeffmann K (2022) The impact of dataset splits on classification performance in medical videos. In: Proceedings of the 2022 international conference on multimedia retrieval. ICMR ’22. Association for Computing Machinery, New York, NY, USA, pp 6–10. https://doi.org/10.1145/3512527.3531424
Bostock M, Ogievetsky V, Heer J (2011) D\(^{3}\) data-driven documents. IEEE Trans Visual Comput Gr 17(12):2301–2309. https://doi.org/10.1109/TVCG.2011.185 pg
Wattenberg M (2002) Arc diagrams: visualizing structure in strings. In: IEEE symposium on information visualization, 2002. INFOVIS 2002, pp 110–116. https://doi.org/10.1109/INFVIS.2002.1173155. ISSN: 1522-404X
Alsallakh B, Aigner W, Miksch S, Hauser H (2013) Radial sets: interactive visual analysis of large overlap** sets. IEEE Trans Visual Comput Gr 19(12):2496–2505. https://doi.org/10.1109/TVCG.2013.184
Brooke J (1996) SUS: a ’quick and dirty’ usability scale. Usability evaluation in industry, pp 207–212. https://doi.org/10.1201/9781498710411-35
Grammatikopoulou M, Flouty E, Kadkhodamohammadi A, Quellec G, Chow A, Nehme J, Luengo I, Stoyanov D (2021) CaDIS: cataract dataset for surgical RGB-image segmentation. Med Image Anal 71:102053. https://doi.org/10.1016/j.media.2021.102053
Stauder R, Ostler D, Kranzfelder M, Koller S, Feußner H, Navab N (August 2017) The TUM LapChole dataset for the M2CAI 2016 workflow challenge. Technical report. https://doi.org/10.48550/ar**v.1610.09278. ar**v:1610.09278 [cs] type: article
Chen W, Feng J, Lu J, Zhou J (2018) Endo3D: online workflow analysis for endoscopic surgeries based on 3D CNN and LSTM. In: OR 2.0 context-aware operating theaters, computer assisted robotic endoscopy, clinical image-based procedures, and skin image analysis. Lecture notes in computer science. Springer, Cham, pp 97–107. https://doi.org/10.1007/978-3-030-01201-4_12
** Y, Li H, Dou Q, Chen H, Qin J, Fu C-W, Heng P-A (2020) Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Anal 59:101572. https://doi.org/10.1016/j.media.2019.101572
Rivoir D, Funke I, Speidel S (March 2023) On the pitfalls of batch normalization for end-to-end video learning: a study on surgical workflow analysis. Technical report. https://doi.org/10.48550/ar**v.2203.07976
Vakayil A, Joseph VR (2022) Data twinning. Stat Anal Data Min ASA Data Sci J 15(5):598–610. https://doi.org/10.1002/sam.11574
Sharma S, Nwoye CI, Mutter D, Padoy N (2023) Rendezvous in time: an attention-based temporal fusion approach for surgical triplet recognition. Int J Comput Assist Radiol Surg 18(6):1053–1059. https://doi.org/10.1007/s11548-023-02914-1
Acknowledgements
We thank the participants of the user study for their contribution to this work.
Funding
Open Access funding enabled and organized by Projekt DEAL. This work was supported by Informatics for Life funded by the Klaus Tschira Foundation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent
Informed consent was obtained from all individual participants of the user study.
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
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Kostiuchik, G., Sharan, L., Mayer, B. et al. Surgical phase and instrument recognition: how to identify appropriate dataset splits. Int J CARS 19, 699–711 (2024). https://doi.org/10.1007/s11548-024-03063-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-024-03063-9