Martin Wagner

Matthias Eisenmann, Annika Reinke, Vivienn Weru et al. · utoronto

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Matthias Eisenmann, Annika Reinke, Vivienn Weru et al.

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and postprocessing (66%). The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

Open-H-Embodiment Consortium, Nigel Nelson, Juo-Tung Chen et al.

Autonomous medical robots hold promise to improve patient outcomes, reduce provider workload, democratize access to care, and enable superhuman precision. However, autonomous medical robotics has been limited by a fundamental data problem: existing medical robotic datasets are small, single-embodiment, and rarely shared openly, restricting the development of foundation models that the field needs to advance. We introduce Open-H-Embodiment, the largest open dataset of medical robotic video with synchronized kinematics to date, spanning more than 49 institutions and multiple robotic platforms including the CMR Versius, Intuitive Surgical's da Vinci, da Vinci Research Kit (dVRK), Rob Surgical BiTrack, Virtual Incision's MIRA, Moon Surgical Maestro, and a variety of custom systems, spanning surgical manipulation, robotic ultrasound, and endoscopy procedures. We demonstrate the research enabled by this dataset through two foundation models. GR00T-H is the first open foundation vision-language-action model for medical robotics, which is the only evaluated model to achieve full end-to-end task completion on a structured suturing benchmark (25% of trials vs. 0% for all others) and achieves 64% average success across a 29-step ex vivo suturing sequence. We also train Cosmos-H-Surgical-Simulator, the first action-conditioned world model to enable multi-embodiment surgical simulation from a single checkpoint, spanning nine robotic platforms and supporting in silico policy evaluation and synthetic data generation for the medical domain. These results suggest that open, large-scale medical robot data collection can serve as critical infrastructure for the research community, enabling advances in robot learning, world modeling, and beyond.

Benjamin Alt, Christian Kunz, Darko Katic et al.

The semantic segmentation of surgical scenes is a prerequisite for task automation in robot assisted interventions. We propose LapSeg3D, a novel DNN-based approach for the voxel-wise annotation of point clouds representing surgical scenes. As the manual annotation of training data is highly time consuming, we introduce a semi-autonomous clustering-based pipeline for the annotation of the gallbladder, which is used to generate segmented labels for the DNN. When evaluated against manually annotated data, LapSeg3D achieves an F1 score of 0.94 for gallbladder segmentation on various datasets of ex-vivo porcine livers. We show LapSeg3D to generalize accurately across different gallbladders and datasets recorded with different RGB-D camera systems.

Lorenzo Mazza, Ariel Rodriguez, Rayan Younis et al.

Imitation learning has achieved remarkable success in robotic manipulation, yet its application to surgical robotics remains challenging due to data scarcity, constrained workspaces, and the need for an exceptional level of safety and predictability. We present a supervised Mixture-of-Experts (MoE) architecture designed for phase-structured surgical manipulation tasks, which can be added on top of any autonomous policy. Unlike prior surgical robot learning approaches that rely on multi-camera setups or thousands of demonstrations, we show that a lightweight action decoder policy like Action Chunking Transformer (ACT) can learn complex, long-horizon manipulation from less than 150 demonstrations using solely stereo endoscopic images, when equipped with our architecture. We evaluate our approach on the collaborative surgical task of bowel grasping and retraction, where a robot assistant interprets visual cues from a human surgeon, executes targeted grasping on deformable tissue, and performs sustained retraction. We benchmark our method against state-of-the-art Vision-Language-Action (VLA) models and the standard ACT baseline. Our results show that generalist VLAs fail to acquire the task entirely, even under standard in-distribution conditions. Furthermore, while standard ACT achieves moderate success in-distribution, adopting a supervised MoE architecture significantly boosts its performance, yielding higher success rates in-distribution and demonstrating superior robustness in out-of-distribution scenarios, including novel grasp locations, reduced illumination, and partial occlusions. Notably, it generalizes to unseen testing viewpoints and also transfers zero-shot to ex vivo porcine tissue without additional training, offering a promising pathway toward in vivo deployment. To support this, we present qualitative preliminary results of policy roll-outs during in vivo porcine surgery.

Reuben Docea, Rayan Younis, Yonghao Long et al.

The D4D Dataset provides paired endoscopic video and high-quality structured-light geometry for evaluating 3D reconstruction of deforming abdominal soft tissue in realistic surgical conditions. Data were acquired from six porcine cadaver sessions using a da Vinci Xi stereo endoscope and a Zivid structured-light camera, registered via optical tracking and manually curated iterative alignment methods. Three sequence types - whole deformations, incremental deformations, and moved-camera clips - probe algorithm robustness to non-rigid motion, deformation magnitude, and out-of-view updates. Each clip provides rectified stereo images, per-frame instrument masks, stereo depth, start/end structured-light point clouds, curated camera poses and camera intrinsics. In postprocessing, ICP and semi-automatic registration techniques are used to register data, and instrument masks are created. The dataset enables quantitative geometric evaluation in both visible and occluded regions, alongside photometric view-synthesis baselines. Comprising over 300,000 frames and 369 point clouds across 98 curated recordings, this resource can serve as a comprehensive benchmark for developing and evaluating non-rigid SLAM, 4D reconstruction, and depth estimation methods.

Silvia Seidlitz, Jan Sellner, Jan Odenthal et al.

Semantic image segmentation is an important prerequisite for context-awareness and autonomous robotics in surgery. The state of the art has focused on conventional RGB video data acquired during minimally invasive surgery, but full-scene semantic segmentation based on spectral imaging data and obtained during open surgery has received almost no attention to date. To address this gap in the literature, we are investigating the following research questions based on hyperspectral imaging (HSI) data of pigs acquired in an open surgery setting: (1) What is an adequate representation of HSI data for neural network-based fully automated organ segmentation, especially with respect to the spatial granularity of the data (pixels vs. superpixels vs. patches vs. full images)? (2) Is there a benefit of using HSI data compared to other modalities, namely RGB data and processed HSI data (e.g. tissue parameters like oxygenation), when performing semantic organ segmentation? According to a comprehensive validation study based on 506 HSI images from 20 pigs, annotated with a total of 19 classes, deep learning-based segmentation performance increases, consistently across modalities, with the spatial context of the input data. Unprocessed HSI data offers an advantage over RGB data or processed data from the camera provider, with the advantage increasing with decreasing size of the input to the neural network. Maximum performance (HSI applied to whole images) yielded a mean DSC of 0.90 ((standard deviation (SD)) 0.04), which is in the range of the inter-rater variability (DSC of 0.89 ((standard deviation (SD)) 0.07)). We conclude that HSI could become a powerful image modality for fully-automatic surgical scene understanding with many advantages over traditional imaging, including the ability to recover additional functional tissue information. Code and pre-trained models: https://github.com/IMSY-DKFZ/htc.

Max Kirchner, Alexander C. Jenke, Sebastian Bodenstedt et al.

Purpose: In this study, we investigate the training of foundation models using federated learning to address data-sharing limitations and enable collaborative model training without data transfer for minimally invasive surgery. Methods: Inspired by the EndoViT study, we adapt the Masked Autoencoder for federated learning, enhancing it with adaptive Sharpness-Aware Minimization (FedSAM) and Stochastic Weight Averaging (SWA). Our model is pretrained on the Endo700k dataset collection and later fine-tuned and evaluated for tasks such as Semantic Segmentation, Action Triplet Recognition, and Surgical Phase Recognition. Results: Our findings demonstrate that integrating adaptive FedSAM into the federated MAE approach improves pretraining, leading to a reduction in reconstruction loss per patch. The application of FL-EndoViT in surgical downstream tasks results in performance comparable to CEN-EndoViT. Furthermore, FL-EndoViT exhibits advantages over CEN-EndoViT in surgical scene segmentation when data is limited and in action triplet recognition when large datasets are used. Conclusion: These findings highlight the potential of federated learning for privacy-preserving training of surgical foundation models, offering a robust and generalizable solution for surgical data science. Effective collaboration requires adapting federated learning methods, such as the integration of FedSAM, which can accommodate the inherent data heterogeneity across institutions. In future, exploring FL in video-based models may enhance these capabilities by incorporating spatiotemporal dynamics crucial for real-world surgical environments.

Alexander C. Jenke, Gregor Just, Claas de Boer et al.

Purpose: Robot-assisted minimally invasive surgery relies on endoscopic video as the sole intraoperative visual feedback. The DaVinci Xi system overlays a graphical user interface (UI) that indicates the state of each robotic arm, including the activation of the endoscope arm. Detecting this activation provides valuable metadata such as camera movement information, which can support downstream surgical data science tasks including tool tracking, skill assessment, or camera control automation. Methods: We developed a lightweight pipeline based on a ResNet18 convolutional neural network to automatically identify the position of the camera tile and its activation state within the DaVinci Xi UI. The model was fine-tuned on manually annotated data from the SurgToolLoc dataset and evaluated across three public datasets comprising over 70,000 frames. Results: The model achieved F1-scores between 0.993 and 1.000 for the binary detection of active cameras and correctly localized the camera tile in all cases without false multiple-camera detections. Conclusion: The proposed pipeline enables reliable, real-time extraction of camera activation metadata from surgical videos, facilitating automated preprocessing and analysis for diverse downstream applications. All code, trained models, and annotations are publicly available.

Paul Maria Scheikl, Balázs Gyenes, Tornike Davitashvili et al.

Cognitive cooperative assistance in robot-assisted surgery holds the potential to increase quality of care in minimally invasive interventions. Automation of surgical tasks promises to reduce the mental exertion and fatigue of surgeons. In this work, multi-agent reinforcement learning is demonstrated to be robust to the distribution shift introduced by pairing a learned policy with a human team member. Multi-agent policies are trained directly from images in simulation to control multiple instruments in a sub task of the minimally invasive removal of the gallbladder. These agents are evaluated individually and in cooperation with humans to demonstrate their suitability as autonomous assistants. Compared to human teams, the hybrid teams with artificial agents perform better considering completion time (44.4% to 71.2% shorter) as well as number of collisions (44.7% to 98.0% fewer). Path lengths, however, increase under control of an artificial agent (11.4% to 33.5% longer). A multi-agent formulation of the learning problem was favored over a single-agent formulation on this surgical sub task, due to the sequential learning of the two instruments. This approach may be extended to other tasks that are difficult to formulate within the standard reinforcement learning framework. Multi-agent reinforcement learning may shift the paradigm of cognitive robotic surgery towards seamless cooperation between surgeons and assistive technologies.

Martin Wagner, Beat-Peter Müller-Stich, Anna Kisilenko et al.

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center dataset. In this work we investigated the generalizability of phase recognition algorithms in a multi-center setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 hours was created. Labels included annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 teams submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n=9 teams), for instrument presence detection between 38.5% and 63.8% (n=8 teams), but for action recognition only between 21.8% and 23.3% (n=5 teams). The average absolute error for skill assessment was 0.78 (n=1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but are not solved yet, as shown by our comparison of algorithms. This novel benchmark can be used for comparable evaluation and validation of future work.

Lena Maier-Hein, Matthias Eisenmann, Duygu Sarikaya et al.

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

Lena Maier-Hein, Martin Wagner, Tobias Ross et al.

Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019.

Tobias Ross, Annika Reinke, Peter M. Full et al.

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

Sebastian Bodenstedt, Martin Wagner, Lars Mündermann et al.

Purpose The course of surgical procedures is often unpredictable, making it difficult to estimate the duration of procedures beforehand. A context-aware method that analyses the workflow of an intervention online and automatically predicts the remaining duration would alleviate these problems. As basis for such an estimate, information regarding the current state of the intervention is required. Methods Today, the operating room contains a diverse range of sensors. During laparoscopic interventions, the endoscopic video stream is an ideal source of such information. Extracting quantitative information from the video is challenging though, due to its high dimensionality. Other surgical devices (e.g. insufflator, lights, etc.) provide data streams which are, in contrast to the video stream, more compact and easier to quantify. Though whether such streams offer sufficient information for estimating the duration of surgery is uncertain. Here, we propose and compare methods, based on convolutional neural networks, for continuously predicting the duration of laparoscopic interventions based on unlabeled data, such as from endoscopic images and surgical device streams. Results The methods are evaluated on 80 laparoscopic interventions of various types, for which surgical device data and the endoscopic video are available. Here the combined method performs best with an overall average error of 37% and an average halftime error of 28%. Conclusion In this paper, we present, to our knowledge, the first approach for online procedure duration prediction using unlabeled endoscopic video data and surgical device data in a laparoscopic setting. We also show that a method incorporating both vision and device data performs better than methods based only on vision, while methods only based on tool usage and surgical device data perform poorly, showing the importance of the visual channel.

Sebastian Bodenstedt, Dominik Rivoir, Alexander Jenke et al.

For many applications in the field of computer assisted surgery, such as providing the position of a tumor, specifying the most probable tool required next by the surgeon or determining the remaining duration of surgery, methods for surgical workflow analysis are a prerequisite. Often machine learning based approaches serve as basis for surgical workflow analysis. In general machine learning algorithms, such as convolutional neural networks (CNN), require large amounts of labeled data. While data is often available in abundance, many tasks in surgical workflow analysis need data annotated by domain experts, making it difficult to obtain a sufficient amount of annotations. The aim of using active learning to train a machine learning model is to reduce the annotation effort. Active learning methods determine which unlabeled data points would provide the most information according to some metric, such as prediction uncertainty. Experts will then be asked to only annotate these data points. The model is then retrained with the new data and used to select further data for annotation. Recently, active learning has been applied to CNN by means of Deep Bayesian Networks (DBN). These networks make it possible to assign uncertainties to predictions. In this paper, we present a DBN-based active learning approach adapted for image-based surgical workflow analysis task. Furthermore, by using a recurrent architecture, we extend this network to video-based surgical workflow analysis. We evaluate these approaches on the Cholec80 dataset by performing instrument presence detection and surgical phase segmentation. Here we are able to show that using a DBN-based active learning approach for selecting what data points to annotate next outperforms a baseline based on randomly selecting data points.

Sebastian Bodenstedt, Antonia Ohnemus, Darko Katic et al.

During laparoscopic surgery, context-aware assistance systems aim to alleviate some of the difficulties the surgeon faces. To ensure that the right information is provided at the right time, the current phase of the intervention has to be known. Real-time locating and classification the surgical tools currently in use are key components of both an activity-based phase recognition and assistance generation. In this paper, we present an image-based approach that detects and classifies tools during laparoscopic interventions in real-time. First, potential instrument bounding boxes are detected using a pixel-wise random forest segmentation. Each of these bounding boxes is then classified using a cascade of random forest. For this, multiple features, such as histograms over hue and saturation, gradients and SURF feature, are extracted from each detected bounding box. We evaluated our approach on five different videos from two different types of procedures. We distinguished between the four most common classes of instruments (LigaSure, atraumatic grasper, aspirator, clip applier) and background. Our method succesfully located up to 86% of all instruments respectively. On manually provided bounding boxes, we achieve a instrument type recognition rate of up to 58% and on automatically detected bounding boxes up to 49%. To our knowledge, this is the first approach that allows an image-based classification of surgical tools in a laparoscopic setting in real-time.

Sebastian Bodenstedt, Max Allan, Anthony Agustinos et al.

Intraoperative segmentation and tracking of minimally invasive instruments is a prerequisite for computer- and robotic-assisted surgery. Since additional hardware like tracking systems or the robot encoders are cumbersome and lack accuracy, surgical vision is evolving as promising techniques to segment and track the instruments using only the endoscopic images. However, what is missing so far are common image data sets for consistent evaluation and benchmarking of algorithms against each other. The paper presents a comparative validation study of different vision-based methods for instrument segmentation and tracking in the context of robotic as well as conventional laparoscopic surgery. The contribution of the paper is twofold: we introduce a comprehensive validation data set that was provided to the study participants and present the results of the comparative validation study. Based on the results of the validation study, we arrive at the conclusion that modern deep learning approaches outperform other methods in instrument segmentation tasks, but the results are still not perfect. Furthermore, we show that merging results from different methods actually significantly increases accuracy in comparison to the best stand-alone method. On the other hand, the results of the instrument tracking task show that this is still an open challenge, especially during challenging scenarios in conventional laparoscopic surgery.

Tobias Ross, David Zimmerer, Anant Vemuri et al.

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue. Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a generative adversarial network (GAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task. The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical or medical data using the target task (in this instance: segmentation). As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.

Sebastian Bodenstedt, Martin Wagner, Darko Katić et al.

Computer-assisted surgery (CAS) aims to provide the surgeon with the right type of assistance at the right moment. Such assistance systems are especially relevant in laparoscopic surgery, where CAS can alleviate some of the drawbacks that surgeons incur. For many assistance functions, e.g. displaying the location of a tumor at the appropriate time or suggesting what instruments to prepare next, analyzing the surgical workflow is a prerequisite. Since laparoscopic interventions are performed via endoscope, the video signal is an obvious sensor modality to rely on for workflow analysis. Image-based workflow analysis tasks in laparoscopy, such as phase recognition, skill assessment, video indexing or automatic annotation, require a temporal distinction between video frames. Generally computer vision based methods that generalize from previously seen data are used. For training such methods, large amounts of annotated data are necessary. Annotating surgical data requires expert knowledge, therefore collecting a sufficient amount of data is difficult, time-consuming and not always feasible. In this paper, we address this problem by presenting an unsupervised method for training a convolutional neural network (CNN) to differentiate between laparoscopic video frames on a temporal basis. We extract video frames at regular intervals from 324 unlabeled laparoscopic interventions, resulting in a dataset of approximately 2.2 million images. From this dataset, we extract image pairs from the same video and train a CNN to determine their temporal order. To solve this problem, the CNN has to extract features that are relevant for comprehending laparoscopic workflow. Furthermore, we demonstrate that such a CNN can be adapted for surgical workflow segmentation. We performed image-based workflow segmentation on a publicly available dataset of 7 cholecystectomies and 9 colorectal interventions.