Surgical Workflow Recognition Research Articles

Deep learning for surgical workflow analysis: a survey of progresses, limitations, and trends

Automatic surgical workflow analysis, which aims to recognize the ongoing surgical events in videos, is fundamental for developing context-aware computer-assisted systems. This paper reviews representative surgical workflow recognition algorithms based on deep learning, outlining their merits, limitations, and future research directions. The literature survey was performed on three large bibliographic databases, covering 67 lary sources, which were comparatively analyzed in terms of spatial feature modeling, spatio-temporal feature modeling, input pre-processing, regularization and post-processing algorithms, as well as learning strategies. Then, common public datasets and evaluation metrics for surgical workflow recognition are also described in detail. Finally, we discuss all literature from different perspectives, and point out the challenges, possible solutions and future trends. The need for more diverse and larger datasets, the potential of unsupervised and semi-supervised learning approaches, comprehensive and equitable metrics, establishing complete regulatory and data standards, and interoperability will be key challenges in translating models to clinical operating rooms. And we propose that surgical activity anticipation and employing large language model as training assistant are interesting research directions in surgical workflow analysis.

Multimodal semi-supervised learning for online recognition of multi-granularity surgical workflows

Purpose Surgical workflow recognition is a challenging task that requires understanding multiple aspects of surgery, such as gestures, phases, and steps. However, most existing methods focus on single-task or single-modal models and rely on costly annotations for training. To address these limitations, we propose a novel semi-supervised learning approach that leverages multimodal data and self-supervision to create meaningful representations for various surgical tasks. Methods Our representation learning approach conducts two processes. In the first stage, time contrastive learning is used to learn spatiotemporal visual features from video data, without any labels. In the second stage, multimodal VAE fuses the visual features with kinematic data to obtain a shared representation, which is fed into recurrent neural networks for online recognition. Results Our method is evaluated on two datasets: JIGSAWS and MISAW. We confirmed that it achieved comparable or better performance in multi-granularity workflow recognition compared to fully supervised models specialized for each task. On the JIGSAWS Suturing dataset, we achieve a gesture recognition accuracy of 83.3%. In addition, our model is more efficient in annotation usage, as it can maintain high performance with only half of the labels. On the MISAW dataset, we achieve 84.0% AD-Accuracy in phase recognition and 56.8% AD-Accuracy in step recognition. Conclusion Our multimodal representation exhibits versatility across various surgical tasks and enhances annotation efficiency. This work has significant implications for real-time decision-making systems within the operating room.

Research on workflow recognition for liver rupture repair surgery.

Liver rupture repair surgery serves as one tool to treat liver rupture, especially beneficial for cases of mild liver rupture hemorrhage. Liver rupture can catalyze critical conditions such as hemorrhage and shock. Surgical workflow recognition in liver rupture repair surgery videos presents a significant task aimed at reducing surgical mistakes and enhancing the quality of surgeries conducted by surgeons. A liver rupture repair simulation surgical dataset is proposed in this paper which consists of 45 videos collaboratively completed by nine surgeons. Furthermore, an end-to-end SA-RLNet, a self attention-based recurrent convolutional neural network, is introduced in this paper. The self-attention mechanism is used to automatically identify the importance of input features in various instances and associate the relationships between input features. The accuracy of the surgical phase classification of the SA-RLNet approach is 90.6%. The present study demonstrates that the SA-RLNet approach shows strong generalization capabilities on the dataset. SA-RLNet has proved to be advantageous in capturing subtle variations between surgical phases. The application of surgical workflow recognition has promising feasibility in liver rupture repair surgery.

Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study

Recent advancements in artificial intelligence have witnessed human-level performance; however, AI-enabled cognitive assistance for therapeutic procedures has not been fully explored nor pre-clinically validated. Here we propose AI-Endo, an intelligent surgical workflow recognition suit, for endoscopic submucosal dissection (ESD). Our AI-Endo is trained on high-quality ESD cases from an expert endoscopist, covering a decade time expansion and consisting of 201,026 labeled frames. The learned model demonstrates outstanding performance on validation data, including cases from relatively junior endoscopists with various skill levels, procedures conducted with different endoscopy systems and therapeutic skills, and cohorts from international multi-centers. Furthermore, we integrate our AI-Endo with the Olympus endoscopic system and validate the AI-enabled cognitive assistance system with animal studies in live ESD training sessions. Dedicated data analysis from surgical phase recognition results is summarized in an automatically generated report for skill assessment.

A novel high accuracy model for automatic surgical workflow recognition using artificial intelligence in laparoscopic totally extraperitoneal inguinal hernia repair (TEP)

IntroductionArtificial intelligence and computer vision are revolutionizing the way we perceive video analysis in minimally invasive surgery. This emerging technology has increasingly been leveraged successfully for video segmentation, documentation, education, and formative assessment. New, sophisticated platforms allow pre-determined segments chosen by surgeons to be automatically presented without the need to review entire videos. This study aimed to validate and demonstrate the accuracy of the first reported AI-based computer vision algorithm that automatically recognizes surgical steps in videos of totally extraperitoneal (TEP) inguinal hernia repair.MethodsVideos of TEP procedures were manually labeled by a team of annotators trained to identify and label surgical workflow according to six major steps. For bilateral hernias, an additional change of focus step was also included. The videos were then used to train a computer vision AI algorithm. Performance accuracy was assessed in comparison to the manual annotations.ResultsA total of 619 full-length TEP videos were analyzed: 371 were used to train the model, 93 for internal validation, and the remaining 155 as a test set to evaluate algorithm accuracy. The overall accuracy for the complete procedure was 88.8%. Per-step accuracy reached the highest value for the hernia sac reduction step (94.3%) and the lowest for the preperitoneal dissection step (72.2%).ConclusionsThese results indicate that the novel AI model was able to provide fully automated video analysis with a high accuracy level. High-accuracy models leveraging AI to enable automation of surgical video analysis allow us to identify and monitor surgical performance, providing mathematical metrics that can be stored, evaluated, and compared. As such, the proposed model is capable of enabling data-driven insights to improve surgical quality and demonstrate best practices in TEP procedures.Graphical abstract

Multilevel effective surgical workflow recognition in robotic left lateral sectionectomy with deep learning: experimental research.

Automated surgical workflow recognition is the foundation for computational models of medical knowledge to interpret surgical procedures. The fine-grained segmentation of the surgical process and the improvement of the accuracy of surgical workflow recognition facilitate the realization of autonomous robotic surgery. This study aimed to construct a multigranularity temporal annotation dataset of the standardized robotic left lateral sectionectomy (RLLS) and develop a deep learning-based automated model for multilevel overall and effective surgical workflow recognition. From December 2016 to May 2019, 45 cases of RLLS videos were enrolled in our dataset. All frames of RLLS videos in this study are labeled with temporal annotations. The authors defined those activities that truly contribute to the surgery as effective frames, while other activities are labeled as under-effective frames. Effective frames of all RLLS videos are annotated with three hierarchical levels of 4 steps, 12 tasks, and 26 activities. A hybrid deep learning model were used for surgical workflow recognition of steps, tasks, activities, and under-effective frames. Moreover, the authors also carried out multilevel effective surgical workflow recognition after removing under-effective frames. The dataset comprises 4383516 annotated RLLS video frames with multilevel annotation, of which 2418468 frames are effective. The overall accuracies of automated recognition for Steps, Tasks, Activities, and under-effective frames are 0.82, 0.80, 0.79, and 0.85, respectively, with corresponding precision values of 0.81, 0.76, 0.60, and 0.85. In multilevel effective surgical workflow recognition, the overall accuracies were increased to 0.96, 0.88, and 0.82 for Steps, Tasks, and Activities, respectively, while the precision values were increased to 0.95, 0.80, and 0.68. In this study, the authors created a dataset of 45 RLLS cases with multilevel annotations and developed a hybrid deep learning model for surgical workflow recognition. The authors demonstrated a fairly higher accuracy in multilevel effective surgical workflow recognition when under-effective frames were removed. Our research could be helpful in the development of autonomous robotic surgery.

DisguisOR: holistic face anonymization for the operating room

PurposeRecent advances in Surgical Data Science (SDS) have contributed to an increase in video recordings from hospital environments. While methods such as surgical workflow recognition show potential in increasing the quality of patient care, the quantity of video data has surpassed the scale at which images can be manually anonymized. Existing automated 2D anonymization methods under-perform in Operating Rooms (OR), due to occlusions and obstructions. We propose to anonymize multi-view OR recordings using 3D data from multiple camera streams.MethodsRGB and depth images from multiple cameras are fused into a 3D point cloud representation of the scene. We then detect each individual’s face in 3D by regressing a parametric human mesh model onto detected 3D human keypoints and aligning the face mesh with the fused 3D point cloud. The mesh model is rendered into every acquired camera view, replacing each individual’s face.ResultsOur method shows promise in locating faces at a higher rate than existing approaches. DisguisOR produces geometrically consistent anonymizations for each camera view, enabling more realistic anonymization that is less detrimental to downstream tasks.ConclusionFrequent obstructions and crowding in operating rooms leaves significant room for improvement for off-the-shelf anonymization methods. DisguisOR addresses privacy on a scene level and has the potential to facilitate further research in SDS.

Surgical phase recognition in laparoscopic videos using gated capsule autoencoder model

ABSTRACT Surgical workflow analysis has gained greater attention in enhancing patient safety and obtaining optimal surgery results. However, automated recognition and classification of surgical phases are highly challenging due to several problems like higher computational complexities, increased time consumption, reduced learning ability, etc. Thus, the proposed study intends to develop an effective surgical workflow recognition and classification mechanism. Initially, the video annotation software is used convert the laparoscopic input videos into several frames for developing a proper recognition system. Then, an Exaggerated Series Wiener Bilateral Filtering (E-SWBF) approach is used in the pre-processing stage for preserving the edges removing the noises. After pre-processing, the spatial and temporal features are extracted through the attention-based convolutional Inception Bi-directional Long Short Term Memory (Attn_conv Inc_2DLSTM) model. Next, the feature dimensionality issue is reduced by selecting significant features through an Enhanced binary Aquila optimization (EBiAO) algorithm. Finally, the surgical phases are recognized and classified by the proposed Gated capsule tweaked autoencoder model (Gcaps_TAE). The obtained values of accuracy 98.95%, precision 96.55%, sensitivity 96.90%, specificity 99.23%, F1-score 96.72%, MSE 0.30%, and MAE 0.101% shows that the proposed model is superior to other existing methods.

PEg TRAnsfer Workflow recognition challenge report: Do multimodal data improve recognition?

Background and objective: In order to be context-aware, computer-assisted surgical systems require accurate, real-time automatic surgical workflow recognition. In the past several years, surgical video has been the most commonly-used modality for surgical workflow recognition. But with the democratization of robot-assisted surgery, new modalities, such as kinematics, are now accessible. Some previous methods use these new modalities as input for their models, but their added value has rarely been studied. This paper presents the design and results of the “PEg TRAnsfer Workflow recognition” (PETRAW) challenge with the objective of developing surgical workflow recognition methods based on one or more modalities and studying their added value.Methods: The PETRAW challenge included a data set of 150 peg transfer sequences performed on a virtual simulator. This data set included videos, kinematic data, semantic segmentation data, and annotations, which described the workflow at three levels of granularity: phase, step, and activity. Five tasks were proposed to the participants: three were related to the recognition at all granularities simultaneously using a single modality, and two addressed the recognition using multiple modalities. The mean application-dependent balanced accuracy (AD-Accuracy) was used as an evaluation metric to take into account class balance and is more clinically relevant than a frame-by-frame score.Results: Seven teams participated in at least one task with four participating in every task. The best results were obtained by combining video and kinematic data (AD-Accuracy of between 93% and 90% for the four teams that participated in all tasks).Conclusion: The improvement of surgical workflow recognition methods using multiple modalities compared with unimodal methods was significant for all teams. However, the longer execution time required for video/kinematic-based methods(compared to only kinematic-based methods) must be considered. Indeed, one must ask if it is wise to increase computing time by 2000 to 20,000% only to increase accuracy by 3%. The PETRAW data set is publicly available at www.synapse.org/PETRAW to encourage further research in surgical workflow recognition.

Surgical workflow recognition with temporal convolution and transformer for action segmentation.

Automatic surgical workflow recognition enabled by computer vision algorithms plays a key role in enhancing the learning experience of surgeons. It also supports building context-aware systems that allow better surgical planning and decision making which may in turn improve outcomes. Utilizing temporal information is crucial for recognizing context; hence, various recent approaches use recurrent neural networks or transformers to recognize actions. We design and implement a two-stage method for surgical workflow recognition. We utilize R(2+1)D for video clip modeling in the first stage. We propose Action Segmentation Temporal Convolutional Transformer (ASTCFormer) network for full video modeling in the second stage. ASTCFormer utilizes action segmentation transformers (ASFormers) and temporal convolutional networks (TCNs) to build a temporally aware surgical workflow recognition system. We compare the proposed ASTCFormer with recurrent neural networks, multi-stage TCN, and ASFormer approaches. The comparison is done on a dataset comprised of 207 robotic and laparoscopic cholecystectomy surgical videos annotated for 7 surgical phases. The proposed method outperforms the compared methods achieving a [Formula: see text] relative improvement in the average segmental F1-score over the state-of-the-art ASFormer method. Moreover, our proposed method achieves state-of-the-art results on the publicly available Cholec80 dataset. The improvement in the results when using the proposed method suggests that temporal context could be better captured when adding information from TCN to the ASFormer paradigm. This addition leads to better surgical workflow recognition.

Ontology-based surgical workflow recognition and prediction

BackgroundSurgical context-aware systems can adapt to the current situation in the operating room and thus provide computer-aided assistance functionalities and intraoperative decision-support. To interact with the surgical team perceptively and assist the surgical process, the system needs to monitor the intraoperative activities, understand the current situation in the operating room at any time, and anticipate the following possible situations. MethodsA structured representation of surgical process knowledge is a prerequisite for any applications in the intelligent operating room. For this purpose, a surgical process ontology, which is formally based on standard medical terminology (SNOMED CT) and an upper-level ontology (GFO), was developed and instantiated for a neurosurgical use case. A new ontology-based surgical workflow recognition and a novel prediction method are presented utilizing ontological reasoning, abstraction, and explication. This way, a surgical situation representation with combined phase, high-level task, and low-level task recognition and prediction was realized based on the currently used instrument as the only input information. ResultsThe ontology-based approach performed efficiently, and decent accuracy was achieved for situation recognition and prediction. Especially during situation recognition, the missing sensor information were reasoned based on the situation representation provided by the process ontology, which resulted in improved recognition results compared to the state-of-the-art. ConclusionsIn this work, a reference ontology was developed, which provides workflow support and a knowledge base for further applications in the intelligent operating room, for instance, context-aware medical device orchestration, (semi-) automatic documentation, and surgical simulation, education, and training.

Temporal-based Swin Transformer network for workflow recognition of surgical video.

Surgical workflow recognition has emerged as an important part of computer-assisted intervention systems for the modern operating room, which also is a very challenging problem. Although the CNN-based approach achieves excellent performance, it does not learn global and long-range semantic information interactions well due to the inductive bias inherent in convolution. In this paper, we propose a temporal-based Swin Transformer network (TSTNet) for the surgical video workflow recognition task. TSTNet contains two main parts: the Swin Transformer and the LSTM. The Swin Transformer incorporates the attention mechanism to encode remote dependencies and learn highly expressive representations. The LSTM is capable of learning long-range dependencies and is used to extract temporal information. The TSTNet organically combines the two components to extract spatiotemporal features that contain more contextual information. In particular, based on a full understanding of the natural features of the surgical video, we propose a priori revision algorithm (PRA) using a priori information about the sequence of the surgical phase. This strategy optimizes the output of TSTNet and further improves the recognition performance. We conduct extensive experiments using the Cholec80 dataset to validate the effectiveness of the TSTNet-PRA method. Our method achieves excellent performance on the Cholec80 dataset, which accuracy is up to 92.8% and greatly exceeds the state-of-the-art methods. By modelling remote temporal information and multi-scale visual information, we propose the TSTNet-PRA method. It was evaluated on a large public dataset, showing a high recognition capability superior to other spatiotemporal networks.

Convolutional-de-convolutional neural networks for recognition of surgical workflow.

Computer-assisted surgery (CAS) has occupied an important position in modern surgery, further stimulating the progress of methodology and technology. In recent years, a large number of computer vision-based methods have been widely used in surgical workflow recognition tasks. For training the models, a lot of annotated data are necessary. However, the annotation of surgical data requires expert knowledge and thus becomes difficult and time-consuming. In this paper, we focus on the problem of data deficiency and propose a knowledge transfer learning method based on artificial neural network to compensate a small amount of labeled training data. To solve this problem, we propose an unsupervised method for pre-training a Convolutional-De-Convolutional (CDC) neural network for sequencing surgical workflow frames, which performs neural convolution in space (for semantic abstraction) and neural de-convolution in time (for frame level resolution) simultaneously. Specifically, through neural convolution transfer learning, we only fine-tuned the CDC neural network to classify the surgical phase. We performed some experiments for validating the model, and it showed that the proposed model can effectively extract the surgical feature and determine the surgical phase. The accuracy (Acc), recall, precision (Pres) of our model reached 91.4, 78.9, and 82.5%, respectively.

The impact of ensemble learning on surgical tools classification during laparoscopic cholecystectomy

Laparoscopic surgery also know as minimally invasive surgery (MIS), is a type of surgical procedure that allows a surgeon to examine the organs inside of the abdomen without having to make large incisions in the skin. It unifies the competence and skills of highly trained surgeons with the power and precision of machines. Furthermore, surgical instruments are inserted through the abdomen with the help of a laparoscope, which is a tube with a high-intensity light and a high-resolution camera at the end. In addition, recorded videos from this type of surgery have become a steadily more important information source. However, MIS videos are often very long, thereby, navigating through these videos is time and effort consuming. The automatic identification of tool presence in laparoscopic videos leads to detecting what tools are used at each time in surgery and helps in the automatic recognition of surgical workflow. The aim of this paper is to predict surgical tools from laparoscopic videos using three states of the arts CNNs, namely: VGG19, Inception v-4, and NASNet-A. In addition, an ensemble learning method is proposed, combining the three CNNs, to solve the tool presence detection problem as a multi-label classification problem. The proposed methods are evaluated on a dataset of 80 cholecystectomy videos (Cholec80 dataset). The results present an improvement of approximately 6.19% and a mean average precision of 97.84% when the ensemble learning method is applied.

Reducing prediction volatility in the surgical workflow recognition of endoscopic pituitary surgery

Purpose:Workflow recognition can aid surgeons before an operation when used as a training tool, during an operation by increasing operating room efficiency, and after an operation in the completion of operation notes. Although several methods have been applied to this task, they have been tested on few surgical datasets. Therefore, their generalisability is not well tested, particularly for surgical approaches utilising smaller working spaces which are susceptible to occlusion and necessitate frequent withdrawal of the endoscope. This leads to rapidly changing predictions, which reduces the clinical confidence of the methods, and hence limits their suitability for clinical translation.Methods:Firstly, the optimal neural network is found using established methods, using endoscopic pituitary surgery as an exemplar. Then, prediction volatility is formally defined as a new evaluation metric as a proxy for uncertainty, and two temporal smoothing functions are created. The first (modal, M_n) mode-averages over the previous n predictions, and the second (threshold, T_n) ensures a class is only changed after being continuously predicted for n predictions. Both functions are independently applied to the predictions of the optimal network.Results:The methods are evaluated on a 50-video dataset using fivefold cross-validation, and the optimised evaluation metric is weighted-F_1 score. The optimal model is ResNet-50+LSTM achieving 0.84 in 3-phase classification and 0.74 in 7-step classification. Applying threshold smoothing further improves these results, achieving 0.86 in 3-phase classification, and 0.75 in 7-step classification, while also drastically reducing the prediction volatility.Conclusion:The results confirm the established methods generalise to endoscopic pituitary surgery, and show simple temporal smoothing not only reduces prediction volatility, but actively improves performance.

Towards accurate surgical workflow recognition with convolutional networks and transformers

ABSTRACT Recognising workflow phases from endoscopic surgical videos is crucial to deriving indicators that convey the quality, efficiency, outcome of the surgery, and offering insights into surgical team skills. Additionally, workflow information is used to organise large surgical video libraries for training purposes. In this paper, we explore different deep networks that capture spatial and temporal information from surgical videos for surgical workflow recognition. The approach is based on a combination of two networks: The first network is used for feature extraction from video snippets. The second network is performing action segmentation to identify the different parts of the surgical workflow by analysing the extracted features. This work focuses on proposing, comparing, and analysing different design choices. This includes fully convolutional, fully transformer, and hybrid models, which consist of transformers used in conjunction with convolutions. We evaluate the methods against a large dataset of endoscopic surgical videos acquired during Gastric Bypass surgery. Both our proposed fully transformer method and fully convolutional approach achieve state-of-the-art results. By integrating transformers and convolutions, our hybrid model achieves 93% frame-level accuracy and 85 segmental edit distance score. This demonstrates the potential of hybrid models that employ both transformers and convolutions for accurate surgical workflow recognition.

MIcro-surgical anastomose workflow recognition challenge report

Background and Objective: Automatic surgical workflow recognition is an essential step in developing context-aware computer-assisted surgical systems. Video recordings of surgeries are becoming widely accessible, as the operational field view is captured during laparoscopic surgeries. Head and ceiling mounted cameras are also increasingly being used to record videos in open surgeries. This makes videos a common choice in surgical workflow recognition. Additional modalities, such as kinematic data captured during robot-assisted surgeries, could also improve workflow recognition. This paper presents the design and results of the MIcro-Surgical Anastomose Workflow recognition on training sessions (MISAW) challenge whose objective was to develop workflow recognition models based on kinematic data and/or videos.Methods: The MISAW challenge provided a data set of 27 sequences of micro-surgical anastomosis on artificial blood vessels. This data set was composed of videos, kinematics, and workflow annotations. The latter described the sequences at three different granularity levels: phase, step, and activity. Four tasks were proposed to the participants: three of them were related to the recognition of surgical workflow at three different granularity levels, while the last one addressed the recognition of all granularity levels in the same model. We used the average application-dependent balanced accuracy (AD-Accuracy) as the evaluation metric. This takes unbalanced classes into account and it is more clinically relevant than a frame-by-frame score.Results: Six teams participated in at least one task. All models employed deep learning models, such as convolutional neural networks (CNN), recurrent neural networks (RNN), or a combination of both. The best models achieved accuracy above 95%, 80%, 60%, and 75% respectively for recognition of phases, steps, activities, and multi-granularity. The RNN-based models outperformed the CNN-based ones as well as the dedicated modality models compared to the multi-granularity except for activity recognition.Conclusion: For high levels of granularity, the best models had a recognition rate that may be sufficient for applications such as prediction of remaining surgical time. However, for activities, the recognition rate was still low for applications that can be employed clinically. The MISAW data set is publicly available at http://www.synapse.org/MISAW to encourage further research in surgical workflow recognition.

Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy

PurposeSurgical workflow recognition is a crucial and challenging problem when building a computer-assisted surgery system. Current techniques focus on utilizing a convolutional neural network and a recurrent neural network (CNN–RNN) to solve the surgical workflow recognition problem. In this paper, we attempt to use a deep 3DCNN to solve this problem.MethodsIn order to tackle the surgical workflow recognition problem and the imbalanced data problem, we implement a 3DCNN workflow referred to as I3D-FL-PKF. We utilize focal loss (FL) to train a 3DCNN architecture known as Inflated 3D ConvNet (I3D) for surgical workflow recognition. We use prior knowledge filtering (PKF) to filter the recognition results.ResultsWe evaluate our proposed workflow on a large sleeve gastrectomy surgical video dataset. We show that focal loss can help to address the imbalanced data problem. We show that our PKF can be used to generate smoothed prediction results and improve the overall accuracy. We show that the proposed workflow achieves 84.16% frame-level accuracy and reaches a weighted Jaccard score of 0.7327 which outperforms traditional CNN–RNN design.ConclusionThe proposed workflow can obtain consistent and smooth predictions not only within the surgical phases but also for phase transitions. By utilizing focal loss and prior knowledge filtering, our implementation of deep 3DCNN has great potential to solve surgical workflow recognition problems for clinical practice.

Semi-supervised learning with progressive unlabeled data excavation for label-efficient surgical workflow recognition

Surgical workflow recognition is a fundamental task in computer-assisted surgery and a key component of various applications in operating rooms. Existing deep learning models have achieved promising results for surgical workflow recognition, heavily relying on a large amount of annotated videos. However, obtaining annotation is time-consuming and requires the domain knowledge of surgeons. In this paper, we propose a novel two-stage Semi-Supervised Learning method for label-efficient Surgical workflow recognition, named as SurgSSL. Our proposed SurgSSL progressively leverages the inherent knowledge held in the unlabeled data to a larger extent: from implicit unlabeled data excavation via motion knowledge excavation, to explicit unlabeled data excavation via pre-knowledge pseudo labeling. Specifically, we first propose a novel intra-sequence Visual and Temporal Dynamic Consistency (VTDC) scheme for implicit excavation. It enforces prediction consistency of the same data under perturbations in both spatial and temporal spaces, encouraging model to capture rich motion knowledge. We further perform explicit excavation by optimizing the model towards our pre-knowledge pseudo label. It is naturally generated by the VTDC regularized model with prior knowledge of unlabeled data encoded, and demonstrates superior reliability for model supervision compared with the label generated by existing methods. We extensively evaluate our method on two public surgical datasets of Cholec80 and M2CAI challenge dataset. Our method surpasses the state-of-the-art semi-supervised methods by a large margin, e.g., improving 10.5% Accuracy under the severest annotation regime of M2CAI dataset. Using only 50% labeled videos on Cholec80, our approach achieves competitive performance compared with full-data training method.

Against spatial-temporal discrepancy: contrastive learning-based network for surgical workflow recognition.

Automatic workflow recognition from surgical videos is fundamental and significant for developing context-aware systems in modern operating rooms. Although many approaches have been proposed to tackle challenges in this complex task, there are still many problems such as the fine-grained characteristics and spatial-temporal discrepancies in surgical videos. We propose a contrastive learning-based convolutional recurrent network with multi-level prediction to tackle these problems. Specifically, split-attention blocks are employed to extract spatial features. Through a mapping function in the step-phase branch, the current workflow can be predicted on two mutual-boosting levels. Furthermore, a contrastive branch is introduced to learn the spatial-temporal features that eliminate irrelevant changes in the environment. We evaluate our method on the Cataract-101 dataset. The results show that our method achieves an accuracy of 96.37% with only surgical step labels, which outperforms other state-of-the-art approaches. The proposed convolutional recurrent network based on step-phase prediction and contrastive learning can leverage fine-grained characteristics and alleviate spatial-temporal discrepancies to improve the performance of surgical workflow recognition.