Search

Accurate segmentation of tools in robot-assisted surgery is critical for machine perception, as it facilitates numerous downstream tasks including augmented reality feedback. While current feed-forward neural network-based methods exhibit excellent segmentation performance under ideal conditions, these models have proven susceptible to even minor corruptions, significantly impairing the model's performance. This vulnerability is especially problematic in surgical settings where predictions might be used to inform high-stakes decisions. To better understand model behavior under non-adversarial corruptions, prior work has explored introducing artificial corruptions, like Gaussian noise or contrast perturbation to test set images, to assess model robustness. However, these corruptions are either not photo-realistic or model/task agnostic. Thus, these investigations provide limited insights into model deterioration under realistic surgical corruptions. To address this limitation, we introduce the SegSTRONG-C challenge that aims to promote the development of algorithms robust to unforeseen but plausible image corruptions of surgery, like smoke, bleeding, and low brightness. We collect and release corruption-free mock endoscopic video sequences for the challenge participants to train their algorithms and benchmark them on video sequences with photo-realistic non-adversarial corruptions for a binary robot tool segmentation task. This new benchmark will allow us to carefully study neural network robustness to non-adversarial corruptions of surgery, thus constituting an important first step towards more robust models for surgical computer vision. In this paper, we describe the data collection and annotation protocol, baseline evaluations of established segmentation models, and data augmentation-based techniques to enhance model robustness.

Surgical robot task automation has been a promising research topic for improving surgical efficiency and quality. Learning-based methods have been recognized as an interesting paradigm and been increasingly investigated. However, existing approaches encounter difficulties in long-horizon goal-conditioned tasks due to the intricate compositional structure, which requires decision-making for a sequence of sub-steps and understanding of inherent dynamics of goal-reaching tasks. In this paper, we propose a new learning-based framework by leveraging the strong reasoning capability of the GPT-based architecture to automate surgical robotic tasks. The key to our approach is developing a goal-conditioned decision transformer to achieve sequential representations with goal-aware future indicators in order to enhance temporal reasoning. Moreover, considering to exploit a general understanding of dynamics inherent in manipulations, thus making the model's reasoning ability to be task-agnostic, we also design a cross-task pretraining paradigm that uses multiple training objectives associated with data from diverse tasks. We have conducted extensive experiments on 10 tasks using the surgical robot learning simulator SurRoL~\cite{long2023human}. The results show that our new approach achieves promising performance and task versatility compared to existing methods. The learned trajectories can be deployed on the da Vinci Research Kit (dVRK) for validating its practicality in real surgical robot settings. Our project website is at: https://med-air.github.io/SurRoL.

Surgical scene simulation plays a crucial role in surgical education and simulator-based robot learning. Traditional approaches for creating these environments with surgical scene involve a labor-intensive process where designers hand-craft tissues models with textures and geometries for soft body simulations. This manual approach is not only time-consuming but also limited in the scalability and realism. In contrast, data-driven simulation offers a compelling alternative. It has the potential to automatically reconstruct 3D surgical scenes from real-world surgical video data, followed by the application of soft body physics. This area, however, is relatively uncharted. In our research, we introduce 3D Gaussian as a learnable representation for surgical scene, which is learned from stereo endoscopic video. To prevent over-fitting and ensure the geometrical correctness of these scenes, we incorporate depth supervision and anisotropy regularization into the Gaussian learning process. Furthermore, we apply the Material Point Method, which is integrated with physical properties, to the 3D Gaussians to achieve realistic scene deformations. Our method was evaluated on our collected in-house and public surgical videos datasets. Results show that it can reconstruct and simulate surgical scenes from endoscopic videos efficiently-taking only a few minutes to reconstruct the surgical scene-and produce both visually and physically plausible deformations at a speed approaching real-time. The results demonstrate great potential of our proposed method to enhance the efficiency and variety of simulations available for surgical education and robot learning.

The healthcare industry has a growing need for realistic modeling and efficient simulation of surgical scenes. With effective models of deformable surgical scenes, clinicians are able to conduct surgical planning and surgery training on scenarios close to real-world cases. However, a significant challenge in achieving such a goal is the scarcity of high-quality soft tissue models with accurate shapes and textures. To address this gap, we present a data-driven framework that leverages emerging neural radiance field technology to enable high-quality surgical reconstruction and explore its application for surgical simulations. We first focus on developing a fast NeRF-based surgical scene 3D reconstruction approach that achieves state-of-the-art performance. This method can significantly outperform traditional 3D reconstruction methods, which have failed to capture large deformations and produce fine-grained shapes and textures. We then propose an automated creation pipeline of interactive surgical simulation environments through a closed mesh extraction algorithm. Our experiments have validated the superior performance and efficiency of our proposed approach in surgical scene 3D reconstruction. We further utilize our reconstructed soft tissues to conduct FEM and MPM simulations, showcasing the practical application of our method in data-driven surgical simulations., Comment: 14 pages, 4 figures. Accepted by International Journal of Computer Assisted Radiology and Surgery

Surgical robot simulation platform plays a crucial role in enhancing training efficiency and advancing research on robot learning. Much effort have been made by scholars on developing open-sourced surgical robot simulators to facilitate research. We also developed SurRoL formerly, an open-source, da Vinci Research Kit (dVRK) compatible and interactive embodied environment for robot learning. Despite its advancements, the simulation of soft bodies still remained a major challenge within the open-source platforms available for surgical robotics. To this end, we develop an interactive physically based soft body simulation framework and integrate it to SurRoL. Specifically, we utilized a high-performance adaptation of the Material Point Method (MPM) along with the Neo-Hookean model to represent the deformable tissue. Lagrangian particles are used to track the motion and deformation of the soft body throughout the simulation and Eulerian grids are leveraged to discretize space and facilitate the calculation of forces, velocities, and other physical quantities. We also employed an efficient collision detection and handling strategy to simulate the interaction between soft body and rigid tool of the surgical robot. By employing the Taichi programming language, our implementation harnesses parallel computing to boost simulation speed. Experimental results show that our platform is able to simulate soft bodies efficiently with strong physical interpretability and plausible visual effects. These new features in SurRoL enable the efficient simulation of surgical tasks involving soft tissue manipulation and pave the path for further investigation of surgical robot learning. The code will be released in a new branch of SurRoL github repo., Comment: 8 pages

Accurate segmentation of surgical instrument tip is an important task for enabling downstream applications in robotic surgery, such as surgical skill assessment, tool-tissue interaction and deformation modeling, as well as surgical autonomy. However, this task is very challenging due to the small sizes of surgical instrument tips, and significant variance of surgical scenes across different procedures. Although much effort has been made on visual-based methods, existing segmentation models still suffer from low robustness thus not usable in practice. Fortunately, kinematics data from the robotic system can provide reliable prior for instrument location, which is consistent regardless of different surgery types. To make use of such multi-modal information, we propose a novel visual-kinematics graph learning framework to accurately segment the instrument tip given various surgical procedures. Specifically, a graph learning framework is proposed to encode relational features of instrument parts from both image and kinematics. Next, a cross-modal contrastive loss is designed to incorporate robust geometric prior from kinematics to image for tip segmentation. We have conducted experiments on a private paired visual-kinematics dataset including multiple procedures, i.e., prostatectomy, total mesorectal excision, fundoplication and distal gastrectomy on cadaver, and distal gastrectomy on porcine. The leave-one-procedure-out cross validation demonstrated that our proposed multi-modal segmentation method significantly outperformed current image-based state-of-the-art approaches, exceeding averagely 11.2% on Dice., Comment: Accepted to IROS 2023

Reinforcement learning is still struggling with solving long-horizon surgical robot tasks which involve multiple steps over an extended duration of time due to the policy exploration challenge. Recent methods try to tackle this problem by skill chaining, in which the long-horizon task is decomposed into multiple subtasks for easing the exploration burden and subtask policies are temporally connected to complete the whole long-horizon task. However, smoothly connecting all subtask policies is difficult for surgical robot scenarios. Not all states are equally suitable for connecting two adjacent subtasks. An undesired terminate state of the previous subtask would make the current subtask policy unstable and result in a failed execution. In this work, we introduce value-informed skill chaining (ViSkill), a novel reinforcement learning framework for long-horizon surgical robot tasks. The core idea is to distinguish which terminal state is suitable for starting all the following subtask policies. To achieve this target, we introduce a state value function that estimates the expected success probability of the entire task given a state. Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task. We demonstrate the effectiveness of our method on three complex surgical robot tasks from SurRoL, a comprehensive surgical simulation platform, achieving high task success rates and execution efficiency. Code is available at $\href{https://github.com/med-air/ViSkill}{\text{https://github.com/med-air/ViSkill}}$., Comment: Accepted to IROS 2023

Surgical robot automation has attracted increasing research interest over the past decade, expecting its potential to benefit surgeons, nurses and patients. Recently, the learning paradigm of embodied intelligence has demonstrated promising ability to learn good control policies for various complex tasks, where embodied AI simulators play an essential role to facilitate relevant research. However, existing open-sourced simulators for surgical robot are still not sufficiently supporting human interactions through physical input devices, which further limits effective investigations on how the human demonstrations would affect policy learning. In this work, we study human-in-the-loop embodied intelligence with a new interactive simulation platform for surgical robot learning. Specifically, we establish our platform based on our previously released SurRoL simulator with several new features co-developed to allow high-quality human interaction via an input device. We showcase the improvement of our simulation environment with the designed new features, and validate effectiveness of incorporating human factors in embodied intelligence through the use of human demonstrations and reinforcement learning as a representative example. Promising results are obtained in terms of learning efficiency. Lastly, five new surgical robot training tasks are developed and released, with which we hope to pave the way for future research on surgical embodied intelligence. Our learning platform is publicly released and will be continuously updated in the website: https://med-air.github.io/SurRoL.

Estimating precise metric depth and scene reconstruction from monocular endoscopy is a fundamental task for surgical navigation in robotic surgery. However, traditional stereo matching adopts binocular images to perceive the depth information, which is difficult to transfer to the soft robotics-based surgical systems due to the use of monocular endoscopy. In this paper, we present a novel framework that combines robot kinematics and monocular endoscope images with deep unsupervised learning into a single network for metric depth estimation and then achieve 3D reconstruction of complex anatomy. Specifically, we first obtain the relative depth maps of surgical scenes by leveraging a brightness-aware monocular depth estimation method. Then, the corresponding endoscope poses are computed based on non-linear optimization of geometric and photometric reprojection residuals. Afterwards, we develop a Depth-driven Sliding Optimization (DDSO) algorithm to extract the scaling coefficient from kinematics and calculated poses offline. By coupling the metric scale and relative depth data, we form a robust ensemble that represents the metric and consistent depth. Next, we treat the ensemble as supervisory labels to train a metric depth estimation network for surgeries (i.e., MetricDepthS-Net) that distills the embeddings from the robot kinematics, endoscopic videos, and poses. With accurate metric depth estimation, we utilize a dense visual reconstruction method to recover the 3D structure of the whole surgical site. We have extensively evaluated the proposed framework on public SCARED and achieved comparable performance with stereo-based depth estimation methods. Our results demonstrate the feasibility of the proposed approach to recover the metric depth and 3D structure with monocular inputs.

Computer-assisted minimally invasive surgery has great potential in benefiting modern operating theatres. The video data streamed from the endoscope provides rich information to support context-awareness for next-generation intelligent surgical systems. To achieve accurate perception and automatic manipulation during the procedure, learning based technique is a promising way, which enables advanced image analysis and scene understanding in recent years. However, learning such models highly relies on large-scale, high-quality, and multi-task labelled data. This is currently a bottleneck for the topic, as available public dataset is still extremely limited in the field of CAI. In this paper, we present and release the first integrated dataset (named AutoLaparo) with multiple image-based perception tasks to facilitate learning-based automation in hysterectomy surgery. Our AutoLaparo dataset is developed based on full-length videos of entire hysterectomy procedures. Specifically, three different yet highly correlated tasks are formulated in the dataset, including surgical workflow recognition, laparoscope motion prediction, and instrument and key anatomy segmentation. In addition, we provide experimental results with state-of-the-art models as reference benchmarks for further model developments and evaluations on this dataset. The dataset is available at https://autolaparo.github.io., Comment: Accepted at MICCAI 2022

Reconstruction of the soft tissues in robotic surgery from endoscopic stereo videos is important for many applications such as intra-operative navigation and image-guided robotic surgery automation. Previous works on this task mainly rely on SLAM-based approaches, which struggle to handle complex surgical scenes. Inspired by recent progress in neural rendering, we present a novel framework for deformable tissue reconstruction from binocular captures in robotic surgery under the single-viewpoint setting. Our framework adopts dynamic neural radiance fields to represent deformable surgical scenes in MLPs and optimize shapes and deformations in a learning-based manner. In addition to non-rigid deformations, tool occlusion and poor 3D clues from a single viewpoint are also particular challenges in soft tissue reconstruction. To overcome these difficulties, we present a series of strategies of tool mask-guided ray casting, stereo depth-cueing ray marching and stereo depth-supervised optimization. With experiments on DaVinci robotic surgery videos, our method significantly outperforms the current state-of-the-art reconstruction method for handling various complex non-rigid deformations. To our best knowledge, this is the first work leveraging neural rendering for surgical scene 3D reconstruction with remarkable potential demonstrated. Code is available at: https://github.com/med-air/EndoNeRF., Comment: 11 pages, 4 figures, conference

With the growing popularity of robotic surgery, education becomes increasingly important and urgently needed for the sake of patient safety. However, experienced surgeons have limited accessibility due to their busy clinical schedule or working in a distant city, thus can hardly provide sufficient education resources for novices. Remote mentoring, as an effective way, can help solve this problem, but traditional methods are limited to plain text, audio, or 2D video, which are not intuitive nor vivid. Augmented reality (AR), a thriving technique being widely used for various education scenarios, is promising to offer new possibilities of visual experience and interactive teaching. In this paper, we propose a novel AR-based robotic surgery remote mentoring system with efficient 3D scene visualization and natural 3D hand interaction. Using a head-mounted display (i.e., HoloLens), the mentor can remotely monitor the procedure streamed from the trainee's operation side. The mentor can also provide feedback directly with hand gestures, which is in-turn transmitted to the trainee and viewed in surgical console as guidance. We comprehensively validate the system on both real surgery stereo videos and ex-vivo scenarios of common robotic training tasks (i.e., peg-transfer and suturing). Promising results are demonstrated regarding the fidelity of streamed scene visualization, the accuracy of feedback with hand interaction, and the low-latency of each component in the entire remote mentoring system. This work showcases the feasibility of leveraging AR technology for reliable, flexible and low-cost solutions to robotic surgical education, and holds great potential for clinical applications.

This paper presents the design and results of the "PEg TRAnsfert Workflow recognition" (PETRAW) challenge whose objective was to develop surgical workflow recognition methods based on one or several modalities, among video, kinematic, and segmentation data, in order to study their added value. The PETRAW challenge provided a data set of 150 peg transfer sequences performed on a virtual simulator. This data set was composed of videos, kinematics, semantic segmentation, and workflow annotations which described the sequences at three different granularity levels: phase, step, and activity. Five tasks were proposed to the participants: three of them were related to the recognition of all granularities with one of the available modalities, while the others addressed the recognition with a combination of modalities. Average application-dependent balanced accuracy (AD-Accuracy) was used as evaluation metric to take unbalanced classes into account and because it is more clinically relevant than a frame-by-frame score. Seven teams participated in at least one task and four of them in all tasks. Best results are obtained with the use of the video and the kinematics data with an AD-Accuracy between 93% and 90% for the four teams who participated in all tasks. The improvement between video/kinematic-based methods and the uni-modality ones was significant for all of the teams. However, the difference in testing execution time between the video/kinematic-based and the kinematic-based methods has to be taken into consideration. Is it relevant to spend 20 to 200 times more computing time for less than 3% of improvement? The PETRAW data set is publicly available at www.synapse.org/PETRAW to encourage further research in surgical workflow recognition., Comment: Challenge report doi.org/10.1016/j.cmpb.2023.107561

Robot-assisted surgery has become progressively more and more popular due to its clinical advantages. In the meanwhile, the artificial intelligence and augmented reality in robotic surgery are developing rapidly and receive lots of attention. However, current methods have not discussed the coherent integration of AI and AR in robotic surgery. In this paper, we develop a novel system by seamlessly merging artificial intelligence module and augmented reality visualization to automatically generate the surgical guidance for robotic surgery education. Specifically, we first leverage reinforcement leaning to learn from expert demonstration and then generate 3D guidance trajectory, providing prior context information of the surgical procedure. Along with other information such as text hint, the 3D trajectory is then overlaid in the stereo view of dVRK, where the user can perceive the 3D guidance and learn the procedure. The proposed system is evaluated through a preliminary experiment on surgical education task peg-transfer, which proves its feasibility and potential as the next generation of robot-assisted surgery education solution.

Objective: The computation of anatomical information and laparoscope position is a fundamental block of surgical navigation in Minimally Invasive Surgery (MIS). Recovering a dense 3D structure of surgical scene using visual cues remains a challenge, and the online laparoscopic tracking primarily relies on external sensors, which increases system complexity. Methods: Here, we propose a learning-driven framework, in which an image-guided laparoscopic localization with 3D reconstructions of complex anatomical structures is obtained. To reconstruct the 3D structure of the whole surgical environment, we first fine-tune a learning-based stereoscopic depth perception method, which is robust to the texture-less and variant soft tissues, for depth estimation. Then, we develop a dense visual reconstruction algorithm to represent the scene by surfels, estimate the laparoscope poses and fuse the depth maps into a unified reference coordinate for tissue reconstruction. To estimate poses of new laparoscope views, we achieve a coarse-to-fine localization method, which incorporates our reconstructed 3D model. Results: We evaluate the reconstruction method and the localization module on three datasets, namely, the stereo correspondence and reconstruction of endoscopic data (SCARED), the ex-vivo phantom and tissue data collected with Universal Robot (UR) and Karl Storz Laparoscope, and the in-vivo DaVinci robotic surgery dataset, where the reconstructed 3D structures have rich details of surface texture with an accuracy error under 1.71 mm and the localization module can accurately track the laparoscope with only images as input. Conclusions: Experimental results demonstrate the superior performance of the proposed method in 3D anatomy reconstruction and laparoscopic localization. Significance: The proposed framework can be potentially extended to the current surgical navigation system.

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.

Reconstructing the scene of robotic surgery from the stereo endoscopic video is an important and promising topic in surgical data science, which potentially supports many applications such as surgical visual perception, robotic surgery education and intra-operative context awareness. However, current methods are mostly restricted to reconstructing static anatomy assuming no tissue deformation, tool occlusion and de-occlusion, and camera movement. However, these assumptions are not always satisfied in minimal invasive robotic surgeries. In this work, we present an efficient reconstruction pipeline for highly dynamic surgical scenes that runs at 28 fps. Specifically, we design a transformer-based stereoscopic depth perception for efficient depth estimation and a light-weight tool segmentor to handle tool occlusion. After that, a dynamic reconstruction algorithm which can estimate the tissue deformation and camera movement, and aggregate the information over time is proposed for surgical scene reconstruction. We evaluate the proposed pipeline on two datasets, the public Hamlyn Centre Endoscopic Video Dataset and our in-house DaVinci robotic surgery dataset. The results demonstrate that our method can recover the scene obstructed by the surgical tool and handle the movement of camera in realistic surgical scenarios effectively at real-time speed., Comment: Accepted to MICCAI 2021

Automatic surgical workflow recognition is a key component for developing context-aware computer-assisted systems in the operating theatre. Previous works either jointly modeled the spatial features with short fixed-range temporal information, or separately learned visual and long temporal cues. In this paper, we propose a novel end-to-end temporal memory relation network (TMRNet) for relating long-range and multi-scale temporal patterns to augment the present features. We establish a long-range memory bank to serve as a memory cell storing the rich supportive information. Through our designed temporal variation layer, the supportive cues are further enhanced by multi-scale temporal-only convolutions. To effectively incorporate the two types of cues without disturbing the joint learning of spatio-temporal features, we introduce a non-local bank operator to attentively relate the past to the present. In this regard, our TMRNet enables the current feature to view the long-range temporal dependency, as well as tolerate complex temporal extents. We have extensively validated our approach on two benchmark surgical video datasets, M2CAI challenge dataset and Cholec80 dataset. Experimental results demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 67.0% v.s. 78.9% Jaccard on Cholec80 dataset)., Comment: Accepted at IEEE Transactions on Medical Imaging (IEEE TMI); Code is available at https://github.com/YuemingJin/TMRNet

The "MIcro-Surgical Anastomose Workflow recognition on training sessions" (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 described at three different granularity levels: phase, step, and activity. The participants were given the option to use kinematic data and videos to develop workflow recognition models. 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. One ranking was made for each task. 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. Six teams, including a non-competing team, participated in at least one task. All models employed deep learning models, such as CNN or RNN. The best models achieved more than 95% AD-Accuracy for phase recognition, 80% for step recognition, 60% for activity recognition, and 75% for all granularity levels. For high levels of granularity (i.e., phases and steps), the best models had a recognition rate that may be sufficient for applications such as prediction of remaining surgical time or resource management. However, for activities, the recognition rate was still low for applications that can be employed clinically. The MISAW data set is publicly available to encourage further research in surgical workflow recognition. It can be found at www.synapse.org/MISAW, Comment: MICCAI2020 challenge report, 36 pages including 15 for supplementary material (complet results for each participating teams), 17 figures

Real-time surgical phase recognition is a fundamental task in modern operating rooms. Previous works tackle this task relying on architectures arranged in spatio-temporal order, however, the supportive benefits of intermediate spatial features are not considered. In this paper, we introduce, for the first time in surgical workflow analysis, Transformer to reconsider the ignored complementary effects of spatial and temporal features for accurate surgical phase recognition. Our hybrid embedding aggregation Transformer fuses cleverly designed spatial and temporal embeddings by allowing for active queries based on spatial information from temporal embedding sequences. More importantly, our framework processes the hybrid embeddings in parallel to achieve a high inference speed. Our method is thoroughly validated on two large surgical video datasets, i.e., Cholec80 and M2CAI16 Challenge datasets, and outperforms the state-of-the-art approaches at a processing speed of 91 fps., Comment: MICCAI2021

Automatic surgical gesture recognition is fundamentally important to enable intelligent cognitive assistance in robotic surgery. With recent advancement in robot-assisted minimally invasive surgery, rich information including surgical videos and robotic kinematics can be recorded, which provide complementary knowledge for understanding surgical gestures. However, existing methods either solely adopt uni-modal data or directly concatenate multi-modal representations, which can not sufficiently exploit the informative correlations inherent in visual and kinematics data to boost gesture recognition accuracies. In this regard, we propose a novel online approach of multi-modal relational graph network (i.e., MRG-Net) to dynamically integrate visual and kinematics information through interactive message propagation in the latent feature space. In specific, we first extract embeddings from video and kinematics sequences with temporal convolutional networks and LSTM units. Next, we identify multi-relations in these multi-modal embeddings and leverage them through a hierarchical relational graph learning module. The effectiveness of our method is demonstrated with state-of-the-art results on the public JIGSAWS dataset, outperforming current uni-modal and multi-modal methods on both suturing and knot typing tasks. Furthermore, we validated our method on in-house visual-kinematics datasets collected with da Vinci Research Kit (dVRK) platforms in two centers, with consistent promising performance achieved., Comment: Accepted for ICRA 2021