Robot-assisted Minimally Invasive Surgery Research Articles

Teleoperation in robot-assisted MIS with adaptive RCM via admittance control

AbstractThis paper presents the development and assessment of a teleoperation framework for robot-assisted minimally invasive surgery (MIS). The framework leverages our novel integration of a previously developed adaptive remote center of motion (RCM) using admittance control. This framework operates within a redundancy resolution method specifically designed for the RCM constraint. We introduce a compact, low-cost, and modular custom-designed instrument module (IM) that ensures integration with the manipulator, featuring a force/torque sensor, a surgical instrument, and an actuation unit for driving the surgical instrument. The paper details the complete teleoperation framework, including the telemanipulation trajectory mapping, kinematic modelling, control strategy, and the integrated admittance controller. Finally, the system’s capability to perform various surgical tasks was demonstrated, including passing a thread through the rings, picking and placing objects, and trajectory tracking.

Utilization of a Single-Site Port as an Adjunct for Multi-Port Robotic-Assisted Surgery in Children.

Introduction: The focused use of a single-site port as an adjunct designed to decrease overall port site number and/or assist with specimen extraction in pediatric robotic surgery has not been fully elucidated. We aimed to describe the feasibility of using the single-site port as an adjunct during multi-port robotic-assisted minimally invasive surgery (RA-MIS). Methods: A single institution retrospective review of pediatric patients who underwent multiport RA-MIS with an adjunctive single-site (SS) port from August 2018 to October 2022 was performed. Demographic, perioperative, and postoperative variables were collected; descriptive analysis was performed. Results: A total of 13 patients were included; 46% were female, and 47% were Caucasian. Median age at surgery was 14.9 years of age (interquartile range [IQR] 10.6, 18); median weight was 61.1 kg (IQR 39.7, 73.6). Eleven patients (85%) underwent splenectomy; 2 patients (15%) underwent adrenalectomy. Four patients had a combined procedure (SS cholecystectomy with multi-port splenectomy [n = 3], multi-port bilateral adrenalectomy [n = 1]). The median total operative time was 197 minutes (IQR 131, 316); median console time was 59 minutes (IQR 40, 126). Two 8 mm robotic ports were utilized for all but 1 patient who required a third 8 mm port. The median length of stay was 2.1 days (IQR 2.0, 3.1). One readmission for fever occurred following a combined cholecystectomy/splenectomy. No hernias or wound infections were identified at the single-site port. Conclusion: Use of a SS port as an adjunct is a feasible option and should be considered for those with splenomegaly or need for combined procedures in different quadrants of the abdomen.

Assessment of Surgeons' Stress Levels with Digital Sensors during Robot-Assisted Surgery: An Experimental Study.

Robot-Assisted Minimally Invasive Surgery (RAMIS) marks a paradigm shift in surgical procedures, enhancing precision and ergonomics. Concurrently it introduces complex stress dynamics and ergonomic challenges regarding the human-robot interface and interaction. This study explores the stress-related aspects of RAMIS, using the da Vinci XI Surgical System and the Sea Spikes model as a standard skill training phantom to establish a link between technological advancement and human factors in RAMIS environments. By employing different physiological and kinematic sensors for heart rate variability, hand movement tracking, and posture analysis, this research aims to develop a framework for quantifying the stress and ergonomic loads applied to surgeons. Preliminary findings reveal significant correlations between stress levels and several of the skill-related metrics measured by external sensors or the SURG-TLX questionnaire. Furthermore, early analysis of this preliminary dataset suggests the potential benefits of applying machine learning for surgeon skill classification and stress analysis. This paper presents the initial findings, identified correlations, and the lessons learned from the clinical setup, aiming to lay down the cornerstones for wider studies in the fields of clinical situation awareness and attention computing.

Augmenting Robot-Assisted Pattern Cutting with Periodic Perturbations-Can We Make Dry Lab Training More Realistic?

Teleoperated robot-assisted minimally-invasive surgery (RAMIS) offers many advantages over open surgery, but RAMIS training still requires optimization. Existing motor learning theories could improve RAMIS training. However, there is a gap between current knowledge based on simple movements and training approaches required for the more complicated work of RAMIS surgeons. Here, we studied how surgeons cope with time-dependent perturbations. We used the da Vinci Research Kit and investigated the effect of time-dependent force and motion perturbations on learning a circular pattern-cutting surgical task. Fifty-four participants were assigned to two experiments, with two groups for each: a control group trained without perturbations and an experimental group trained with 1Hz perturbations. In the first experiment, force perturbations alternatingly pushed participants' hands inwards and outwards in the radial direction. In the second experiment, the perturbation constituted a periodic up-and-down motion of the task platform. Participants trained with perturbations learned how to overcome them and improve their performances during training without impairing them after the perturbations were removed. Moreover, training with motion perturbations provided participants with an advantage when encountering the same or other perturbations after training, compared to training without perturbations. Periodic perturbations can enhance RAMIS training without impeding the learning of the perturbed task. Our results demonstrate that using challenging training tasks that include perturbations can better prepare surgical trainees for the dynamic environment they will face with patients in the operating room.

Application of tactile sensing in human-computer interaction in robot-assisted surgery and medical fields

Robot-assisted Minimally Invasive Surgery (RMIS) is a revolutionary breakthrough in the field of surgery in 21st-century clinical medicine, and in recent years it has become the standard of care in Western medicine. It makes highly accurate medical operations possible based on the advantages of traditional minimally invasive surgery, such as reducing patient trauma and accelerating post-operative healing. However, the most advanced robotic-assisted surgical systems available on the market, as exemplified by the da Vinci system, are still not equipped with tactile receptors. In recent years, scientists and engineers have come up with different techniques and ideas, including various forms of tactile sensors, to improve the quality of the process. In this paper, the sensor devices that can be used for RMIS are classified into six different types based on their structural characteristics, and typical examples of them are listed. For some of the sensing structures that are only in the theoretical stage, inferences and explanations are given based on references. And the application directions are summarized as tactile diagnosis and operator sensing. Research in the last decade in both areas of sensing technology is summarized and outlined respectively.

ACAM-FoC: A Deep Neural Network Augmented From CAM-FoC to Measure the Grip Force of Mass-Produced Elongated Surgical Instruments

Learning-based grip force measurement methods in robot-assisted minimally invasive surgery (RAMIS) outperforms the traditional model-based methods and avoids the application issues of sensor-based approaches. However, few studies have investigated the problem of grip force measurement in mass-produced surgical instruments. This letter takes the difference in motion hysteresis and mechanism friction among mass-produced surgical instruments into account, and proposes a novel learning-based method ACAM-FoC. ACAM-FoC is an augmentation of CAM-FoC, which is a high accuracy lightweight network proposed in our preceding research. Loss function monotonicity limitation is introduced to alleviate the negative effect of unbalance training data. Offiline experiments are conducted to verify the effectiveness and the advantages over other two existing methods. Online experiments on the self-developed surgical robot system are conducted to preliminarily realize and verify the grip force measurement and feedback in real time. The results support the importance of grip force feedback in leader-follower operation tasks.

Rethinking exemplars for continual semantic segmentation in endoscopy scenes: Entropy-based mini-batch pseudo-replay

Endoscopy is a widely used technique for the early detection of diseases or robotic-assisted minimally invasive surgery (RMIS). Numerous deep learning (DL)-based research works have been developed for automated diagnosis or processing of endoscopic view. However, existing DL models may suffer from catastrophic forgetting. When new target classes are introduced over time or cross institutions, the performance of old classes may suffer severe degradation. More seriously, data privacy and storage issues may lead to the unavailability of old data when updating the model. Therefore, it is necessary to develop a continual learning (CL) methodology to solve the problem of catastrophic forgetting in endoscopic image segmentation. To tackle this, we propose a Endoscopy Continual Semantic Segmentation (EndoCSS) framework that does not involve the storage and privacy issues of exemplar data. The framework includes a mini-batch pseudo-replay (MB-PR) mechanism and a self-adaptive noisy cross-entropy (SAN-CE) loss. The MB-PR strategy circumvents privacy and storage issues by generating pseudo-replay images through a generative model. Meanwhile, the MB-PR strategy can also correct the model deviation to the replay data and current training data, which is aroused by the significant difference in the amount of current and replay images. Therefore, the model can perform effective representation learning on both new and old tasks. SAN-CE loss can help model fitting by adjusting the model’s output logits, and also improve the robustness of training. Extensive continual semantic segmentation (CSS) experiments on public datasets demonstrate that our method can robustly and effectively address the catastrophic forgetting brought by class increment in endoscopy scenes. The results show that our framework holds excellent potential for real-world deployment in a streaming learning manner.

Safe Manipulation in Robotic Surgery Using Compliant Constant-Force Mechanism

Safe manipulation of soft tissue in robotic-assisted minimally invasive surgery (RMIS) is a challenging task for surgeons. The conventional solution is to introduce tactile sensors to measure the tool-tissue interaction force, and then transmit the signal back to the surgeon to enable manual force control. However, since the RMIS-forceps is very small, even the hand tremor of the surgeon could lead to unstable force applied to the tissue. To cope with this problem, we present a compliant constant-force mechanism (CFM) in this article to achieve stable force regulation of RMIS forceps. The proposed CFM is comprised of a pair of symmetrical compliant slider-crank mechanisms, whose mechanical behavior can be described by a pseudo-rigid-body (PRB) model. Cross-spring-based compliant joints are also introduced to improve the model accuracy, while the magnitude of the generated constant force can be adjusted by using detachable slider-crank mechanisms with different force configurations. In this work, the proposed CFM is selective-laser-sintered with polyamide (PA2200) and is actuated by a linear motor. Experiments were also conducted and successfully validated the constant-force performance of the proposed CFM. Furthermore, a grasping test of artificial artery was also performed, which demonstrated the application of the developed CFM system in RMIS.

RCM adjustment for a double-parallelogram based RCM mechanism used for MIS robots

The inevitable errors in the manufacturing, assembly, and testing of a remote center-of-motion (RCM) mechanism lead to the erroneous link parameters which deviate its geometry. Consequently, the motion, as well as the force, become non-zero at the entry port to the patient’s body which is undesirable. To address this issue, the current work first presents the accurate kinematic model of the RCM of an exemplary double-parallelogram-based RCM mechanism. Thereafter, it introduces the RCM adjustment concept and a flexure-based compliant mechanism to nullify/minimize the said deviation. For the analytical design of the flexure element, this paper makes the required design calculations and performs the finite element analysis. It is followed by the disclosure of the RCM Adjustment System and a systematized method of RCM adjustment for a mechanically constrained RCM device. The devised system is based on the prescribed compliant mechanism design and is advantageous, over the traditional RCM adjustments. The potential of the proposed concept lies in the fact that it is not limited to the adopted mechanism only rather, it is extendable to other mechanisms as well which was missing in the prior art. In addition, it offers a more simplified and economical design. Further, an initial prototype of the exemplary mechanism is manufactured using laser micromachining and rapid prototyping techniques. Both analytical as well as physical validations have been performed which proved the efficacy of the proposed kinematic modeling concept. Furthermore, the prototype of the introduced RCM Adjustment System is manufactured as a single-piece design which demonstrated its effectiveness. The preferred embodiment of the same is the said double-parallelogram-based RCM mechanism which is most widely used for robot-assisted minimally invasive surgery (RAMIS). It is designed in a SolidWorks environment and manufactured using Al6101-T6 and SS304 as link material, and a variety of standard elements.

Multi-scale feature retention and aggregation for colorectal cancer diagnosis using gastrointestinal images

Colonoscopy is considered the gold standard for colorectal cancer diagnosis and prognosis. However, existing methods are less accurate and prone to overlooking lesions during gastrointestinal endoscopic examinations. Computer-assisted diagnosis combined with robot-assisted minimally invasive surgery (RMIS) can significantly help medical practitioners detect and treat lesions. Therefore, two novel architectures are developed for polyp and surgical instrument segmentation to aid colorectal cancer diagnosis, assessment, and treatment. Colorectal cancer segmentation network (CCS-Net) is the base network used in this study. It uses the maximum convolutional layers near the input image for effective feature extraction from low-level information. In addition, CCS-Net uses an efficient feature upsampling unit to efficiently increase the input spatial features’ map size. Hence, CCS-Net is capable of providing a fair performance with satisfactory computational efficiency The multi-scale feature retention and aggregation network (MFRA-Net) is the final network in this study. MFRA-Net is developed to improve the segmentation accuracy of the CCS-Net further as it uses multi-scale feature retention to retain low-level spatial features and transfers them to deep stages of the network. MFRA-Net also combines multi-scale high-strided low-level information with high-level information to boost network segmentation performance. Finally, all the transferred multi-scale features from the early stages of the network are aggregated with high-level features in the deep levels of the network. This multi-scale feature retention and aggregation mechanism enables the network to maintain a better segmentation performance compared with other methods even with challenging blur, specular reflection, low contrast, and high variation cases. We evaluated both architectures on four challenging datasets: Kvasir-SEG, CVC-ClinicDB, Kvasir-Instrument, and the UW-Sinus-Surgery-Live dataset. The proposed method achieves dice similarity coefficients of 95.98%, 94.19%, 92.81%, and 88.57% for the CVC-ClinicDB, Kvasir-SEG, Kvasir-Instrument, and UW-Sinus-Surgery-Live datasets. The proposed method achieves superior segmentation performance compared with state-of-the-art methods and requires only 4.9 million trainable parameters for complete training. Therefore, the proposed networks can effectively assist health professionals in surgical procedures and colorectal cancer diagnosis through surgical instruments and polyp segmentation, respectively.

A Highly Integrated 3D MEMS Force Sensing Module With Variable Sensitivity for Robotic‐Assisted Minimally Invasive Surgery

AbstractIn robotic‐assisted minimally invasive surgery (RMIS), non‐sentient surgical instruments make it impossible for surgeons to perceive operational force during the procedure. To facilitate surgeons with force telepresence during surgery, a highly integrated MEMS‐based piezoresistive 3D force sensing module, which is composed of a MEMS‐based piezoresistive sensor chip, an encapsulation cap with miniature pyramids, and a top elastic layer, is demonstrated. This innovative combined construction allows for rapid replacement of elastic layers with different thicknesses and different Young's modulus, so as to realize an adjustable sensitivity and measurement range for different surgeries. By replacing the elastic layer, the same amount of change in resistance can be achieved for external force of 3 and 10 N in the Z‐axis; the sensitivity in X‐ and Y‐axes can be increased by a maximum of eight and seven times, respectively. Meanwhile, miniature size enables it to be integrated into various surgical instruments’ tip. Experimental demonstrations involving palpation simulated nodule detection of kidney, ex vivo puncture, and threading forces estimation of tissue‐mimicking are conducted to validate the effectiveness of adjusting sensitivity and range. This sensing module is potentially a promising solution for low‐cost and versatility to surgical instruments, which can facilitate unification of force‐sensing/intelligent surgical instruments.

A touch-free human-robot collaborative surgical navigation robotic system based on hand gesture recognition.

Robot-assisted minimally invasive surgery (RAMIS) has gained significant traction in clinical practice in recent years. However, most surgical robots rely on touch-based human-robot interaction (HRI), which increases the risk of bacterial diffusion. This risk is particularly concerning when surgeons must operate various equipment with their bare hands, necessitating repeated sterilization. Thus, achieving touch-free and precise manipulation with a surgical robot is challenging. To address this challenge, we propose a novel HRI interface based on gesture recognition, leveraging hand-keypoint regression and hand-shape reconstruction methods. By encoding the 21 keypoints from the recognized hand gesture, the robot can successfully perform the corresponding action according to predefined rules, which enables the robot to perform fine-tuning of surgical instruments without the need for physical contact with the surgeon. We evaluated the surgical applicability of the proposed system through both phantom and cadaver studies. In the phantom experiment, the average needle tip location error was 0.51 mm, and the mean angle error was 0.34 degrees. In the simulated nasopharyngeal carcinoma biopsy experiment, the needle insertion error was 0.16 mm, and the angle error was 0.10 degrees. These results indicate that the proposed system achieves clinically acceptable accuracy and can assist surgeons in performing contactless surgery with hand gesture interaction.

A Modular 3-Degrees-of-Freedom Force Sensor for Robot-Assisted Minimally Invasive Surgery Research.

Effective force modulation during tissue manipulation is important for ensuring safe, robot-assisted, minimally invasive surgery (RMIS). Strict requirements for in vivo applications have led to prior sensor designs that trade off ease of manufacture and integration against force measurement accuracy along the tool axis. Due to this trade-off, there are no commercial, off-the-shelf, 3-degrees-of-freedom (3DoF) force sensors for RMIS available to researchers. This makes it challenging to develop new approaches to indirect sensing and haptic feedback for bimanual telesurgical manipulation. We present a modular 3DoF force sensor that integrates easily with an existing RMIS tool. We achieve this by relaxing biocompatibility and sterilizability requirements and by using commercial load cells and common electromechanical fabrication techniques. The sensor has a range of ±5 N axially and ±3 N laterally with errors of below 0.15 N and maximum errors below 11% of the sensing range in all directions. During telemanipulation, a pair of jaw-mounted sensors achieved average errors below 0.15 N in all directions. It achieved an average grip force error of 0.156 N. The sensor is for bimanual haptic feedback and robotic force control in delicate tissue telemanipulation. As an open-source design, the sensors can be adapted to suit other non-RMIS robotic applications.

An Automated Skill Assessment Framework Based on Visual Motion Signals and a Deep Neural Network in Robot-Assisted Minimally Invasive Surgery.

Surgical skill assessment can quantify the quality of the surgical operation via the motion state of the surgical instrument tip (SIT), which is considered one of the effective primary means by which to improve the accuracy of surgical operation. Traditional methods have displayed promising results in skill assessment. However, this success is predicated on the SIT sensors, making these approaches impractical when employing the minimally invasive surgical robot with such a tiny end size. To address the assessment issue regarding the operation quality of robot-assisted minimally invasive surgery (RAMIS), this paper proposes a new automatic framework for assessing surgical skills based on visual motion tracking and deep learning. The new method innovatively combines vision and kinematics. The kernel correlation filter (KCF) is introduced in order to obtain the key motion signals of the SIT and classify them by using the residual neural network (ResNet), realizing automated skill assessment in RAMIS. To verify its effectiveness and accuracy, the proposed method is applied to the public minimally invasive surgical robot dataset, the JIGSAWS. The results show that the method based on visual motion tracking technology and a deep neural network model can effectively and accurately assess the skill of robot-assisted surgery in near real-time. In a fairly short computational processing time of 3 to 5 s, the average accuracy of the assessment method is 92.04% and 84.80% in distinguishing two and three skill levels. This study makes an important contribution to the safe and high-quality development of RAMIS.

High-Sensitivity and Wide-Range Resistance Measurement Based on Self-Balancing Wheatstone Bridge and Gated Recurrent Neural Network

A Wheatstone bridge and the following amplifier are widely used for measuring resistance. But for the measurement of small resistance change, the gain of the amplifier must be very high, which can reduce measurement range and introduce obvious baseline drift into the measured signal inevitably. In this study, a self-balancing Wheatstone bridge is designed based on a digitally controlled potentiometer (DCP). During the initial balance of the Wheatstone bridge, the DCP is adjusted until the output of the bridge is close to zero volts. When the bridge works for the measurement of dynamic resistance, the DCP is readjusted to compensate the remarkable change in the resistance, and the output of the amplifier is thus limited in the input voltage range of the ADC. At the same time, the signal sampled by the ADC is processed by the least-squares fitting to extend the measurement range. In addition, an attention-based gated recurrent unit (AGRU) is proposed to remove the drift in the signal. The effectiveness, stability, and accuracy of the proposed method have been demonstrated through multiple force measurement experiments on the instrument of a robot assisted minimally invasive surgery (RMIS) system.

A Step Towards Conditional Autonomy - Robotic Appendectomy

In recent years, Robot-Assisted Minimally Invasive Surgery (RAMIS) has been widely adopted worldwide due to its high precision, improved ergonomics and intuitive control. With the advances in artificial intelligence and surgical robot technologies, it is anticipated that the cognitive load on the surgeons could be relieved with a higher level of autonomy on surgical robots as well as simultaneously improving the precision of surgical robots' operations, minimising the risk of human errors and leading to safer operations. However, much research is still focused on task autonomy due to the complexity of the operations, and the limited clinical data on robotic surgery in some specific scenarios. Therefore, recent research has widely used simulated surgery scenarios to collect data to train artificial intelligence (AI) models. In this paper, we propose a method as a step towards conditional autonomy for robotic appendectomy. To achieve conditional autonomy, demonstration data was collected from human operators performing the appendectomy in a simulated robotic scene. The robotic instrument movements and trajectories for performing the appendectomy were learned from the demonstrated data. Once the surgeon specifies the location of the appendix, the proposed framework can carry out the appendectomy autonomously by using the dynamic motion primitives (DMP) generated from the learned surgical movements. Through the extensive validations in a simulated environment and on the da Vinci Research Kit (dVRK), we have shown that the proposed method can carry out the appendectomy procedure semi-automatically. Based on five metrics, it shows that the framework can reduce the total task path length, completion time and appendix stump length while maintaining a high degree of similarity to the demonstrated trajectory. This work demonstrated the feasibility of conditional autonomy in robotic surgeries.

Effects of robot-assisted minimally invasive surgery on osteoporotic vertebral compression fracture: a systematic review, meta-analysis, and meta-regression of retrospective study.

To conduct a systematic review on the effect of robot-assisted minimally invasive surgery (R-MIS) on the clinical outcomes and complications of patients with osteoporotic vertebral compression fractures (OVCFs). The researchers searched the papers published on PubMed, The Cochrane Library, Web of Science, Embase, Scopus, Ovid MEDLINE, Wiley Online Library, China National Knowledge Infrastructure (CNKI), Chinese biomedical literature service system (SinoMed), and China Medical Association Data. The standardized mean difference (SMD) or mean difference (MD), relative risk (RR), and 95% confidence interval (CI) were calculated. Besides, the data was merged through the random-effect model or common-effect model. A meta-regression mixed-effects single-factor model was utilized to analyze the sources of heterogeneity. Twelve studies were included, involving 1042 OVCFs cases. The prognosis of patients treated with R-MIS was significantly improved, such as Oswestry disability index (ODI) score (MD = -0.65, P = 0.0171), Cobb's angles (MD = -1.03, P = 0.0027), X-ray fluoroscopy frequency (SMD = -2.41, P < 0.0001), Length of hospital stay (MD = -0.33, P = 0.0002), and Cement leakage (RR = 0.37, P < 0.0001). However, no obvious improvement was found in the results of Visual analog scale (VAS) score (MD = -0.16, P = 0.1555), Volume of bone cement (MD = 0.22, P = 0.8339), and Operation time (MD = -3.20, P = 0.3411) after being treated by R-MIS. The meta-regression analysis demonstrated that R-MIS presented no significant impact on the covariates of VAS and Operation time. R-MIS can significantly reduce the patients' ODI, Cobb's angles, X-ray fluoroscopy frequency, and Cement leakage ratio, and shorten the Length of hospital stay. Therefore, R-MIS may be an effective method to promote the patients' functional recovery, correct spinal deformity, reduce the X-ray fluoroscopy frequency, shorten the Length of hospital stay, and reduce the complications of OVCFs bone Cement leakage.

A Concurrent Framework for Constrained Inverse Kinematics of Minimally Invasive Surgical Robots.

Minimally invasive surgery has undergone significant advancements in recent years, transforming various surgical procedures by minimizing patient trauma, postoperative pain, and recovery time. However, the use of robotic systems in minimally invasive surgery introduces significant challenges related to the control of the robot's motion and the accuracy of its movements. In particular, the inverse kinematics (IK) problem is critical for robot-assisted minimally invasive surgery (RMIS), where satisfying the remote center of motion (RCM) constraint is essential to prevent tissue damage at the incision point. Several IK strategies have been proposed for RMIS, including classical inverse Jacobian IK and optimization-based approaches. However, these methods have limitations and perform differently depending on the kinematic configuration. To address these challenges, we propose a novel concurrent IK framework that combines the strengths of both approaches and explicitly incorporates RCM constraints and joint limits into the optimization process. In this paper, we present the design and implementation of concurrent inverse kinematics solvers, as well as experimental validation in both simulation and real-world scenarios. Concurrent IK solvers outperform single-method solvers, achieving a 100% solve rate and reducing the IK solving time by up to 85% for an endoscope positioning task and 37% for a tool pose control task. In particular, the combination of an iterative inverse Jacobian method with a hierarchical quadratic programming method showed the highest average solve rate and lowest computation time in real-world experiments. Our results demonstrate that concurrent IK solving provides a novel and effective solution to the constrained IK problem in RMIS applications.

Surgical smoke removal via residual Swin transformer network.

In robot-assisted minimally invasive surgery (RMIS), smoke produced by laser ablation and cauterization causes degradation in the visual quality of the operating field, increasing the difficulty and risk of surgery. Therefore, it is important and meaningful to remove fog or smoke from the endoscopic video to maintain a clear visual field. In this paper, we propose a novel method for surgical smoke removal based on the Swin transformer. Our method firstly uses convolutional neural network to extract shallow features, then uses the Swin transformer block to further extract deep features and finally generates smoke-free images. We conduct quantitative and qualitative experiments on the proposed method, and we also validate the desmoking results in the surgical instrument segmentation task. Extensive experiments on synthetic and real dataset show that the proposed approach has good performance and outperforms the state-of-the-art surgical smoke removal methods. Our method effectively removes surgical smoke, improves image quality and reduces the risk of RMIS. It provides a clearer visual field for the surgeon, as well as for subsequent visual tasks, such as instrument segmentation, 3D scene reconstruction and surgery automation.

Exploring the future of surgical practices

Background: Robotic-Assisted Minimally Invasive Surgery (RAMIS) represents a significant advancement in surgical techniques, leveraging robotic systems to enhance precision, reduce invasiveness, and improve patient outcomes. The da Vinci surgical system has been a leading example, demonstrating the potential of robotic assistance in minimally invasive procedures. Aim: This paper explores the evolution of RAMIS, focusing on technological advancements, integration with Artificial Intelligence (AI), and future directions in surgical robotics. Methods: The study reviews the development and current state of RAMIS technologies, including the historical background, state-of-the-art systems, and emerging innovations. It analyzes data from a range of sources including literature reviews, market reports, and recent research developments. Results: RAMIS systems, particularly the da Vinci surgical system, have achieved widespread adoption due to their advanced features, such as enhanced vision, improved ergonomics, and training programs. Recent advancements include AI integration, new sensor technologies, and enhanced imaging modalities. Despite these improvements, challenges remain in achieving higher levels of autonomy and addressing cost and regulatory issues. Conclusion: RAMIS continues to evolve with significant advancements in AI, haptic feedback, and simulation technologies. Future developments are expected to further enhance surgical precision and outcomes.