Application Of Robot-assisted Surgery Research Articles

Impact of Artificial Intelligence and Machine Learning on Urological Practice

Abstract Artificial intelligence (AI) has revolutionized urology while reshaping clinical practice and research. It excels in predicting treatment outcomes and enhancing disease diagnosis accuracy, particularly in bladder disorders such as interstitial cystitis, bladder cancer, and reproductive urology. AI’s data analysis capabilities enable early detection and prognosis by identifying patterns in vast datasets. It paves the way for more personalized treatments and reshapes disease classification. In the age of “big data,” AI simplifies complex healthcare information while improving decision-making and patient care. In addition, physical AI applications in robot-assisted surgery and nanotechnology enhance drug administration precision, surgical effectiveness, and patient outcomes. This review highlights AI’s pivotal role in identifying and treating urological disorders, aiding surgical guidance, and advancing tissue engineering, showcasing its significant impact and ongoing progress in the field of urology.

Pyeloplasty in Children with Ureteropelvic Junction Obstruction and Associated Kidney Anomalies: Can a Robotic Approach Make Surgery Easier?

Robot-assisted pyeloplasty is widely used in pediatric surgery because of its well-known advantages over open or laparoscopic surgery. The aim is to explore our experience and evaluate the achievements we have made. We evaluated patients undergoing robotic pyeloplasty from January 2016 to November 2021, including those who presented with a ureteropelvic junction obstruction associated with other anomalies of the kidney. The parameters examined were: age, weight, associated renal malformations, conversion rate, operative time, and intra- and postoperative complications. Of 39 patients, 7 (20%) were included, of whom 5 (71%) were male and 2 (29%) were female. The mean age at surgery was 84 months (range 36-180 months), and the mean weight at surgery was 24.4 kg (range 11-40 kg). In five (71%) patients the ureteropelvic junction obstruction (UPJO) was left-sided and in two (29%) it was right-sided. In four (57%) cases, UPJO was associated with a horseshoe kidney, right-sided in one (25%) patient, and left-sided in the other three (75%). A 180° rotation of the kidney was present in one (14%) patient. Nephrolithiasis was present in two (29%) patients. The mean operative time was 160 min (range 140-240 min). The average bladder catheter dwell time was 1 day (range 2-3 days), while the average abdominal drainage dwell time was 2 days (range 2-4 days). The mean hospitalization time was 4 days (range 3-9 days). On average, after 45 days (range 30-65) the JJ ureteral stent was removed cystoscopically. No intraoperative complications were reported, while one case of persistent macrohematuria with anemia requiring blood transfusion occurred postoperatively. Ureteropelvic junction obstruction might be associated with other congenital urinary tract anomalies such as a duplicated collecting system, horseshoe kidney, or pelvic kidney. These kinds of malformations can complicate surgery and require more attention and accuracy from the surgeon. Our experience shows that, with regards to the robotic learning curve required for pyeloplasty, the treatment of the ureteropelvic junction in these situations does not present insurmountable difficulties nor is burdened by complications. The application of robot-assisted surgery in pediatric urology makes difficult pyeloplasties easier.

FRSR: Framework for real-time scene reconstruction in robot-assisted minimally invasive surgery

3D reconstruction of the intra-operative scenes provides precise position information which is the foundation of various safety related applications in robot-assisted surgery, such as augmented reality. Herein, a framework integrated into a known surgical system is proposed to enhance the safety of robotic surgery. In this paper, we present a scene reconstruction framework to restore the 3D information of the surgical site in real time. In particular, a lightweight encoder–decoder network is designed to perform disparity estimation, which is the key component of the scene reconstruction framework. The stereo endoscope of da Vinci Research Kit (dVRK) is adopted to explore the feasibility of the proposed approach, and it provides the possibility for the migration to other Robot Operating System (ROS) based robot platforms due to the strong independence on hardware. The framework is evaluated using three different scenarios, including a public dataset (3018 pairs of endoscopic images), the scene from the dVRK endoscope in our lab as well as a self-made clinical dataset captured from an oncology hospital. Experimental results show that the proposed framework can reconstruct 3D surgical scenes in real time (25 FPS), and achieve high accuracy (2.69 ± 1.48 mm in MAE, 5.47 ± 1.34 mm in RMSE and 0.41 ± 0.23 in SRE, respectively). It demonstrates that our framework can reconstruct intra-operative scenes with high reliability of both accuracy and speed, and the validation of clinical data also shows its potential in surgery. This work enhances the state of art in 3D intra-operative scene reconstruction based on medical robot platforms. The clinical dataset has been released to promote the development of scene reconstruction in the medical image community.

Transoral Robotic Surgical Proficiency Via Real-Time Tactile Collision Awareness System.

In 2009, the Food and Drug Administration approved the use of the surgical robotic system for removal of benign and malignant conditions of the upper aerodigestive tract. This novel application of robotic-assisted surgery, termed transoral robotic surgery (TORS), places robotic instruments and camera system through the mouth to reach recessed areas of the pharynx and larynx. Over the successive decade, there was a rapid adoption of TORS with a surgical growth rate that continues to increase. Despite the rapid clinical acceptance, the field of TORS has not yet seen substantive changes or advances in the technical shortcomings, the lack of which has restricted objective TORS-specific surgical skills assessment as well as subsequent skills improvement efforts. One of the primary technical challenges of TORS is operating in a confined space, where the robotic system is maneuvered within the restrictive boundaries of the mouth and throat. Due to these confined boundaries of the pharynx, instruments can frequently collide with anatomic structures such as teeth and bone, producing anatomic collisions. Therefore, we hypothesized that anatomic collisions negatively impact TORS surgical performance. Secondarily, we hypothesized that avoidance of unwanted anatomic collisions could improve TORS surgical proficiency. Design and fidelity testing for a custom TORS training platform with an integrated anatomic collision-sensing system providing real-time tactile feedback is described. Following successful platform assembly and testing, validation study using the platform was carried through prospective surgical training with trial randomization. Twenty otolaryngology-head and neck surgery residents, each trainee performing three discrete mock surgical trials (n = 60), performed the initial system validation. Ten of the 20 residents were randomized to perform the surgical trials utilizing the real-time feedback system. The remaining 10 residents were randomized to perform the surgical trials without the feedback system, although the system still could record collision data. Surgical proficiency was measured by Global Evaluative Assessment of Robotic Skills (GEARS) score, time to completion, and tumor resection scores (categorical scale ranging 0-3, describing the adequacy of resection). Major anatomic collisions (greater than 5N of force) negatively affected GEARS robotic skills. A mixed model analysis demonstrated that for every additional occurrence of a major collision, GEARS robotic skills assessment score would decrease by 0.29 points (P = .04). Real-time collision awareness created significantly fewer major (> 5 N) anatomic collisions with the tactile feedback system active (n = 30, mean collisions = 2.9 ± 4.2) as compared with trials without tactile feedback (n = 30, mean collisions = 12.53 ± 23.23) (P < .001). The second assessment measure of time to completion was unaffected by the presence of collisions or by the use of tactile feedback system. The third proficiency assessment was measured with tumor resection grading. Tumor resection scores was significantly (P = .02) improved with collision awareness system activated than trials without collision awareness. In order to test our primary hypothesis, a novel TORS training platform was successfully developed that provides collision force measurements including frequency, severity, and duration of anatomic collisions. Additionally, the platform was modulated to provide real-time tactile feedback of the occurrence of out-of-field collisions. Utilizing this custom platform, our hypothesis that anatomic collisions during TORS diminishes surgical performance was supported. Additionally, our secondary hypothesis that subsequent reduction of anatomic collisions improves TORS proficiency was supported by the surgical trial. Dedicated investigation to characterize the effect size and clinical impact is required in order to translate this finding into training curriculums and into clinical utilization. II (Randomized trial) Laryngoscope, 130:S1-S17, 2020.

Laparoscopic &amp; robotic liver resection for colorectal cancer metastases

Distant metastasis of colorectal cancer to the liver will occur in approximately 50% of patients and surgical resection is associated with improved survival. Over the past decade minimally invasive techniques have been adopted with an increasing number of major hepatic resections performed for both benign and malignant disease, including colorectal cancer liver metastasis. This review aims to provide an overview and summary of the current data on the perioperative and oncologic outcomes of minimally invasive hepatectomy for metastatic colorectal cancer. Furthermore, the application of robotic assisted surgery and the use of minimally invasive techniques in locoregional treatment of colorectal liver metastasis (CRLM) are also examined.

Application of robot-assisted surgery in the surgical treatment of head and neck cancer

In recent years, robot-assisted surgery (RAS) has developed rapidly and become one of the hot topics in clinical research. Compared with traditional surgery, RAS has advantages in terms of minimal invasiveness, aesthetics, and functional preservation, and has been gradually applied in clinical practice such as neurosurgery, urology, and head and neck surgery. In the treatment of head and neck tumors, RAS can effectively minimize the surgical injury and accelerate postoperative recovery. This article reviews the application of RAS in the resection of primary lesions of head and neck tumors, neck dissection, and reconstruction of tissue defects.

Nonlinear Model-Mediated Teleoperation for Surgical Applications under Time Variant Communication Delay

Robot-assisted surgery is often carried out through master-slave teleoperation. With the progress of robotic technology and development of novel surgical procedures, new challenges emerge like need for haptic feedback and time delay in teleoperation communication channels, etc. Most existing bilateral teleoperation works in literature emphasize more on maintaining system stability at the cost of degraded transparency, with time variant communication delay further worsening the situation. In this paper, we present a nonlinear Hunt-Crossley model-mediated bilateral teleoperation scheme with targeted applications in robot-assisted surgery. The system stability is guaranteed by decoupling the master and slave subsystems and the system transparency is enhanced with online environment parameter estimation using recursive least squares (RLS) technique. Simulation studies have been carried out for both constant and time varying interaction environments. The proposed teleoperation scheme is shown to be efficient in providing stable and transparent performance and robust against communication delay and environment parameter variance.

Robotic harvest of the latissimus dorsi muscle – a feasibility study on a cadaver and application on a clinical case

The applications of robotic assisted surgery have quickly widespread and established in a variety of surgical fields. Current interest of robotic assisted surgery is shifted to endoscopic telesurgery because its small size of incisions, cosmetic advantage, less invasive surgical technics, decrease of internal scar tissues, short duration of hospitalisation and cost effectiveness. We present here an anatomical feasibility and a clinical case of latissimus dorsi muscle harvest with robotic assisted endoscopic surgery.

Robotic-assisted endometrial cancer staging and radical hysterectomy with the da Vinci® surgical system

Robotic-assisted surgery leverages the advantages of standard laparoscopy while restoring three-dimensional vision, ergonomic, intuitive controls, and wristed instruments that approximate the motion of the human hand. Robotic-assisted surgery has already shown feasibility and in many cases superiority to standard laparoscopy in urology and general and cardiothoracic surgery. The applications of robotic-assisted surgery are rapidly being incorporated into the field of gynecologic oncology.

The Surgical Assistant Workstation

The Surgical Assistant Workstation (SAW) is a software development framework that can be used to develop new applications in robot-assisted surgery with augmented visualization. Robot-assisted laparoscopic surgery and micro-surgery as presented by the da Vinci telerobotic system and the Johns Hopkins Steady Hand, respectively can be improved by providing fully-integrated image guidance and information-enhanced intra-operative assistance to the surgical team and to the surgeon in particular. This paper describes several use case applications of the SAW framework, as well as a novel user interface library being developed to support 3D interactive menu systems and overlays for surgical guidance.