Objective: Navigation through tortuous and deformable vessels using catheters with limited steering capability underscores the need for reliable path planning. State-of-the-art path planners do not fully account for the deformable nature of the environment. Methods: This work proposes a robust path planner via a learning from demonstrations method, named Curriculum Generative Adversarial Imitation Learning (C-GAIL). This path planning framework takes into account the interaction between steerable catheters and vessel walls and the deformable property of vessels. Results: In-silico comparative experiments show that the proposed network achieves a 38% higher success rate in static environments and 17% higher in dynamic environments compared to a state-of-the-art approach based on GAIL. In-vitro validation experiments indicate that the path generated by the proposed C-GAIL path planner achieves a targeting error of 1.26±0.55mm and a tracking error of 5.18±3.48mm. These results represent improvements of 41% and 40% over the conventional centerline-following technique for targeting error and tracking error, respectively. Conclusion: The proposed C-GAIL path planner outperforms the state-of-the-art GAIL approach. The in-vitro validation experiments demonstrate that the path generated by the proposed C-GAIL path planner aligns better with the actual steering capability of the pneumatic artificial muscle-driven catheter utilized in this study. Therefore, the proposed approach can provide enhanced support to the user in navigating the catheter towards the target with greater accuracy, effectively meeting clinical accuracy requirements. Significance: The proposed path planning framework exhibits superior performance in managing uncertainty associated with vessel deformation, thereby resulting in lower tracking errors.

Negative Pressure Wound Therapy (NPWT) is a treatment that promotes healing of chronic wounds. Despite high prevalence of chronic wounds in Low- and Middle-Income Countries (LMICs), NPWT devices are not available nor affordable. This study aims to improve chronic wound care in LMICs by presenting the Wound Care (WOCA) system, designed for building, testing and use in LMICs. Design requirements were formulated using input from literature, ISO standards, and wound care experts. The WOCA design was developed to provide safe, portable, user-friendly and affordable NPWT to patients in LMICs. The design features an adjustable operating pressure ranging from −75 to −125 mmHg, a battery for portability, a 300 ml canister, overflow protection, and system state alarms. An Arduino controls the pressure and monitors the system state. Three prototypes were developed and built in Nepal, and their performance was evaluated. Pressure control was 125 ± 10 % mmHg, internal leakage was 7.5 ± 4.3 mmHg/min, reserve capacity was 189 ± 16.9 ml/min, and overflow protection and alarm systems were effectively working. Prototype cost was approximately 280 USD. The WOCA demonstrates to be a locally producible NPWT device that can safely generate a stable vacuum. Future research will include clinical trials situated in LMICs.

This systematic review explores machine learning (ML) applications in surgical motion analysis using non-optical motion tracking systems (NOMTS), alone or with optical methods. It investigates objectives, experimental designs, model effectiveness, and future research directions. From 3632 records, 84 studies were included, with Artificial Neural Networks (38%) and Support Vector Machines (11%) being the most common ML models. Skill assessment was the primary objective (38%). NOMTS used included internal device kinematics (56%), electromagnetic (17%), inertial (15%), mechanical (11%), and electromyography (1%) sensors. Surgical settings were robotic (60%), laparoscopic (18%), open (16%), and others (6%). Procedures focused on bench-top tasks (67%), clinical models (17%), clinical simulations (9%), and non-clinical simulations (7%). Over 90% accuracy was achieved in 36% of studies. Literature shows NOMTS and ML can enhance surgical precision, assessment, and training. Future research should advance ML in surgical environments, ensure model interpretability and reproducibility, and use larger datasets for accurate evaluation.

Laparoscopic surgery offers significant benefits to patients in low-resource settings compared to open surgery such as faster recovery, less pain, and lower infection rate. However, there exist significant barriers to the safe introduction of laparoscopy such as high costs and limited availability of trained staff. Low- and middle-income country (LMIC) hospitals suffer from higher post-surgical infection which might be due to the limited facilities for the sterile reprocessing of laparoscopic instruments. To design a solution to this issue, a detailed understanding of local settings was needed. Therefore, this research applied a context-driven design approach, based on the Roadmap for Design of Surgical Equipment for Safe Surgery Worldwide. Over several design phases, the need for a reprocessing device was established. An analysis of the sterile reprocessing of laparoscopic instruments led to a list of context-specific design requirements. These were translated to a final conceptual design of a laparoscopic instrument cleaner using a waterfall design method. Finally, a usability study of the loading system of the device was conducted with nurses in four Indian hospitals. A root-cause analysis of the usability study showed that the device was not intuitive enough to use for Indian nurses. A redesign of the loading system was made to improve its ease of use. The design process used in this study can be used as an example for designers wanting to address the critical issue of context-specific medical devices worldwide, or more specifically, the sterile supply of surgical instruments in resource-constrained environments.

Background: Preoperative planning of patients diagnosed with pancreatic head cancer is difficult and requires specific expertise. This pilot study assesses the added value of three-dimensional (3D) patient models and computer-aided detection (CAD) algorithms in determining the resectability of pancreatic head tumors. Methods: This study included 14 hepatopancreatobiliary experts from eight hospitals. The participants assessed three radiologically resectable and three radiologically borderline resectable cases in a simulated setting via crossover design. Groups were divided in controls (using a CT scan), a 3D group (using a CT scan and 3D models), and a CAD group (using a CT scan, 3D and CAD). For the perceived fulfillment of preoperative needs, the quality and confidence of clinical decision-making were evaluated. Results: A higher perceived ability to determine degrees and the length of tumor–vessel contact was reported in the CAD group compared to controls (p = 0.022 and p = 0.003, respectively). Lower degrees of tumor–vessel contact were predicted for radiologically borderline resectable tumors in the CAD group compared to controls (p = 0.037). Higher confidence levels were observed in predicting the need for vascular resection in the 3D group compared to controls (p = 0.033) for all cases combined. Conclusions: “CAD (including 3D) improved experts’ perceived ability to accurately assess vessel involvement and supports the development of evolving techniques that may enhance the diagnosis and treatment of pancreatic cancer”.

Since the introduction of robot-assisted laparoscopic surgery, efforts have been made to incorporate force sensing technologies to monitor critical components and to provide force feedback. The advanced laparoscopic robotic system (AdLap RS) is a robotic platform that aims to make robot technology more sustainable through the use of the fully reusable shaft-actuated tip-articulating (SATA) instruments. The SATA instrument driver features electronics and sensors exposed to the sterile environment, which complicate the sterilisation process. The aim of this study was to develop and validate smart sensing in stepper motors using the back electromotive force in a newly developed Smart SATA Driver (SSD), eliminating the need for sensors in the sterile environment. Methods: The stepper drivers were equipped with TMC2209 ICs featuring StallGuard technology to measure back EMF. The tip was actuated up until a set StallGuard threshold value was reached, at which the resulting tip force was measured. This cycle was repeated ten times for a range of threshold levels. A regression analysis with a power series model was used to determine the quality of the fit. Results: The SSD is capable of exerting tip forces between 2.4 and 8.2 N. The back EMF force test demonstrated a strong correlation between obtained StallGuard values and measured tip forces. The regression analysis showed an R-squared of 0.95 and a root Mean squared error of 0.4 N. Discussion: The back EMF force test shows promise for force feedback, but its accuracy limits real-time use due to back EMF fluctuations. Future improvements in motor stability and refining the back EMF model are needed to enable real-time feedback. Conclusion: The strong correlation during the back EMF force test shows its potential as a low-budget method for detecting motor stalls and estimating tool–tissue forces without the need for sensors in laparoscopic instruments.

Peripheral autonomic nerve function (ANF) impairment (ANFI) can be one of the first indicators for leprosy or leprosy neuropathy. However, within leprosy, hardly any ANF assessment methods are used in current practice. Skin temperature could be a proxy measure to assess ANF. Therefore, this research aims to explore whether low-cost infrared (IR) video thermography can be used as an ANF assessment tool by measuring the skin temperature response (STR) of human hands before, and after applying a cold pressor test (CPT). A protocol was defined to perform a baseline measurement, apply CPT, and record the resulting STR curve during 15 minutes. An IR video camera connected to a mobile phone was selected as sensor. A setup was developed to immobilize the position of the hands and fingers relative to the camera. A Python script was developed to extract the hand palm skin temperature STR curve from an IR video for 12 ulnar and median innervated regions of interest (ROI) in 1s intervals. A Matlab script was developed to post-process the raw temperature data into filtered data. This data is used to calculate key metrics that describe the STR curve. This approach was evaluated on technical accuracy and precision by comparing IR data for 3 cameras to a reference sensor. The variability caused by the observer analyzing the data was studied by analyzing the same video 5 times by 2 observers. The subject variability was studied by enrolling 7 subjects into a pilot, testing them daily for 5 consecutive days. The results show a high mean Interclass correlation of 0.94 between the 3 IR cameras and the reference sensor. Bland-Altman plots show a mean accuracy of +0.090°C between the cameras and the reference, and a variation between −1.30 and +1.50°C. High agreement was shown between observers analyzing the data. The pilot test showed high variability in STR curve within subjects. Although the general shape of the STR was similar, the location of the steep increase in recovery varied strongly within and between subjects. This study shows that a low-cost, portable IR camera can be used to measure STR of human hands after CPT. A pilot study showed high subject variability for repeated testing of the STR curve. Future research is needed to establish its value in assessing ANF in leprosy patients or other systemic and local neuropathies and traumatic nerve conditions.

Background: Laparoscopic surgery requires a complex set of motor skills. Currently, basic laparoscopic skills training is performed in a static environment, while intraoperatively, abdominal tissue is often moving. The aim of this study was to develop a dynamic training platform and evaluate its impact on laparoscopic skills acquisition in a box trainer. Methods: The Dynamic Laparoscopic Platform (DyLaP) includes a moving base which has been intergrated with the Lapron box trainer and the ForceSense objective measurement system. Dynamic training was evaluated in a comparative study where novices were divided into a static and dynamic training group, performing six training trials of a peg transfer task with the DyLaP. Afterwards, both groups performed a dynamic exam task. Task manipulation (force) and instrument efficiency (path length and time) were measured. Results: Participants (n = 12) exhibited a significant difference (p < 0.05) in time, path length, and maximum force between the static and dynamic groups in the first trial. Learning curves were most prevalent in the dynamic group. Conclusions: The DyLaP can be used to provide a challenging and realistic training environment. From the comparative peg transfer study, it can be concluded that dynamic training significantly affects laparoscopic skill acquisition. More research is needed to evaluate dynamic training effects in force-based training tasks.

Endovascular intervention is a minimally invasive method for treating cardiovascular diseases. Although fluoroscopy, known for real-time catheter visualization, is commonly used, it exposes patients and physicians to ionizing radiation and lacks depth perception due to its 2D nature. To address these limitations, a study was conducted using teleoperation and 3D visualization techniques. This in-vitro study involved the use of a robotic catheter system and aimed to evaluate user performance through both subjective and objective measures. The focus was on determining the most effective modes of interaction. Three interactive modes for guiding robotic catheters were compared in the study: 1) Mode GM, using a gamepad for control and a standard 2D monitor for visual feedback; 2) Mode GH, with a gamepad for control and HoloLens providing 3D visualization; and 3) Mode HH, where HoloLens serves as both control input and visualization device. Mode GH outperformed other modalities in subjective metrics, except for mental demand. It exhibited a median tracking error of 4.72 mm, a median targeting error of 1.01 mm, a median duration of 82.34 s, and a median natural logarithm of dimensionless squared jerk of 40.38 in the in-vitro study. Mode GH showed 8.5%, 4.7%, 6.5%, and 3.9% improvements over Mode GM and 1.5%, 33.6%, 34.9%, and 8.1% over Mode HH for tracking error, targeting error, duration, and dimensionless squared jerk, respectively. To sum up, the user study emphasizes the potential benefits of employing HoloLens for enhanced 3D visualization in catheterization. The user study also illustrates the advantages of using a gamepad for catheter teleoperation, including user-friendliness and passive haptic feedback, compared to HoloLens. To further gauge the potential of using a more traditional joystick as a control input device, an additional study utilizing the Haption Virtuose robot was conducted. It reveals the potential for achieving smoother trajectories, with a 38.9% reduction in total path length compared to a gamepad, potentially due to its larger range of motion and single-handed control.

Objective: Detecting the cancerous growth margin and achieving a negative margin is one of the challenges that surgeons face during cancer procedures. A smart electrosurgical knife with integrated optical fibers has been designed previously to enable real-time use of diffuse reflectance spectroscopy for intraoperative margin assessment. In this paper, the thermal effect of the electrosurgical knife on tissue sensing is investigated. Methods: Porcine tissues and phantoms were used to investigate the performance of the smart electrosurgical knife after electrosurgery. The fat-to-water content ratio (F/W-ratio) served as the discriminative parameter for distinguishing tissues and tissue mimicking phantoms with varying fat content. The F/W-ratio of tissues and phantoms was measured with the smart electrosurgical knife before and after 14 minutes of electrosurgery. Additionally, a layered porcine tissue and phantom were sliced and measured from top to bottom with the smart electrosurgical knife. Results: Mapping the thermal activity of the electrosurgical knife's electrode during animal tissue electrosurgery revealed temperatures exceeding 400 °C. Electrosurgery for 14 minutes had no impact on the device's accurate detection of the F/W-ratio. The smart electrosurgical knife enables real-time tissue detection and predicts the fat content of the next layer from 4 mm ahead. Conclusion: The design of the smart electrosurgical knife outlined in this paper demonstrates its potential utility for tissue detection during electrosurgery. Significance: In the future, the smart electrosurgical knife could be a valuable intraoperative margin assessment tool, aiding surgeons in detecting tumor borders and achieving negative margins.

Objective: Hemodialysis patients usually receive an arteriovenous fistula (AVF) in the arm as vascular access conduit to allow dialysis 2-3 times a week. This AVF introduces the high flow necessary for dialysis, but over time the ever-present supraphysiological flow is the leading cause of complications. This study aims to develop an implantable device able to non-invasively remove the high flow outside dialysis sessions. Methods: The developed prototype features a magnetic ring allowing external coupling and torque transmission to non-invasively control an AVF valve. Mock-up devices were implanted into arm and sheep cadavers to test sizes and locations. The transmission torque, output force, and valve closure are measured for different representative skin thicknesses. Results: The prototype was placed successfully into arm and sheep cadavers. In the prototype, a maximum output force of 78.9 ± 4.2 N, 46.7 ± 1.9 N, 25.6 ± 0.7 N, 13.5 ± 0.6 N and 6.3 ± 0.4 N could be achieved non-invasively through skin thicknesses of 1-5 mm respectively. The fistula was fully collapsible in every measurement through skin thickness up to the required 4 mm. Conclusion: The prototype satisfies the design requirements. It is fully implantable and allows closure and control of an AVF through non-invasive torque transmission. In vivo studies are pivotal in assessing functionality and understanding systemic effects. Significance: A method is introduced to transfer large amounts of energy to a medical implant for actuation of a mechanical valve trough a closed surface. This system allows non-invasive control of an AVF to reduce complications related to the permanent high flow in conventional AVFs.

While articulated surgical instruments have enabled the proliferation of minimally invasive interventions, procedures such as laparo-endoscopic single-site surgery are waning in popularity. One potential reason for this decline is a lack of sufficiently dexterous instruments. Although multi-steerable instruments exist, these are often complex and therefore expensive assemblies. Even when 3D printing was used to simplify the design of these instruments, the requirement for high-performance 3D printers limited the reduction in manufacturing costs. To tackle this issue, we propose six guidelines for converting a 3D printed compliant medical instrument from printing on a Digital Light Processing (DLP) printer to a Fused Filament Fabrication (FFF) printer. These guidelines provide a framework to manage and compensate for differences in the two processes to achieve comparable results at a reduced cost. The proposed guidelines were evaluated by assembling a FFF 3D printed prototype that shows equivalent performance to its DLP 3D printed counterpart.

Annually, over 300 million surgeries occur globally, requiring numerous surgical instruments. However, many instruments on the tray are returned to the central sterile supply department (CSSD) unused, creating an unsustainable pattern of unnecessary consumption. To address this, we developed a method for optimising surgical instrument trays (SITs) that is straightforward to implement in other hospitals. This optimisation aims to enhance patient safety and sustainability and to improve working conditions and reduce costs. We identified actual instrument usage (IU) in the operating room (OR) and obtained expert recommendations (ERs). Data from both methods were combined in a computer model (CM) to adjust the SITs. The performance of the adjusted SITs was assessed over a year. IU of three different SITs was collected during 16 procedures (mean = 28.4%, SD = 6.4%). Combining IU and ERs resulted in a 36.7% reduction in instruments and a 31.3% weight reduction. These measures contribute to reducing the carbon footprint and enhancing sustainability. During the evaluation of the new SIT contents (n = 7 procedures), mean IU increased from 28.4% (SD = 6.4%) to 46.5% (SD = 11.0%), with no missing instruments during surgery. A one-year follow-up showed no need for further alterations. Combining both methods yields better results than using them individually, efficiently reducing unnecessary items in SITs without compromising patient safety.

Our research highlights the potential of Diffuse Reflectance Spectroscopy (DRS) in detecting cortical breaches during pedicle screw placement. We propose a sideways-looking fiber-optic probe, integrating diffuse light emission with both forward and sideways light collection. Experiments on an optical tissue phantom validate the probe’s potential to distinguish bone tissues and provide real-time guidance for spine surgery. Our findings prove that DRS with diffuse emission can detect perpendicular breaches, and demonstrate how the integration of a 45^◦ slanted fiber coated with gold enables parallel breach detection, advancing spine surgery by allowing for accurate pedicle screw placement.

Introduction: Most robotic instruments and their drives still risk residual contamination due to cleaning complexities, rendering them limited reusable, and tend to have larger instruments than the 5mm laparoscopic standard. The novel steerable laparoscopic SATA-LRS uses modularity for cleanability and exchangeability. The SATA-Drive: a robotic driver designed for the actuation of a 3mm scaled version of the SATA-LRS is presented. Methods: A modular, expandable gear mechanism was designed to efficiently rotate and translate the instrument shafts. The 3mm SATA-LRS is controlled as proof. An user-experiment is conducted to test the (de)coupling of the instrument to and from the drive. Results: A video shows the SATA-Driver successfully articulating, rotating and grasping the end-effector. End-effector dis- and reassembly is possible in 36 (13 SD) seconds, while complete instrument coupling requires 28(8 SD) seconds and de-coupling requires 16 (7 SD) seconds. Discussion: A non-surgical robot arm, mounted with the SATA-drive has effectively been transformed into a system similar to robot assisted laparoscopy. The modularity of the drive's segmented build can easily be adapted and could benefit the adoption of future instruments. The SATA-LRS's cleanability features and its end-effector changes without disassembly are expected to benefit medical robotics. The 3mm SATA-LRS shows the instrument's potential for mini-laparoscopy.

Minimally Invasive Procedures (MIPs) emerged as an alternative to more invasive surgical approaches, offering patient benefits such as smaller incisions, less pain, and shorter hospital stay. In one class of MIPs, where natural body lumens or small incisions are used to access deeper anatomical locations, Flexible Surgical and Interventional Robots (FSIRs) such as catheters and endoscopes are widely used. Due to their flexible and compliant nature, FSIRs can be inserted via natural orifices or small incisions, then moved towards hard-to-reach targets to perform interventional tasks. However, existing FSIRs are confronted with challenges in sensing, control, and navigation. These issues stem from the robot's non-linear behavior and the intricate nature of the lumens, where accurately modeling the complex interactions and disturbances proves to be exceptionally difficult. The rapid advances in Machine Learning (ML) have facilitated the widespread adoption of ML techniques in FSIRs. This article provides an overview of these efforts by first introducing a classification of existing ML algorithms, including traditional ML methods and modern Deep Learning (DL) approaches, commonly used in FSIRs. Next, the use of ML algorithms is surveyed per sub-domain, namely for perception, modeling, control, and navigation. Trends, popularity, strengths, and/or limitations of different ML algorithms are analyzed. The different roles that ML plays among tasks are investigated and described. Finally, discussions are conducted on the limitations and the prospects of ML in MIPs.

Endovascular interventions are minimally invasive procedures that utilize the vascular system to access anatomical regions deep within the body. Image-guided assistance provides valuable real-time information about the dynamic state of the vascular environment. However, the reliance on intraoperative 2-D fluoroscopy images limits depth perception, prompting the demand for intraoperative 3-D imaging. Existing image registration methods face difficulties in accurately incorporating tissue deformations compared to the preoperative 3-D model, particularly in a weakly supervised manner. Additionally, reconstructing deformations from 2-D to 3-D space and presenting this intraoperative model visually to clinicians poses further complexities. To address these challenges, this study introduces a novel deformable model-to-image registration framework using deep learning. Furthermore, this research proposes a visualization method through augmented reality to guide endovascular interventions. This study utilized image data collected from nine patients who underwent transcatheter aortic valve implantation (TAVI) procedures. The registration results in 2-D indicate that the proposed deformable model-to-image registration framework achieves a modified dice similarity coefficient (MDSC) value of 0.89±0.02 and a penalization of deformations in spare space (PDSS) value of 0.04±0.01, offering an improvement of 3.5%-98.6% over the state-of-the-art image registration approach. Additionally, the accuracy of registration in 3-D was evaluated using a dataset obtained from an intervention simulator, resulting in a mean absolute error (MAE) of 1.51±1.02 mm within the region of interest. Overall, the study validates the feasibility and accuracy of the proposed weakly supervised deformable model-to-image registration framework, demonstrating its potential to provide intraoperative 3-D imaging as intervention assistance in dynamic vascular environments.

Purpose. Patient-tailored intracavitary/interstitial (IC/IS) brachytherapy (BT) applicators may increase dose conformity in cervical cancer patients. Current configuration planning methods in these custom applicators rely on manual specification or a small set of (straight) needles. This work introduces and validates a two-stage approach for establishing channel configurations in the 3D printed patient-tailored ARCHITECT applicator. Methods. For each patient, the patient-tailored applicator shape was based on the first BT application with a commercial applicator and integrated connectors to a commercial (Geneva) intrauterine tube and two lunar ring channels. First, a large candidate set was generated of channels that steer the needle to desired poses in the target region and are contained in the applicator. The channels’ centrelines were represented by Bézier curves. Channels running between straight target segments and entry points were optimised and refined to ensure (dynamic) feasibility. Second, channel configurations were selected using geometric coverage optimisation. This workflow was applied to establish patient-tailored geometries for twenty-two patients previously treated using the Venezia applicator. Treatment plans were automatically generated using the in-house developed algorithm BiCycle. Plans for the clinically used configuration, T P clin , and patient-tailored configuration, T P arch , were compared. Results. Channel configurations could be generated in clinically feasible time (median: 2651 s, range 1826-3812 s). All T P arch and T P clin plans were acceptable, but planning aims were more frequently attained with patient-tailored configurations (115/132 versus 100/132 instances). Median CTV_IR D 98 and bladder D 2 c m 3 doses significantly improved ( p < 0.001 and p < 0.01 respectively) in T P arch plans in comparison with T P clin plans, and in approximately half of the patients dosimetric indices improved. Conclusion. Automated patient-tailored BT channel configuration planning for 3D printed applicators is clinically feasible. A treatment planning study showed that all plans met planning limits for the patient-tailored configurations, and in selected cases improved the plan quality in comparison with commercial applicator configurations.