Surgical Tools Research Articles

Decoding surgical skill: an objective and efficient algorithm for surgical skill classification based on surgical gesture features -experimental studies.

Various surgical skills lead to differences in patient outcomes and identifying poorly skilled surgeons with constructive feedback contributes to surgical quality improvement. The aim of the study was to develop an algorithm for evaluating surgical skills in laparoscopic cholecystectomy based on the features of elementary functional surgical gestures (Surgestures). Seventy-five laparoscopic cholecystectomy videos were collected from 33 surgeons in five hospitals. The phase of mobilization hepatocystic triangle and gallbladder dissection from the liver bed of each video were annotated with 14 Surgestures. The videos were grouped into competent and incompetent based on the quantiles of modified global operative assessment of laparoscopic skills (mGOALS). Surgeon-related information, clinical data, and intraoperative events were analyzed. Sixty-three Surgesture features were extracted to develop the surgical skill classification algorithm. The area under the receiver operating characteristic curve of the classification and the top features were evaluated. Correlation analysis revealed that most perioperative factors had no significant correlation with mGOALS scores. The incompetent group has a higher probability of cholecystic vascular injury compared to the competent group (30.8 vs 6.1%, P =0.004). The competent group demonstrated fewer inefficient Surgestures, lower shift frequency, and a larger dissection-exposure ratio of Surgestures during the procedure. The area under the receiver operating characteristic curve of the classification algorithm achieved 0.866. Different Surgesture features contributed variably to overall performance and specific skill items. The computer algorithm accurately classified surgeons with different skill levels using objective Surgesture features, adding insight into designing automatic laparoscopic surgical skill assessment tools with technical feedback.

A comprehensive review of haptic feedback in minimally invasive robotic liver surgery: Advancements and challenges

AbstractBackgroundLiver medical procedures are considered one of the most challenging because of the liver's complex geometry, heterogeneity, mechanical properties, and movement due to respiration. Haptic features integrated into needle insertion systems and other medical devices could support physicians but are uncommon. Additional training time and safety concerns make it difficult to implement in robot‐assisted surgery. The main challenges of any haptic device in a teleoperated system are the stability and transparency levels required to develop a safe and efficient system that suits the physician's needs.PurposeThe objective of the review article is to investigate whether haptic‐based teleoperation potentially improves the efficiency and safety of liver needle insertion procedures compared with insertion without haptic feedback. In addition, it looks into haptic technology that can be integrated into simulators to train novice physicians in liver procedures.MethodsThis review presents the physician's needs during liver interventions and the consequent requirements of haptic features to help the physician. This paper provides an overview of the different aspects of a teleoperation system in various applications, especially in the medical field. It finally presents the state‐of‐the‐art haptic technology in robot‐assisted procedures for the liver. This includes 3D virtual models of the liver and force measurement techniques used in haptic rendering to estimate the real‐time position of the surgical instrument relative to the liver.ResultsHaptic feedback technology can be used to navigate the surgical tool through the desired trajectory to reach the target accurately and avoid critical regions. It also helps distinguish between various textures of liver tissue.ConclusionHaptic feedback can complement the physician's experience to compensate for the lack of real‐time imaging during Computed Tomography guided (CT‐guided) liver procedures. Consequently, it helps the physician mitigate the destruction of healthy tissues and takes less time to reach the target.

Cemented or uncemented fixation: Which allows a more acceptable prosthetic femoral version in total hip arthroplasty?

BackgroundThree-dimensional computed-tomography (3D-CT) planning for primary Total Hip Arthroplasty (THA) typically uses the external femoral surface; as a result, it is difficult to predict the prosthetic femoral version (PFV) for uncemented femoral stems that press-fit to the internal surface of the bone. Cemented fixation allows the surgeon to adjust the version independent of the internal femoral anatomy. We aimed to better understand the effect of the fixation type on PFV.MethodsThis was a case series study including a total of 95 consecutive patients (106 hips), who underwent uncemented (n = 81 hips) and cemented (n = 25 hips) primary THA using the posterior approach. The surgeon aimed for a PFV of 20°. Our primary objective was to compare PFV in both groups; our secondary objective was to evaluate the clinical outcomes.ResultsThe mean (± SD) PFV was 13° (± 9°) and 23° (± 8°) for the uncemented and cemented THA groups (P < 0.001), respectively. In the uncemented THA group, 36% of the patients had a PFV of < 10°. In the cemented THA group, this clinically important threshold dropped to 8%. Similarly, the Bland–Altman (BA) plots showed wider 95% limits of agreement for the uncemented group. Satisfactory clinical outcomes were recorded.ConclusionWe found that the PFV was more clinically acceptable, for the posterior surgical approach, in the cemented group when compared to the uncemented group. Both THA groups reported high variability indicating the need to develop surgical tools to guide the PFV closer to the surgical target.

Real-time surgical tool detection with multi-scale positional encoding and contrastive learning.

Real-time detection of surgical tools in laparoscopic data plays a vital role in understanding surgical procedures, evaluating the performance of trainees, facilitating learning, and ultimately supporting the autonomy of robotic systems. Existing detection methods for surgical data need to improve processing speed and high prediction accuracy. Most methods rely on anchors or region proposals, limiting their adaptability to variations in tool appearance and leading to sub-optimal detection results. Moreover, using non-anchor-based detectors to alleviate this problem has been partially explored without remarkable results. An anchor-free architecture based on a transformer that allows real-time tool detection is introduced. The proposal is to utilize multi-scale features within the feature extraction layer and at the transformer-based detection architecture through positional encoding that can refine and capture context-aware and structural information of different-sized tools. Furthermore, a supervised contrastive loss is introduced to optimize representations of object embeddings, resulting in improved feed-forward network performances for classifying localized bounding boxes. The strategy demonstrates superiority to state-of-the-art (SOTA) methods. Compared to the most accurate existing SOTA (DSSS) method, the approach has an improvement of nearly 4% on mAP and a reduction in the inference time by 113%. It also showed a 7% higher mAP than the baselinemodel.

Integrating Virtual Surgical Planning and 3D-Printed Tools with Iliac Bone Grafts for Orbital and Zygomatic Reconstruction in Hemifacial Microsomia Patients.

Hemifacial Microsomia (HFM) is the second most common congenital craniofacial malformation syndrome, and the complexity of HFM makes its treatment challenging. The present study aimed to introduce a new approach of utilization of virtual surgical planning (VSP) and 3D-printed surgical adjuncts for maxillofacial reconstruction. Five HFM patients were included in this study. All participants were provided with a full VSP, including the design of osteotomy lines, the design and fabrication of 3D-printed cutting guides, fixation plates, and titanium mesh for implantation. With the assistance of 3D-printed cutting guides and fixation plates, the orbital deformities were corrected, and a 3D-printed titanium mesh combined with iliac cancellous bone graft was applied to reconstruct the zygomatic arch. The surgical accuracy, effectiveness, and bone absorption rate were evaluated. All patients completed the entirely digital treatment process without experiencing severe complications. The surgical adjuncts were effective in aligning the movement of the bone segments with the surgical plan, resulting in mean 3D deviations (1.0681 ± 0.15 mm) and maximum 3D deviations (3.1127 ± 0.44 mm). The image fusion results showed that the patients' postoperative position of the maxilla, zygoma, and orbital rim was consistent with the virtual surgical plan, with only a slight increase in the area of bone grafting. The postoperative measurements showed significant improvement in the asymmetry indices of Er (AI of Er: from 17.91 ± 3.732 to 5.427 ± 1.389 mm, p = 0.0001) and FZ (AI of FZ: from 7.581 ± 1.435 to 4.070 ± 1.028 mm, p = 0.0009) points. In addition, the observed bone resorption rate at the 6-month follow-up across the five patients was 45.24% ± 3.13%. In conclusion, the application of VSP and 3D-printed surgical adjuncts demonstrates significant value in enhancing the precision and effectiveness of surgical treatments for HFM. A 3D-printed titanium mesh combined with iliac cancellous bone graft can be considered an ideal alternative for the reconstruction of the zygomatic arch.

Managing the OR: Tools, resources and guidelines to effectively manage operative suites

As modern medicine offers novel surgical therapies for conditions simple and complex, the proper resource allocation of operating rooms, surgical staff and supporting services is becoming increasingly important for healthcare organisations. Surgical services are one of the most essential parts of any healthcare system, substantially influencing patient choice of healthcare services. These services are typically the centre for revenue but also impart considerable costs. Given the complexity of surgical schedule planning, expectations of high reliability and demand on resources, many healthcare organisations have resorted to using a static block schedule based on historic utilisation patterns. This is based on the dogma that surgical schedules are not predictable, surgical blocks are stable, and surgical yield has no direct correlation with outpatient schedules. Here we share our two-year experience with a Surgical Predictor Tool using our surgical practice management principles and the cost-effective use of these means to meet the needs of patients and our surgical staff in an integrated community health system.

A quantitative analysis of surgical smoke-derived particulate matter and formaldehyde exposure during spine surgery: a possible occupational hazard.

Since its introduction, electrocautery has served as a valuable surgical tool, enabling precise tissue cutting and effective hemostasis in spine surgery. While there have been numerous efforts to elucidate the possible hazardous effects of surgical smoke in various surgical fields, there has been very little discussion in the context of spine surgery. The objective of this study was to measure and conduct a quantitative analysis of the particulate matter (PM) of different sizes and of formaldehyde (HCHO) generated by smoke during spine surgeries. This study included a consecutive series of patients who underwent 1- or 2-level lumbar spinal fusion surgery between June and November 2021. Particle counts were measured using a particle counter, specifically focusing on six different sizes of PM (0.3, 0.5, 1, 2.5, 5, and 10 µm). Additionally, measurements were taken for HCHO in parts per million (ppm). Monopolar cautery was used in the surgical setting. Systematic measurements were conducted at specific time points during the surgical procedures to assess the levels of PM and HCHO. Furthermore, the efficacy of surgical smoke suction was evaluated by comparing the PM levels with and without adjacent placement of suction. This study involved 35 patients, with measurements of both PM and HCHO taken in 27 cases. The remaining 8 cases had measurements only for PM. In this study, statistically significant quantitative changes in various PM sizes were observed when electrocautery was used during spine surgery (12.3 ± 1.7 vs 1975.7 ± 422.8, 3.4 ± 0.5 vs 250.1 ± 45.7, and 1.9 ± 0.2 vs 78.1 ± 13.3, respectively, for 2.5-, 5-, and 10-µm PM; p < 0.05). The level of HCHO was also significantly higher (0.085 ± 0.006 vs 0.131 ± 0.014 ppm, p < 0.05) with electrocautery use. Utilization of adjacent suction of surgical smoke during electrocautery demonstrated a statistically significant reduction in PM levels. The findings of this study highlight the potential surgical smoke-related hazards that spine surgeons may be exposed to in the operating room. Implementing simple interventions, such as utilizing nearby suction, can effectively minimize the amount of toxic surgical smoke and mitigate these risks.

Development and Evaluation of a Markerless 6 DOF Pose Tracking Method for a Suture Needle from a Robotic Endoscope

Remarkable progress has been made in the field of robot-assisted surgery in recent years, particularly in the area of surgical task automation, though many challenges and opportunities still exist. Among these topics, the detection and tracking of surgical tools play a pivotal role in enabling autonomous systems to plan and execute procedures effectively. For instance, accurate estimation of a needle’s position and posture is essential for surgical systems to grasp the needle and perform suturing tasks autonomously. In this paper, we developed image-based methods for markerless 6 degrees of freedom (DOF) suture needle pose estimation using keypoint detection technique based on Deep Learning and Point-to-point Registration, we also leveraged multi-viewpoint from a robotic endoscope to enhance the accuracy. The data collection and annotation process was automated by utilizing a simulated environment, enabling us to create a dataset with 3446 evenly distributed needle samples across a suturing phantom space for training and to demonstrate more convincing and unbiased performance results. We also investigated the impact of training set size on the keypoint detection accuracy. Our implemented pipeline that takes a single RGB image achieved a median position error of 1.4 mm and a median orientation error of 2.9∘, while our multi-viewpoint method was able to further reduce the random errors.

Intracardiac Three-Dimensional Image as Surgical Decision-Making Tool of Congenital Heart Disease.

This study aimed to evaluate the anatomical reproducibility of a preoperative intracardiac 3D image (IC image) created using computed tomography, and to investigate its usefulness as a surgical decision-making tool. Between 2012 and 2022, ventricular septal defect (VSD) patients, and double outlet right ventricle (DORV) or transposition of the great arteries (TGA) with pulmonary stenosis (PS) patients who underwent cardiac surgery and had preoperative computed tomography were enrolled. SYNAPSE VINCENT® (Fujifilm) was used to create an IC image which was analyzed retrospectively. In 14 VSD patients, the diagnostic consistency rate in the Soto classification with intraoperative findings was 100% (14/14) for IC image versus 64% (9/14) for transthoracic echocardiography (P = 0.04). The defect size showed a higher correlation coefficient with IC image (0.837, P = 0.001) than with transthoracic echocardiography (0.567, P = 0.034). In 11 DORV/TGA with PS patients, the diagnostic consistency rate in the Lev classification was 100% (9/9) for IC image versus 77% (7/9) for transthoracic echocardiography (P = 0.47). The secondary interventricular foramen (SVF)/left ventricular outflow tract (LVOT) ratio by IC image was significantly smaller in the biventricular-repair group (median 0.71, IQR 0.67-1.06) than in the univentricular-repair group (median 1.79, IQR 1.53-2.42) (P = 0.006). An IC image is useful as a surgical decision-making tool for simple VSDs and complex congenital heart diseases such as DORV or TGA with pulmonary stenosis. The SVF/LVOT ratio determined from the IC image may be a useful indicator for avoiding LVOT obstruction.

Development of Bleeding Artificial Intelligence Detector (BLAIR) System for Robotic Radical Prostatectomy

Background: Addressing intraoperative bleeding remains a significant challenge in the field of robotic surgery. This research endeavors to pioneer a groundbreaking solution utilizing convolutional neural networks (CNNs). The objective is to establish a system capable of forecasting instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon about bleeding risks. Methods: To achieve this, a multi-task learning (MTL) CNN was introduced, leveraging a modified version of the U-Net architecture. The aim was to categorize video input as either “absence of blood accumulation” (0) or “presence of blood accumulation” (1). To facilitate seamless interaction with the neural networks, the Bleeding Artificial Intelligence-based Detector (BLAIR) software was created using the Python Keras API and built upon the PyQT framework. A subsequent clinical assessment of BLAIR’s efficacy was performed, comparing its bleeding identification performance against that of a urologist. Various perioperative variables were also gathered. For optimal MTL-CNN training parameterization, a multi-task loss function was adopted to enhance the accuracy of event detection by taking advantage of surgical tools’ semantic segmentation. Additionally, the Multiple Correspondence Analysis (MCA) approach was employed to assess software performance. Results: The MTL-CNN demonstrated a remarkable event recognition accuracy of 90.63%. When evaluating BLAIR’s predictive ability and its capacity to pre-warn surgeons of potential bleeding incidents, the density plot highlighted a striking similarity between BLAIR and human assessments. In fact, BLAIR exhibited a faster response. Notably, the MCA analysis revealed no discernible distinction between the software and human performance in accurately identifying instances of bleeding. Conclusion: The BLAIR software proved its competence by achieving over 90% accuracy in predicting bleeding events during RARP. This accomplishment underscores the potential of AI to assist surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.

Development of a virtual reality-based zygomatic implant surgery training system with global collision detection and optimized finite element method model

Background and objectiveZygomatic implant surgery is challenging due to the complex structure of the zygomatic bone, limited visual range during surgery, and lengthy implant path. Moreover, traditional training methods are costly, and experimental subjects are scarce. MethodsTo overcome these challenges, we propose a novel training system that integrates visual, haptic, and auditory feedback to create a more immersive surgical experience. The system uses dynamic bounding volume hierarchy (BVH) and Symplectic Euler to detect global collisions between surgical tools and models, while an optimized finite element method (FEM) model simulates soft tissue and detects collisions. Compared to previous works, our system achieves global rigid-body collisions between surgical tools and patient models, while also providing stable and realistic simulation and collisions of soft tissues. This advancement offers a more realistic simulation for zygomatic implant surgery. ResultsWe conducted three experiments and evaluations. The first experiment measured the axial force generated during the zygomatic implant simulation process and compared it with actual surgery, demonstrating the realistic force rendering feedback of our system. The second evaluation involved 15 novice surgeons who experienced the system and completed a questionnaire survey focusing on five aspects. The results showed satisfactory evaluations. The third experiment involved six surgeons who underwent in-depth training for two hours daily and were tested on the first, third, and fifth days. We collected data and combined it with the doctors' feedback to prove that our system can improve surgeons' proficiency in zygomatic implant surgery and provide a novel training solution for this procedure. ConclusionWe have innovatively integrated global collision detection and optimized soft tissue simulation into our system. Furthermore, we have conducted experimental validation to demonstrate the effectiveness of this implementation. We present a novel solution for zygomatic implant surgery training.

Knowledge, attitudes, beliefs and practices of the WHO surgical checklist in neurosurgery at a quaternary referral hospital, Durban, South Africa

BackgroundDespite an established WHO surgical safety checklist (SSCL) at the referral hospital in Durban, ‘‘Never Events’’ still occur. Observations suggest that many surgical team members are unaware of SSCL existence, those who knew about it are not convinced that it prevents errors, reduces morbidity and mortality and tend not to use it. ObjectivesThe study aimed to establish the knowledge, attitudes, beliefs and practices regarding the SSCL and its use among the neurosurgical staff at a quaternary referral hospital in Durban, South Africa. MethodsQuestionnaires were distributed to neurosurgical theatre staff at the referral hospital in Durban. Data collected included their awareness, beliefs, attitude and practices regarding the SSCL. Data collected were analysed using R Statistical computing software of the R core Team, 2020. ResultsOf the participants that responded, 97% had knowledge of SSCL, 84% knew where it is, 86% believed that it was easily accessible, 96% knew why and 90% knew when to use it. All agreed that the SSCL is a crucial safety tool. Majority believed that SSCL prevents perioperative adverse events, is not time consuming, is not a useless tool, does not increase the workload and does not make patients anxious. ConclusionResults show that most surgical teams know of WHO SSCL. The negative attitude of staff towards SSCL is a significant factor in most of the studies in deterring effective implementation and use. The majority of the study participants believe the SSCL is an essential surgical safety tool useful in preventing errors, morbidity and mortality.

Minimally Invasive Gastrointestinal Surgery: A Review.

Minimally invasive surgery uses several procedures with fewer side effects (bleeding, infections, etc.), a shorter hospital stay, and less discomfort following minimally invasive surgery. Laparoscopy was one of the first forms of minimally invasive surgery. It involves doing surgery while using tiny cameras through one or more small incisions, surgical tools along with tubes. Robotic surgery is another kind of minimally invasive procedure.Along with supporting accurate, flexible, and regulated surgical procedures, it provides the physician with a three-dimensional, enlarged view of the operative site. Minimally invasive surgery continues to advance, making it an advantage for patients with a variety of illnesses.Nowadays, many surgeons prefer it to traditional surgery, which frequently necessitates a longer hospital stay and requires larger incisions. Since then, numerous surgical specialties have greatly increased their use of minimally invasive surgery. A minimally invasive procedure is preferred for the majority of patients who require gastrointestinal surgery. Minimally invasive gastrointestinal procedures are just as successful as open procedures and, in some situations, may result in more effective outcomes. While recovery from open surgeries frequently takes five to ten days in the hospital, minimally invasive surgeries are less painful for patients and hasten recovery. It is safe from the perspective of the patient and has a lower postoperative mortality rate. This procedure involves a learning curve among surgeons.

CNSC-44. BIOLOGICAL PATTERN DISCOVERY IN GLIOBLASTOMA

Abstract Glioblastoma(GBM - IDH wildtype) is an adult glioma, showing abysmal prognosis. Sequencing technologies show us the existence of a neurodevelopmental frame-work, upon which heterogeneous molecular patterns are overlaid. The tumor's functional capacity is the net result of extrinsic+intrinsic molecular factors interacting with each other. These factors affect how cells communicate and organize themselves into complex functional architectures that support their evolution, survival and resistance. Understanding the phenotypic significance of a tumor's architecture, will allow us to understand these processes and compute complex patterns in GBM that are "biologically-relevant". First, we showed, as a proof-of-concept, that "biologically-relevant" signatures are imprinted within the spatial organization of cells using spatial pixel analysis. We used a phase-contrast image dataset of glioblastoma stem cells grown in culture, imaged 4-12hrly, over 12-16 days. We applied 29 hand-engineered pixel features per image, deriving spatial pixel signatures for each of our 17’601 phase-contrast images. Using different computational analytical methods and gene expression from matched bulk RNA datasets, we showed that spatial pixel patterning follows biologically relevant phenotypes. We found samples of images with high PC2 scores had higher mesenchymal/microglia scores, as compared to samples of images with low PC2 scores, which showed higher neurodevelopmental signatures. In addition, we found that mathematical algorithms describing entropy, homogeneity, contrast and complexity were clearly enriched in specific biological groups. Hence, our study showed that the organizational/architectural patterns of biological entities show preservation of fundamental organizational principles. Building upon the above data (which is currently a manuscript under preparation), we will apply these principles towards pattern discovery of GBM tissues at multiple architectural hierarchies (i.e subcellular, cellular, stroma) using different GBM models, imaging and spatial transcriptomics. If structure equates to function, understanding GBM architecture will have important applications in surgical tool developments and understanding relevant mechanistic patterns in GBM.

The computational design of a fractal-inspired soft robotic

Soft robotics, with their application in biomedical fields like flexible surgical tools and wearable exo-suits, have revolutionized biomedical practices. To adapt to different scales of application scenarios, our research emphasizes fractal-inspired soft robotics, leveraging the unique scalable and reconfigurable properties of fractal structures. This study focuses on the computational design and simulation of these robots. Traditional modeling methods, apt for rigid robotic arms, falter for soft materials due to their extensive flexibility. We introduced a deep learning strategy with physics-informed neural network for accurate soft robot dynamics modeling. Unlike existing networks optimized for rigid systems, our approach integrates elastic beam theory and deformation laws into Lagrangian Dynamics, making it ideal for simulating fractal soft robotic arms. Compared to conventional finite element simulations and learning approaches, our method shows superior effectiveness. We also conducted simple simulation experiments to show that fractal soft arm is potentially suitable for medical procedures (such as dilating passages) and proved that this fractal-designed soft robotic arm exhibits good portability and adaptability to various scenarios, making it a promising candidate for guiding the design of future surgical robots.

Clinical application of 3D printing-assisted patient-specific instrument osteotomy guide in stiff clubfoot: preliminary findings

BackgroundThe orthopedic treatment of the stiff clubfoot is challenging for clinicians, and the purpose of this study was to explore the preliminary findings of 3D printing-assisted patient-specific instrument (PSI) osteotomy guide for use in the orthopedic treatment of the stiff clubfoot.Material and methodsThere were 20 patients (25 feet) with stiff clubfoot admitted from December 2018 to June 2022, including 13 males (16 feet) and 7 females (9 feet), aged 24–52 years, mean 40.15 years; 8 left feet, 7 right feet, 5 bipedal. All patients underwent triple arthrodesis and were divided into 10 cases (12 feet) in the PSI group (n = 12) and 10 cases (13 feet) in the conventional surgery group (n = 13) according to the surgical approach. The duration of surgery and the number of radiation exposures were recorded in all cases, and the American Orthopedic Foot and Ankle Society (AOFAS), and International Congenital Clubfoot Study Group (ICFSG) scoring systems were applied postoperatively to assess the effect of corrective treatment. All measurement data were expressed as mean ± standard deviation, and differences between groups were determined by Student’s t test. All count data between the two groups were compared using the chi-square test or Fisher’s exact test analysis.ResultsAll 20 patients (25 feet) were followed up for 1 year. No major complications related to osteotomy, such as overcorrection, incomplete correction, or bone nonunion, were observed in the PSI and conventional surgery groups at the final follow-up, and the PSI group had the advantage of shorter operative time (P < 0.01), less radiation exposure (P < 0.01), and higher excellent rate compared with the conventional surgery group. The AOFAS score (P > 0.05) and ICFSG score (P > 0.05) at the last follow-up were not statistically significant in both groups, but the excellent rate at the last follow-up was 91.7% in the PSI group which was significantly higher than that of the conventional surgery group at 76.9%.ConclusionsThe utilization of 3D printing-assisted PSI osteotomy guide in orthopedic surgery for stiff clubfoot offers a safe and effective surgical tool for triple joint fusion treatment. This technology simplifies surgical procedures, minimizes intraoperative radiation exposures, reduces surgical time, and enables precise and personalized treatment.

A Deep Learning Approach to Classify Surgical Skill in Microsurgery Using Force Data from a Novel Sensorised Surgical Glove.

Microsurgery serves as the foundation for numerous operative procedures. Given its highly technical nature, the assessment of surgical skill becomes an essential component of clinical practice and microsurgery education. The interaction forces between surgical tools and tissues play a pivotal role in surgical success, making them a valuable indicator of surgical skill. In this study, we employ six distinct deep learning architectures (LSTM, GRU, Bi-LSTM, CLDNN, TCN, Transformer) specifically designed for the classification of surgical skill levels. We use force data obtained from a novel sensorized surgical glove utilized during a microsurgical task. To enhance the performance of our models, we propose six data augmentation techniques. The proposed frameworks are accompanied by a comprehensive analysis, both quantitative and qualitative, including experiments conducted with two cross-validation schemes and interpretable visualizations of the network's decision-making process. Our experimental results show that CLDNN and TCN are the top-performing models, achieving impressive accuracy rates of 96.16% and 97.45%, respectively. This not only underscores the effectiveness of our proposed architectures, but also serves as compelling evidence that the force data obtained through the sensorized surgical glove contains valuable information regarding surgical skill.

LAST: LAtent Space-constrained Transformers for Automatic Surgical Phase Recognition and Tool Presence Detection.

When developing context-aware systems, automatic surgical phase recognition and tool presence detection are two essential tasks. There exist previous attempts to develop methods for both tasks but majority of the existing methods utilize a frame-level loss function (e.g., cross-entropy) which does not fully leverage the underlying semantic structure of a surgery, leading to sub-optimal results. In this paper, we propose multi-task learning-based, LAtent Space-constrained Transformers, referred as LAST, for automatic surgical phase recognition and tool presence detection. Our design features a two-branch transformer architecture with a novel and generic way to leverage video-level semantic information during network training. This is done by learning a non-linear compact presentation of the underlying semantic structure information of surgical videos through a transformer variational autoencoder (VAE) and by encouraging models to follow the learned statistical distributions. In other words, LAST is of structure-aware and favors predictions that lie on the extracted low dimensional data manifold. Validated on two public datasets of the cholecystectomy surgery, i.e., the Cholec80 dataset and the M2cai16 dataset, our method achieves better results than other state-of-the-art methods. Specifically, on the Cholec80 dataset, our method achieves an average accuracy of 93.12±4.71%, an average precision of 89.25±5.49%, an average recall of 90.10±5.45% and an average Jaccard of 81.11 ±7.62% for phase recognition, and an average mAP of 95.15±3.87% for tool presence detection. Similar superior performance is also observed when LAST is applied to the M2cai16 dataset.

Telenursing practice in the care of surgical cancer patients: a scoping review protocol

IntroductionTelenursing is a component of telehealth that occurs when nurses use information and communication technologies to provide care and nursing services remotely. To understand how telenursing services in surgical oncology...

Characteristics and electrochemical properties of Al2O3 thin films on surgical scalpel blades

Surface modification techniques play an important role in shaping the physicochemical properties of surgical tools. The article discusses the problem of the destruction of surgical scalpel blades and the methods of depositing thin films on them.