Meningioma recurrence: Time for an online prediction tool?

Background: Meningioma, the most common brain tumor, traditionally considered benign, has a relatively high risk of recurrence over a patient's lifespan. In addition, with the emergence of several clinical, radiological, and molecular variables, it is becoming evident that existing grading criteria, including Simpson's and World Health Organization classification, may not be sufficient or accurate. As web-based tools for widespread accessibility and usage become commonplace, such as those for gene identification or other cancers, it is timely for meningioma care to take advantage of evolving new markers to help advance patient care. Methods: A scoping review of the meningioma literature was undertaken using the MEDLINE and Embase databases. We reviewed original studies and review articles from September 2022 to December 2023 that provided the most updated information on the demographic, clinical, radiographic, histopathological, molecular genetics, and management of meningiomas in the adult population. Results: Our scoping review reveals a large body of meningioma literature that has evaluated the determinants for recurrence and aggressive tumor biology, including older age, female sex, genetic abnormalities such as telomerase reverse transcriptase promoter mutation, CDKN2A deletion, subtotal resection, and higher grade. Despite a large body of evidence on meningiomas, however, we noted a lack of tools to aid the clinician in decision-making. We identified the need for an online, self-updating, and machine-learning-based dynamic model that can incorporate demographic, clinical, radiographic, histopathological, and genetic variables to predict the recurrence risk of meningiomas. Conclusion: Although a challenging endeavor, a recurrence prediction tool for meningioma would provide critical information for the meningioma patient and the clinician making decisions on long-term surveillance and management of meningiomas.

Force Profile as Surgeon-Specific Signature.

Objective: To investigate the notion that a surgeon's force profile can be the signature of their identity and performance. Summary background data: Surgeon performance in the operating room is an understudied topic. The advent of deep learning methods paired with a sensorized surgical device presents an opportunity to incorporate quantitative insight into surgical performance and processes. Using a device called the SmartForceps System and through automated analytics, we have previously reported surgeon force profile, surgical skill, and task classification. However, an investigation of whether an individual surgeon can be identified by surgical technique has yet to be studied. Methods: In this study, we investigate multiple neural network architectures to identify the surgeon associated with their time-series tool-tissue forces using bipolar forceps data. The surgeon associated with each 10-second window of force data was labeled, and the data were randomly split into 80% for model training and validation (10% validation) and 20% for testing. Data imbalance was mitigated through subsampling from more populated classes with a random size adjustment based on 0.1% of sample counts in the respective class. An exploratory analysis of force segments was performed to investigate underlying patterns differentiating individual surgical techniques. Results: In a dataset of 2819 ten-second time segments from 89 neurosurgical cases, the best-performing model achieved a micro-average area under the curve of 0.97, a testing F1-score of 0.82, a sensitivity of 82%, and a precision of 82%. This model was a time-series ResNet model to extract features from the time-series data followed by a linearized output into the XGBoost algorithm. Furthermore, we found that convolutional neural networks outperformed long short-term memory networks in performance and speed. Using a weighted average approach, an ensemble model was able to identify an expert surgeon with 83.8% accuracy using a validation dataset. Conclusions: Our results demonstrate that each surgeon has a unique force profile amenable to identification using deep learning methods. We anticipate our models will enable a quantitative framework to provide bespoke feedback to surgeons and to track their skill progression longitudinally. Furthermore, the ability to recognize individual surgeons introduces the mechanism of correlating outcome to surgeon performance.

Effect of MBF-20 Interlayer on the Microstructure and Corrosion Behaviour of Inconel 625 Super Alloy after Diffusion Brazing.

The joining zone includes three main parts, which comprise an isothermal solidification zone (ISZ), the athermal solidification zone (ASZ), and a diffusion affected zone (DAZ). Field emission scanning electron microscopy (FESEM) was used here to observe the microstructure equipped with ultra-thin window energy dispersive X-ray spectrometer (EDS) system. Additionally, electrochemical impedance spectroscopy (EIS) and cyclic potentiodynamic polarization tests were conducted to evaluate the effect of the DB process on the corrosion resistance of the Inconel 625 superalloy. In the bonding time period, some Mo- and Cr-rich boride precipitations and Ni-rich γ-solid solution phases with hardened alloy elements, such as Mo and Cr, formed in DAZ and ASZ, respectively, because of the inter-diffusion of melting point depressants (MPD). Moreover, during cooling cycles, Ni-Cr-B, Ni-Mo-B, Ni-Si-B, and Ni-Si phase compounds were formed in the ASZ area at 1110-850 °C. The DAZ area developed by borides compound with cubic, needle, and grain boundary morphologies. The corrosion tests indicated that the DB process led to a reduction in the passive region and increased the sensitivity to pitting corrosion.

Tool-tissue force segmentation and pattern recognition for evaluating neurosurgical performance.

Surgical data quantification and comprehension expose subtle patterns in tasks and performance. Enabling surgical devices with artificial intelligence provides surgeons with personalized and objective performance evaluation: a virtual surgical assist. Here we present machine learning models developed for analyzing surgical finesse using tool-tissue interaction force data in surgical dissection obtained from a sensorized bipolar forceps. Data modeling was performed using 50 neurosurgery procedures that involved elective surgical treatment for various intracranial pathologies. The data collection was conducted by 13 surgeons of varying experience levels using sensorized bipolar forceps, SmartForceps System. The machine learning algorithm constituted design and implementation for three primary purposes, i.e., force profile segmentation for obtaining active periods of tool utilization using T-U-Net, surgical skill classification into Expert and Novice, and surgical task recognition into two primary categories of Coagulation versus non-Coagulation using FTFIT deep learning architectures. The final report to surgeon was a dashboard containing recognized segments of force application categorized into skill and task classes along with performance metrics charts compared to expert level surgeons. Operating room data recording of > 161 h containing approximately 3.6 K periods of tool operation was utilized. The modeling resulted in Weighted F1-score = 0.95 and AUC = 0.99 for force profile segmentation using T-U-Net, Weighted F1-score = 0.71 and AUC = 0.81 for surgical skill classification, and Weighted F1-score = 0.82 and AUC = 0.89 for surgical task recognition using a subset of hand-crafted features augmented to FTFIT neural network. This study delivers a novel machine learning module in a cloud, enabling an end-to-end platform for intraoperative surgical performance monitoring and evaluation. Accessed through a secure application for professional connectivity, a paradigm for data-driven learning is established.

Tool-Tissue Forces in Hemangioblastoma Surgery.

OBJECTIVE: Surgical resection of intracranial hemangioblastoma poses technical challenges that may be difficult to impart to trainees. Here, we introduce knowledge of tool-tissue forces in Newton (N), observed during hemangioblastoma surgery. METHODS: Seven surgeons (2 groups: trainees and mentor), with mentor (n = 1) and trainees (n = 6, PGY 1-6 including clinical fellowship), participated in 6 intracranial hemangioblastoma surgeries. Using sensorized bipolar forceps, we evaluated tool-tissue force profiles of 5 predetermined surgical tasks: 1) dissection, 2) coagulation, 3) retracting, 4) pulling, and 5) manipulating. Force profile for each trial included force duration, average, maximum, minimum, range, standard deviation (SD), and correlation coefficient. Force errors including unsuccessful trial bleeding or incomplete were compared between surgeons and with successful trials. RESULTS: Force data from 718 trials were collected. The mean (standard deviation) of force used in all surgical tasks and across all surgical levels was 0.20 ± 0.17 N. The forces exerted by trainee surgeons were significantly lower than those of the mentor (0.15 vs. 0.24; P < 0.0001). A total of 18 (4.5%) trials were unsuccessful, 4 of them being unsuccessful trial-bleeding and the rest, unsuccessful trial-incomplete. The force in unsuccessful trial-bleeding was higher than successful trials (0.3 [0.09] vs. 0.17 [0.11]; P = 0.0401). Toward the end of surgery, higher force was observed (0.17 vs. 0.20; P < 0.0001). CONCLUSIONS: The quantification of tool-tissue forces during hemangioblastoma surgery with feedback to the surgeon, could well enhance surgical training and allow avoidance of bleeding associated with high force error.

Effect of Laser Metal Deposition Parameters on the Characteristics of Stellite 6 Deposited Layers on Precipitation-Hardened Stainless Steel.

Laser metal deposition (LMD) is one of the manufacturing processes in the industries, which is used to enhance the properties of components besides producing and repairing important engineering components. In this study, Stellite 6 was deposited on precipitation-hardened martensitic stainless steel (17-4 PH) by using the LMD process, which employed a pulsed Nd:YAG laser. To realize a favor deposited sample, the effects of three LMD parameters (focal length, scanning speed, and frequency) were investigated, as well as microstructure studies and the results of a microhardness test. Some cracks were observed in the deposited layers with a low scanning speed, which were eliminated by an augment of the scanning speed. Furthermore, some defects were found in the deposited layers with a high scanning speed and a low frequency, which can be related to the insufficient laser energy density and a low overlapping factor. Moreover, various morphologies were observed within the microstructure of the samples, which can be attributed to the differences in the stability criterion and cooling rate across the layer. In the long run, a defect-free sample (S-120-5.5-25) possessing suitable geometrical attributes (wetting angle of 57° and dilution of 25.1%) and a better microhardness property at the surface (≈335 Hv) has been introduced as a desirable LMDed sample.

A data-driven performance dashboard for surgical dissection.

Surgical error and resulting complication have significant patient and economic consequences. Inappropriate exertion of tool-tissue force is a common variable for such error, that can be objectively monitored by sensorized tools. The rich digital output establishes a powerful skill assessment and sharing platform for surgical performance and training. Here we present SmartForceps data app incorporating an Expert Room environment for tracking and analysing the objective performance and surgical finesse through multiple interfaces specific for surgeons and data scientists. The app is enriched by incoming geospatial information, data distribution for engineered features, performance dashboard compared to expert surgeon, and interactive skill prediction and task recognition tools to develop artificial intelligence models. The study launches the concept of democratizing surgical data through a connectivity interface between surgeons with a broad and deep capability of geographic reach through mobile devices with highly interactive infographics and tools for performance monitoring, comparison, and improvement.

Mechanical Property Improvement in Dissimilar Friction Stir Welded Al5083/Al6061 Joints: Effects of Post-Weld Heat Treatment and Abnormal Grain Growth.

The 5083 and 6061(T6) aluminum (Al) alloys are widely used in transportation industries and the development of structural designs because of their high toughness and high corrosion resistance. Friction stir welding (FSW) was performed to produce the dissimilar welded joint of Al5083-Al 6061(T6) under different welding parameters. However, softening behavior occurred in the friction stir welded (FSWed) samples because of grain coarsening or the dissolution of precipitation-hardening phases in the welding zone. Consequently, this research intended to investigate the effect of the post-weld heat treatment (PWHT) method on the mechanical property improvement of the dissimilar FSWed Al5083-Al6061(T6) and governing abnormal grain growth (AGG) through different welding parameters. The results showed PWHT enhanced the mechanical properties of dissimilar joints of Al5083-Al6061(T6). AGG was obtained in the microstructure of PWHTed joints, but appropriate PWHT could recover the dissolved precipitation-hardening particle in the heat-affected zone of the as-welded joint. Further, the tensile strength of the dissimilar joint increased from 181 MPa in the as-welded joint to 270 MPa in the PWHTed joint, showing 93% welding efficacy.

Data analytics interrogates robotic surgical performance using a microsurgery-specific haptic device.

OBJECTIVES: With the increase in robot-assisted cases, recording the quantifiable dexterity of surgeons is essential for proficiency evaluations. The present study employs sensor-based kinematics and recorded surgeon experience for evaluating a new haptic device. METHODS: Thirty surgeons performed a task simulating micromanipulation with neuroArmPLUSHD and two commercially available hand-controllers. The surgical performance was evaluated based on subjective measures obtained from survey and objective features derived from the sensors. Statistical analyses were performed to assess the hand-controllers and regression analysis was used to identify the key features and develop a machine learning model for surgical skill assessment. FINDINGS: MANCOVA tests on objective features demonstrated significance (α = 0.05) for time (p = 0.02), errors (p = 0.01), distance (p = 0.03), clutch incidents (p = 0.03), and forces (p = 0.00). The majority of metrics were in favor of neuroArmPLUSHD. The surgeons found it smoother, more comfortable, less tiring, and easier to maneuver with more realistic force feedback. The ensemble machine learning model trained with 5-fold cross-validation showed an accuracy (SD) of 0.78 (0.15) in surgeon skill classification. CONCLUSIONS: This study validates the importance of incorporating a superior haptic device in telerobotic surgery for standardization of surgical education and patient care.

Automated differentiation of benign renal oncocytoma and chromophobe renal cell carcinoma on computed tomography using deep learning.

OBJECTIVES: To develop and evaluate the feasibility of an objective method using artificial intelligence (AI) and image processing in a semi-automated fashion for tumour-to-cortex peak early-phase enhancement ratio (PEER) in order to differentiate CD117(+) oncocytoma from the chromophobe subtype of renal cell carcinoma (ChRCC) using convolutional neural networks (CNNs) on computed tomography imaging. METHODS: The CNN was trained and validated to identify the kidney + tumour areas in images from 192 patients. The tumour type was differentiated through automated measurement of PEER after manual segmentation of tumours. The performance of this diagnostic model was compared with that of manual expert identification and tumour pathology with regard to accuracy, sensitivity and specificity, along with the root-mean-square error (RMSE), for the remaining 20 patients with CD117(+) oncocytoma or ChRCC. RESULTS: The mean ± sd Dice similarity score for segmentation was 0.66 ± 0.14 for the CNN model to identify the kidney + tumour areas. PEER evaluation achieved accuracy of 95% in tumour type classification (100% sensitivity and 89% specificity) compared with the final pathology results (RMSE of 0.15 for PEER ratio). CONCLUSIONS: We have shown that deep learning could help to produce reliable discrimination of CD117(+) benign oncocytoma and malignant ChRCC through PEER measurements obtained by computer vision.

Synthesis, Characterization, and Antibacterial Activity of Ag2O-Loaded Polyethylene Terephthalate Fabric via Ultrasonic Method.

In this study, Ag2O was synthesized on polyethylene terephthalate fabrics by using an ultrasonic technique with Ag ion reduction in an aqueous solution. The effects of pH on the microstructure and antibacterial properties of the fabrics were evaluated. X-ray diffraction confirmed the presence of Ag2O on the fabrics. The fabrics were characterized by Fourier transform infrared spectroscopy, ultraviolet⁻visible spectroscopy, and wettability testing. Field-emission scanning electron microscopy verified that the change of pH altered the microstructure of the materials. Moreover, the antibacterial activity of the fabrics against Escherichia coli was related to the morphology of Ag2O particles. Thus, the surface structure of Ag2O particles may be a key factor of the antibacterial activity.

Evaluation of a Virtual Reality Percutaneous Nephrolithotomy (PCNL) Surgical Simulator.

Percutaneous Nephrolithotomy is the standard surgical procedure used to remove large kidney stones. PCNL procedures have a steep learning curve; a physician needs to complete between 36 and 60 procedures, to achieve clinical proficiency. Marion Surgical K181 is a virtual reality surgical simulator, which emulates the PCNL procedures without compromising the well-being of patients. The simulator uses a VR headset to place a user in a realistic and immersive operating theater, and haptic force-feedback robots to render physical interactions between surgical tools and the virtual patient. The simulator has two modules for two different aspects of PCNL kidney stone removal procedure: kidney access module where the user must insert a needle into the kidney of the patient, and a kidney stone removal module where the user removes the individual stones from the organ. In this paper, we present user trials to validate the face and construct validity of the simulator. The results, based on the data gathered from 4 groups of users independently, indicate that Marion's surgical simulator is a useful tool for teaching and practicing PCNL procedures. The kidney stone removal module of the simulator has proven construct validity by identifying the skill level of different users based on their tool path. We plan to continue evaluating the simulator with a larger sample of users to reinforce our findings.

A computer vision technique for automated assessment of surgical performance using surgeons' console-feed videos.

PURPOSE: To develop and validate an automated assessment of surgical performance (AASP) system for objective and computerized assessment of pelvic lymph node dissection (PLND) as an integral part of robot-assisted radical cystectomy (RARC) using console-feed videos recorded during live surgery. METHODS: Video recordings of 20 PLNDs were included. The quality of lymph node clearance was assessed based on the features derived from the computer vision process which include: the number and cleared area of the vessels/nerve (N-Vs); image median color map; and mean entropy (measures the level of disorganization) in the video frame. The automated scores were compared to the validated pelvic lymphadenectomy appropriateness and completion evaluation (PLACE) scoring rated by a panel of expert surgeons. Logistic regression analysis was employed to compare automated scores versus PLACE scores. RESULTS: Fourteen procedures were used to develop the AASP algorithm. A logistic regression model was trained and validated using the aforementioned features with 30% holdout cross-validation. The model was tested on the remaining six procedures, and the accuracy of predicting the expert-based PLACE scores was 83.3%. CONCLUSIONS: To our knowledge, this is the first automated surgical skill assessment tool that provides an objective evaluation of surgical performance with high accuracy compared to expert surgeons' assessment that can be extended to any endoscopic or robotic video-enabled surgical procedure.

A machine learning approach to detect changes in gait parameters following a fatiguing occupational task.

The purpose of this study is to provide a method for classifying non-fatigued vs. fatigued states following manual material handling. A method of template matching pattern recognition for feature extraction ($1 Recognizer) along with the support vector machine model for classification were applied on the kinematics of gait cycles segmented by our stepwise search-based segmentation algorithm. A single inertial measurement unit on the ankle was used, providing a minimally intrusive and inexpensive tool for monitoring. The classifier distinguished between states using distance-based scores from the recogniser and the step duration. The results of fatigue detection showed an accuracy of 90% across data from 20 recruited subjects. This method utilises the minimum amount of data and features from only one low-cost sensor to reliably classify the state of fatigue induced by a realistic manufacturing task using a simple machine learning algorithm that can be extended to real-time fatigue monitoring as a future technology to be employed in the manufacturing facilities. Practitioner Summary: We examined the use of a wearable sensor for the detection of fatigue-related changes in gait based on a simulated manual material handling task. Classification based on foot acceleration and position trajectories resulted in 90% accuracy. This method provides a practical framework for predicting realistic levels of fatigue.