Bridging 3D Slicer and ROS2 for Image-Guided Robotic Interventions.

Developing image-guided robotic systems requires access to flexible, open-source software. For image guidance, the open-source medical imaging platform 3D Slicer is one of the most adopted tools that can be used for research and prototyping. Similarly, for robotics, the open-source middleware suite robot operating system (ROS) is the standard development framework. In the past, there have been several "ad hoc" attempts made to bridge both tools; however, they are all reliant on middleware and custom interfaces. Additionally, none of these attempts have been successful in bridging access to the full suite of tools provided by ROS or 3D Slicer. Therefore, in this paper, we present the SlicerROS2 module, which was designed for the direct use of ROS2 packages and libraries within 3D Slicer. The module was developed to enable real-time visualization of robots, accommodate different robot configurations, and facilitate data transfer in both directions (between ROS and Slicer). We demonstrate the system on multiple robots with different configurations, evaluate the system performance and discuss an image-guided robotic intervention that can be prototyped with this module. This module can serve as a starting point for clinical system development that reduces the need for custom interfaces and time-intensive platform setup.

Sensor-Based Automated Detection of Electrosurgical Cautery States.

In computer-assisted surgery, it is typically required to detect when the tool comes into contact with the patient. In activated electrosurgery, this is known as the energy event. By continuously tracking the electrosurgical tools' location using a navigation system, energy events can help determine locations of sensor-classified tissues. Our objective was to detect the energy event and determine the settings of electrosurgical cautery-robustly and automatically based on sensor data. This study aims to demonstrate the feasibility of using the cautery state to detect surgical incisions, without disrupting the surgical workflow. We detected current changes in the wires of the cautery device and grounding pad using non-invasive current sensors and an oscilloscope. An open-source software was implemented to apply machine learning on sensor data to detect energy events and cautery settings. Our methods classified each cautery state at an average accuracy of 95.56% across different tissue types and energy level parameters altered by surgeons during an operation. Our results demonstrate the feasibility of automatically identifying energy events during surgical incisions, which could be an important safety feature in robotic and computer-integrated surgery. This study provides a key step towards locating tissue classifications during breast cancer operations and reducing the rate of positive margins.

Real-time electromagnetic navigation for breast-conserving surgery using NaviKnife technology: A matched case-control study.

Breast-conserving surgery (BCS) is a mainstay in breast cancer treatment. For nonpalpable breast cancers, current strategies have limited accuracy, contributing to high positive margin rates. We developed NaviKnife, a surgical navigation system based on real-time electromagnetic (EM) tracking. The goal of this study was to confirm the feasibility of intraoperative EM navigation in patients with nonpalpable breast cancer and to assess the potential value of surgical navigation. We recruited 40 patients with ultrasound visible, single, nonpalpable lesions, undergoing BCS. Feasibility was assessed by equipment functionality and sterility, acceptable duration of the operation, and surgeon feedback. Secondary outcomes included specimen volume, positive margin rate, and reoperation outcomes. Study patients were compared to a control group by a matched case-control analysis. There was no equipment failure or breach of sterility. The median operative time was 66 (44-119) minutes with NaviKnife vs 65 (34-158) minutes for the control (P = .64). NaviKnife contouring time was 3.2 (1.6-9) minutes. Surgeons rated navigation as easy to setup, easy to use, and useful in guiding nonpalpable tumor excision. The mean specimen volume was 95.4 ± 73.5 cm3 with NaviKnife and 140.7 ± 100.3 cm3 for the control (P = .01). The positive margin rate was 22.5% with NaviKnife and 28.7% for the control (P = .52). The re-excision specimen contained residual disease in 14.3% for NaviKnife and 50% for the control (P = .28). Our results demonstrate that real-time EM navigation is feasible in the operating room for BCS. Excisions performed with navigation result in the removal of less breast tissue without compromising postive margin rates.

MR-guided perineural injection of the ganglion impar: technical considerations and feasibility.

OBJECTIVE: Perineural ganglion impar injections are used in the management of pelvic pain syndromes; however, there is no consensus regarding the optimal image guidance. Magnetic resonance imaging (MRI) provides high soft tissue contrast and the potential to directly visualize and target the ganglion. The purpose of this study was to assess the feasibility of MR-guided percutaneous perineural ganglion impar injections. MATERIALS AND METHODS: Six MR-guided ganglion impar injections were performed in six human cadavers. Procedures were performed with a clinical 1.5-Tesla MRI system through a far lateral transgluteus approach. Ganglion impar visibility, distance from the sacrococcygeal joint, number of intermittent MRI control steps required to place the needle, target error between the intended and final needle tip location, inadvertent punctures of non-targeted vulnerable structures, injectant distribution, and procedure time were determined. RESULTS: The ganglion impar was seen on MRI in 4/6 (66 %) of cases and located 0.8 mm cephalad to 16.3 mm caudad (average 1.2 mm caudad) to the midpoint of the sacrococcygeal joint. Needle placement required an average of three MRI control steps (range, 2-6). The average target error was 2.2 ± 2.1 mm. In 6/6 cases (100 %), there was appropriate periganglionic distribution and filling of the presacrococcygeal space. No punctures of non-targeted structures occurred. The median procedure time was 20 min (range, 12-29 min). CONCLUSION: Interventional MRI can visualize and directly target the ganglion impar for accurate needle placement and successful periganglionic injection with the additional benefit of no ionizing radiation exposure to patient and staff. Our results support clinical evaluation.

Computerized training system for ultrasound-guided lumbar puncture on abnormal spine models: a randomized controlled trial.

PURPOSE: A randomized controlled trial was carried out to determine whether Perk Tutor, a computerized training platform that displays an ultrasound image and real-time needle position in a three-dimensional (3D) anatomical model, would benefit residents learning ultrasound-guided lumbar puncture (LP) in simulation phantoms with abnormal spinal anatomy. METHODS: Twenty-four residents were randomly assigned to either the Perk Tutor (P) or the Control (C) group and asked to perform an LP with ultrasound guidance on part-task trainers with spinal pathology. Group P was trained with the 3D display along with conventional ultrasound imaging, while Group C used conventional ultrasound only. Both groups were then tested solely with conventional ultrasound guidance on an abnormal spinal model not previously seen. We measured potential tissue damage, needle path in tissue, total procedure time, and needle insertion time. Procedural success rate was a secondary outcome. RESULTS: The needle tracking measurements (expressed as median [interquartile range; IQR]) in Group P vs Group C revealed less potential tissue damage (39.7 [21.3-42.7] cm(2) vs 128.3 [50.3-208.2] cm(2), respectively; difference 88.6; 95% confidence intervals [CI] 24.8 to 193.5; P = 0.01), a shorter needle path inside the tissue (426.0 [164.9-571.6] mm vs 629.7 [306.4-2,879.1] mm, respectively; difference 223.7; 95% CI 76.3 to 1,859.9; P = 0.02), and lower needle insertion time (30.3 [14.0-51.0] sec vs 59.1 [26.0-136.2] sec, respectively; difference 28.8; 95% CI 2.2 to 134.0; P = 0.05). Total procedure time and overall success rates between groups did not differ. CONCLUSION: Residents trained with augmented reality 3D visualization had better performance metrics on ultrasound-guided LP in pathological spine models.

Assessment of lumbar puncture skill in experts and nonexperts using checklists and quantitative tracking of needle trajectories: implications for competency-based medical education.

UNLABELLED: CONSTRUCT: With the current shift toward competency-based education, rigorous assessment tools are needed for procedurally based tasks. BACKGROUND: Multiple tools exist to evaluate procedural skills, each with specific weaknesses. APPROACH: We sought to determine if quantitative needle tracking could be used as a measure of lumbar puncture (LP) performance and added discriminatory value to a dichotomous checklist. Thirty-two medical students were divided into 2 groups. One group was asked to practice an LP once (single practice [SP]) and the other 5 times (multiple practice [MP]). Experts (attending ER physicians, senior ER residents, and a junior anesthesia resident) were used as comparators. Medical students were assessed again at 1 month to assess skill retention. Groups were assessed performing an LP with an electromagnetic tracking device that allows the needle's 3-dimensional movements to be captured and analyzed, and a dichotomous checklist. RESULTS: Quantitative needle metrics as assessed by electromagnetic tracking showed a decreasing trend in needle movement distance with practice and with experience. The SP group made significantly more checklist mistakes initially as compared to the MP group (1.2 vs. 0.3, p <.05). At 1 month, there was a significant increase in both groups' mistakes (SP 3.4 vs. MP 1.3, p =.01). No correlation existed between individuals' needle motion and checklist mistakes. CONCLUSIONS: These findings suggest that quantitative needle tracking identifies students who struggle with needle insertion but are successful at completing the dichotomous checklist.

[Relationship between early myocardial reperfusion assessed by videodensitometry and late left ventricular function. Results following invasive treatment of acute myocardial infarction]. / A videodenzitometriával vizsgált korai myocardialis reperfúzió és a kései balkamra-funkció összefüggései. Eredmények acut myocardialis infarctus invazív ellátását követoen.

INTRODUCTION: It is known that there is a relationship between myocardial perfusion and left ventricular function. AIM: The aim of the current study was to examine the relationship between myocardial reperfusion as assessed by videodensitometry on coronary angiograms following invasive treatment of ST elevation myocardial infarction and magnetic resonance imaging-derived late left ventricular function. METHOD: The study included 25 patients with ST elevation myocardial infarction. A quantitative parameter of myocardial (re)perfusion was calculated by the ratio of maximal density (Gmax) and the time to reach maximum density (Tmax) following invasive treatment. Magnetic resonance imaging was performed 387±262 days after ST elevation myocardial infarction for the evaluation of left ventricular function in all cases. RESULTS: Significant correlations were demonstrated between left ventricular ejection fraction and Gmax (r = 0.40, p = 0.05) and Gmax/Tmax (r = 0.41, p = 0.04) following vessel masking. CONCLUSIONS: The results demonstrate significant relationship between densitometric Gmax/Tmax and late left ventricular function following ST elevation myocardial infarction. Orv. Hetil., 2014. 155(5), 187-193.

Shape completion in the dark: completing vertebrae morphology from 3D ultrasound.

PURPOSE: Ultrasound (US) imaging, while advantageous for its radiation-free nature, is challenging to interpret due to only partially visible organs and a lack of complete 3D information. While performing US-based diagnosis or investigation, medical professionals therefore create a mental map of the 3D anatomy. In this work, we aim to replicate this process and enhance the visual representation of anatomical structures. METHODS: We introduce a point cloud-based probabilistic deep learning (DL) method to complete occluded anatomical structures through 3D shape completion and choose US-based spine examinations as our application. To enable training, we generate synthetic 3D representations of partially occluded spinal views by mimicking US physics and accounting for inherent artifacts. RESULTS: The proposed model performs consistently on synthetic and patient data, with mean and median differences of 2.02 and 0.03 in Chamfer Distance (CD), respectively. Our ablation study demonstrates the importance of US physics-based data generation, reflected in the large mean and median difference of 11.8 CD and 9.55 CD, respectively. Additionally, we demonstrate that anatomical landmarks, such as the spinous process (with reconstruction CD of 4.73) and the facet joints (mean distance to ground truth (GT) of 4.96 mm), are preserved in the 3D completion. CONCLUSION: Our work establishes the feasibility of 3D shape completion for lumbar vertebrae, ensuring the preservation of level-wise characteristics and successful generalization from synthetic to real data. The incorporation of US physics contributes to more accurate patient data completions. Notably, our method preserves essential anatomical landmarks and reconstructs crucial injections sites at their correct locations.

From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery.

PURPOSE: Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. METHODS: Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. RESULTS: The best-performing model using both quantitative evaluation and our visual ranking framework achieved a mean Dice score of 0.959. Quantitative metrics are positively associated with expert visual rankings. However, the predictive value of generated contours was limited with a sensitivity of 0.750 and a specificity of 0.433 when tested against pathology reports. CONCLUSION: We present a clinical evaluation of deep learning models trained for intraoperative tumor segmentation in breast-conserving surgery. We demonstrate that automatic contouring is limited in predicting pathology margins despite achieving high performance on quantitative metrics.

Augmented reality visualisation using an image overlay system for MR-guided interventions: technical performance of spine injection procedures in human cadavers at 1.5 Tesla.

OBJECTIVES: To prospectively assess the technical performance of an augmented reality system for MR-guided spinal injection procedures. METHODS: The augmented reality system was used with a clinical 1.5-T MRI system. A total of 187 lumbosacral spinal injection procedures (epidural injection, spinal nerve root injection, facet joint injection, medial branch block, discography) were performed in 12 human cadavers. Needle paths were planned with the Perk Station module of 3D Slicer software on high-resolution MR images. Needles were placed under augmented reality MRI navigation. MRI was used to confirm needle locations. T1-weighted fat-suppressed MRI was used to visualise the injectant. Outcome variables assessed were needle adjustment rate, inadvertent puncture of non-targeted structures, successful injection rate and procedure time. RESULTS: Needle access was achieved in 176/187 (94.1 %) targets, whereas 11/187 (5.9 %) were inaccessible. Six of 11 (54.5 %) L5-S1 disks were inaccessible, because of an axial obliquity of 30˚ (27˚-34˚); 5/11 (45.5 %) facet joints were inaccessible because of osteoarthritis or fusion. All accessible targets (176/187, 94.1 %) were successfully injected, requiring 47/176 (26.7 %) needle adjustments. There were no inadvertent punctures of vulnerable structures. Median procedure time was 10.2 min (5-19 min). CONCLUSIONS: Image overlay navigated MR-guided spinal injections were technically accurate. Disks with an obliquity ≥27˚ may be inaccessible.

Tracked ultrasound snapshots in percutaneous pedicle screw placement navigation: a feasibility study.

BACKGROUND: Computerized navigation improves the accuracy of minimally invasive pedicle screw placement during spine surgery. Such navigation, however, exposes both the patient and the staff to radiation during surgery. To avoid intraoperative exposure to radiation, tracked ultrasound snapshots-ultrasound image frames coupled with corresponding spatial positions-could be used to map preoperatively defined screw plans into the intraoperative coordinate frame. The feasibility of such an approach, however, has not yet been investigated. QUESTIONS/PURPOSES: Are there vertebral landmarks that can be identified using tracked ultrasound snapshots? Can tracked ultrasound snapshots allow preoperative pedicle screw plans to be accurately mapped--compared with CT-derived pedicle screw plans--into the intraoperative coordinate frame in a simulated setting? METHODS: Ultrasound visibility of registration landmarks was checked on volunteers and phantoms. An ultrasound machine with integrated electromagnetic tracking was used for tracked ultrasound acquisition. Registration was performed using 3D Slicer open-source software (www.slicer.org). Two artificial lumbar spine phantoms were used to evaluate registration accuracy of pedicle screw plans using tracked ultrasound snapshots. Registration accuracy was determined by comparing the ultrasound-derived plans with the CT-derived plans. RESULTS: The four articular processes proved to be identifiable using tracked ultrasound snapshots. Pedicle screw plans were registered to the intraoperative coordinate system using landmarks. The registrations were sufficiently accurate in that none of the registered screw plans intersected the pedicle walls. Registered screw plan positions had an error less than 1.28 ± 1.37 mm (average ± SD) in each direction and an angle difference less than 1.92° ± 1.95° around each axis relative to the CT-derived positions. CONCLUSIONS: Registration landmarks could be located using tracked ultrasound snapshots and permitted accurate mapping of pedicle screw plans to the intraoperative coordinate frame in a simulated setting. CLINICAL RELEVANCE: Tracked ultrasound may allow accurate computer-navigated pedicle screw placement while avoiding ionizing radiation in the operating room; however, further studies that compare this approach with other navigation techniques are needed to confirm the practical use of this new approach.

Use of Machine Learning to Assess Cataract Surgery Skill Level With Tool Detection.

Purpose: To develop a method for objective analysis of the reproducible steps in routine cataract surgery. Design: Prospective study; machine learning. Participants: Deidentified faculty and trainee surgical videos. Methods: Consecutive cataract surgeries performed by a faculty or trainee surgeon in an ophthalmology residency program over 6 months were collected and labeled according to degrees of difficulty. An existing image classification network, ResNet 152, was fine-tuned for tool detection in cataract surgery to allow for automatic identification of each unique surgical instrument. Individual microscope video frame windows were subsequently encoded as a vector. The relation between vector encodings and perceived skill using k-fold user-out cross-validation was examined. Algorithms were evaluated using area under the receiver operating characteristic curve (AUC) and the classification accuracy. Main Outcome Measures: Accuracy of tool detection and skill assessment. Results: In total, 391 consecutive cataract procedures with 209 routine cases were used. Our model achieved an AUC ranging from 0.933 to 0.998 for tool detection. For skill classification, AUC was 0.550 (95% confidence interval [CI], 0.547-0.553) with an accuracy of 54.3% (95% CI, 53.9%-54.7%) for a single snippet, AUC was 0.570 (0.565-0.575) with an accuracy of 57.8% (56.8%-58.7%) for a single surgery, and AUC was 0.692 (0.659-0.758) with an accuracy of 63.3% (56.8%-69.8%) for a single user given all their trials. Conclusions: Our research shows that machine learning can accurately and independently identify distinct cataract surgery tools in videos, which is crucial for comparing the use of the tool in a step. However, it is more challenging for machine learning to accurately differentiate overall and specific step skill to assess the level of training or expertise. Financial Disclosures: The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Real-time integration between Microsoft HoloLens 2 and 3D Slicer with demonstration in pedicle screw placement planning.

PURPOSE: Up to date, there has been a lack of software infrastructure to connect 3D Slicer to any augmented reality (AR) device. This work describes a novel connection approach using Microsoft HoloLens 2 and OpenIGTLink, with a demonstration in pedicle screw placement planning. METHODS: We developed an AR application in Unity that is wirelessly rendered onto Microsoft HoloLens 2 using Holographic Remoting. Simultaneously, Unity connects to 3D Slicer using the OpenIGTLink communication protocol. Geometrical transform and image messages are transferred between both platforms in real time. Through the AR glasses, a user visualizes a patient's computed tomography overlaid onto virtual 3D models showing anatomical structures. We technically evaluated the system by measuring message transference latency between the platforms. Its functionality was assessed in pedicle screw placement planning. Six volunteers planned pedicle screws' position and orientation with the AR system and on a 2D desktop planner. We compared the placement accuracy of each screw with both methods. Finally, we administered a questionnaire to all participants to assess their experience with the AR system. RESULTS: The latency in message exchange is sufficiently low to enable real-time communication between the platforms. The AR method was non-inferior to the 2D desktop planner, with a mean error of 2.1 ± 1.4 mm. Moreover, 98% of the screw placements performed with the AR system were successful, according to the Gertzbein-Robbins scale. The average questionnaire outcomes were 4.5/5. CONCLUSIONS: Real-time communication between Microsoft HoloLens 2 and 3D Slicer is feasible and supports accurate planning for pedicle screw placement.

Augmented reality visualization with use of image overlay technology for MR imaging-guided interventions: assessment of performance in cadaveric shoulder and hip arthrography at 1.5 T.

PURPOSE: To prospectively assess overlay technology in providing accurate and efficient targeting for magnetic resonance (MR) imaging-guided shoulder and hip joint arthrography. MATERIALS AND METHODS: A prototype augmented reality image overlay system was used in conjunction with a clinical 1.5-T MR imager. A total of 24 shoulder joint and 24 hip joint injections were planned in 12 human cadavers. Two operators (A and B) participated, each performing procedures on different cadavers using image overlay guidance. MR imaging was used to confirm needle positions, monitor injections, and perform MR arthrography. Accuracy was assessed according to the rate of needle adjustment, target error, and whether the injection was intraarticular. Efficiency was assessed according to arthrography procedural time. Operator differences were assessed with comparison of accuracy and procedure times between the operators. Mann-Whitney U test and Fisher exact test were used to assess group differences. RESULTS: Forty-five arthrography procedures (23 shoulders, 22 hips) were performed. Three joints had prostheses and were excluded. Operator A performed 12 shoulder and 12 hip injections. Operator B performed 11 shoulder and 10 hip injections. Needle adjustment rate was 13% (six of 45; one for operator A and five for operator B). Target error was 3.1 mm±1.2 (standard deviation) (operator A, 2.9 mm±1.4; operator B, 3.5 mm±0.9). Intraarticular injection rate was 100% (45 of 45). The average arthrography time was 14 minutes (range, 6-27 minutes; 12 minutes [range, 6-25 minutes] for operator A and 16 minutes [range, 6-27 min] for operator B). Operator differences were not significant with regard to needle adjustment rate (P=.08), target error (P=.07), intraarticular injection rate (P>.99), and arthrography time (P=.22). CONCLUSION: Image overlay technology provides accurate and efficient MR guidance for successful shoulder and hip arthrography in human cadavers.

Augmented reality visualization with image overlay for MRI-guided intervention: accuracy for lumbar spinal procedures with a 1.5-T MRI system.

OBJECTIVE: The purpose of this study was to prospectively evaluate the accuracy of an augmented reality image overlay system in MRI-guided spinal injection procedures. MATERIALS AND METHODS: An augmented reality prototype was used in conjunction with a 1.5-T MRI system. A human lumbar spine phantom was used in which 62 targets were punctured to assess the accuracy of the system. Sixty anatomic targets (facet joint, disk space, and spinal canal) were punctured to assess how the accuracy of the system translated into practice. A visualization software interface was used to compare planned needle paths and final needle locations on coregistered CT images (standard of reference). Outcome variables included entry error, angle error, depth error, target error, successful access of anatomic targets, number of needle adjustments, and time requirements. RESULTS: Accuracy assessments showed entry error of 1.6 ± 0.8 mm, angle error of 1.6° ± 1.0°, depth error of 0.7 ± 0.5 mm, and target error of 1.9 ± 0.9 mm. All anatomic targets (60 of 60 insertions) were successfully punctured, including all 20 facet joints, all 20 disks, and all 20 spinal canals. Four needle adjustments (6.7%) were required. Planning of a single needle path required an average of 55 seconds. A single needle insertion required an average of 1 minute 27 seconds. CONCLUSION: The augmented reality image overlay system evaluated facilitated accurate MRI guidance for successful spinal procedures in a lumbar spine model. It exhibited potential for simplifying the current practice of MRI-guided lumbar spinal injection procedures.

[Aortic valve stenosis is associated with reduced myocardial perfusion as assessed by videodensitometry in coronary angiograms]. / Az aortabillentyu szukülete együtt jár a koronarográfiás felvételeken videodenzitometria során meghatározott myocardialis perfúzió csökkenésével.

UNLABELLED: Aortic valve stenosis may be accompanied by angina despite coronary arteries free of significant stenosis due to microvascular abnormalities. AIMS: The aim of the current study was to test whether densitometry-derived myocardial perfusion on coronary angiogram is reduced in patients with aortic valve stenosis. METHODS: The study comprised 20 patients with aortic valve stenosis (mean transvalvular gradient: 47.4±15.2 mm Hg) and 30 control subjects without significant epicardial coronary artery stenosis. A quantitative parameter of myocardial perfusion was calculated by the ratio of maximal density (Gmax) and time to reach maximum density (Tmax) on time-density curves in regions of interest of each coronary artery on coronary angiograms. RESULTS: Mean three-vessel Gmax/Tmax proved to be significantly lower in patients with aortic valve stenosis compared to control subjects (2.55±1.02 1/sec vs. 3.39±1.09 1/sec, p<0.01). CONCLUSIONS: Reduced Gmax/Tmax values indicative of myocardial perfusion abnormalities as measured by densitometry on coronary angiograms could be demonstrated in patients with aortic valve stenosis compared to controls.

Training in soft tissue resection using real-time visual computer navigation feedback from the Surgery Tutor: A randomized controlled trial.

BACKGROUND: In competency-based medical education, surgery trainees are often required to learn procedural skills in a simulated setting before proceeding to the clinical environment. The Surgery Tutor computer navigation platform allows for real-time proctor-less assessment of open soft tissue resection skills; however, the use of this platform as an aid in acquisition of procedural skills is yet to be explored. METHODS: In this prospective randomized controlled trial, 20 final year medical students were randomized to receive either training with real-time computer navigation feedback (Intervention, n = 10) or simulation training without navigation feedback (Control, n = 10) during resection of simulated non-palpable soft tissue tumors. Real-time computer navigation feedback allowed participants to visualize the position of their scalpel relative to the tumor. Computer navigation feedback was removed for postintervention assessment. Primary outcome was positive margin rate. Secondary outcomes were procedure time, mass of tissue excised, number of scalpel motions, and distance traveled by the scalpel. RESULTS: Training with real-time computer navigation resulted in a significantly lower positive margin rate as compared to training without navigation feedback (0% vs 40%, P = .025). All other performance metrics were not significantly different between the 2 groups. Participants in the intervention group displayed significant improvement in positive margin rate from baseline to final assessment (80% vs 0%, P < .01), whereas participants in the Control group did not. CONCLUSION: Real-time visual computer navigation feedback from the Surgery Tutor resulted in superior acquisition of procedural skills as compared to training without navigation feedback.

System for Central Venous Catheterization Training Using Computer Vision-Based Workflow Feedback.

OBJECTIVE: To develop a system for training central venous catheterization that does not require an expert observer. We propose a training system that uses video-based workflow recognition and electromagnetic tracking to provide trainees with real-time instruction and feedback. METHODS: The system provides trainees with prompts about upcoming tasks and visual cues about workflow errors. Most tasks are recognized from a webcam video using a combination of a convolutional neural network and a recurrent neural network. We evaluated the system's ability to recognize tasks in the workflow by computing the percent of tasks that were recognized and the average signed transitional delay between the system and reviewers. We also evaluated the usability of the system using a participant questionnaire. RESULTS: The system was able to recognize 86.2% of tasks in the workflow. The average signed transitional delay was -0.7s. The average usability score on the questionnaire was 4.7 out of 5 for the system overall. The participants found the interactive task list to be the most useful component of the system with an average score of 4.8 out of 5. CONCLUSION: Overall, the participants' response to the system was positive. Participants perceived that the system would be useful for central venous catheterization training. Our system provides trainees with meaningful instruction and feedback without needing an expert observer to be present. SIGNIFICANCE: We are able to provide trainees with more opportunities to access instruction and meaningful feedback by using workflow recognition.

Real-time automatic tumor segmentation for ultrasound-guided breast-conserving surgery navigation.

PURPOSE: Ultrasound-based navigation is a promising method in breast-conserving surgery, but tumor contouring often requires a radiologist at the time of surgery. Our goal is to develop a real-time automatic neural network-based tumor contouring process for intraoperative guidance. Segmentation accuracy is evaluated by both pixel-based metrics and expert visual rating. METHODS: This retrospective study includes 7318 intraoperative ultrasound images acquired from 33 breast cancer patients, randomly split between 80:20 for training and testing. We implement a u-net architecture to label each pixel on ultrasound images as either tumor or healthy breast tissue. Quantitative metrics are calculated to evaluate the model's accuracy. Contour quality and usability are also assessed by fellowship-trained breast radiologists and surgical oncologists. Additionally, the viability of using our u-net model in an existing surgical navigation system is evaluated by measuring the segmentation frame rate. RESULTS: The mean dice similarity coefficient of our u-net model is 0.78, with an area under the receiver-operating characteristics curve of 0.94, sensitivity of 0.95, and specificity of 0.67. Expert visual ratings are positive, with 93% of responses rating tumor contour quality at or above 7/10, and 75% of responses rating contour quality at or above 8/10. Real-time tumor segmentation achieved a frame rate of 16 frames-per-second, sufficient for clinical use. CONCLUSION: Neural networks trained with intraoperative ultrasound images provide consistent tumor segmentations that are well received by clinicians. These findings suggest that neural networks are a promising adjunct to alleviate radiologist workload as well as improving efficiency in breast-conserving surgery navigation systems.

The use of 3D digital anatomy model improves the communication with patients presenting with prostate disease: The first experience in Senegal.

OBJECTIVES: We hypothesized that the use of an interactive 3D digital anatomy model can improve the quality of communication with patients about prostate disease. METHODS: A 3D digital anatomy model of the prostate was created from an MRI scan, according to McNeal's zonal anatomy classification. During urological consultation, the physician presented the digital model on a computer and used it to explain the disease and available management options. The experience of patients and physicians was recorded in questionnaires. RESULTS: The main findings were as follows: 308 patients and 47 physicians participated in the study. In the patient group, 96.8% reported an improved level of understanding of prostate disease and 90.6% reported an improved ability to ask questions during consultation. Among the physicians, 91.5% reported improved communication skills and 100% reported an improved ability to obtain patient consent for subsequent treatment. At the same time, 76.6% of physicians noted that using the computer model lengthened the consultation. CONCLUSION: This exploratory study found that the use of a 3D digital anatomy model in urology consultations was received overwhelmingly favorably by both patients and physicians, and it was perceived to improve the quality of communication between patient and physician. A randomized study is needed to confirm the preliminary findings and further quantify the improvements in the quality of patient-physician communication.