Comparing adaptations from blood flow restriction exercise training using regulated or unregulated pressure systems: A systematic review and meta-analysis.

OBJECTIVE: No study has examined outcomes derived from blood flow restriction exercise training interventions using regulated compared with unregulated blood flow restriction pressure systems. Therefore, we used a systematic review and meta-analyses to compare the chronic adaptations to blood flow restriction exercise training achieved with regulated and unregulated blood flow restriction pressure systems. DATA SOURCES: The electronic database search included using the tool EBSCOhost and other online database search engines. The search included Medline, SPORTDiscus, CINAHL, Embase and SpringerLink. METHODS: Included studies utilised chronic blood flow restriction exercise training interventions greater than two weeks duration, where blood flow restriction was applied using a regulated or unregulated blood flow restriction pressure system, and where outcome measures such as muscle strength, muscle size or physical function were measured both pre- and post-training. Studies included in the meta-analyses used an equivalent non-blood flow restriction exercise comparison group. RESULTS: Eighty-one studies were included in the systematic review. Data showed that regulated (n = 47) and unregulated (n = 34) blood flow restriction pressure systems yield similar training adaptations for all outcome measures post-intervention. For muscle strength and muscle size, this was reaffirmed in the included meta-analyses. CONCLUSION: This review indicates that practitioners may achieve comparable training adaptations with blood flow restriction exercise training using either regulated or unregulated blood flow restriction pressure systems. Therefore, additional factors such as device quality, participant comfort and safety, cost and convenience are important factors to consider when deciding on appropriate equipment to use when prescribing blood flow restriction exercise training.

Running is acceptable and efficacious in adults with non-specific chronic low back pain: the ASTEROID randomised controlled trial.

OBJECTIVES: Running is one of the most accessible forms of exercise, yet its suitability for adults with chronic low back pain (LBP) is unknown. This study assessed the efficacy and acceptability of running in adults with chronic LBP. METHODS: This two-arm parallel (1:1) individually randomised controlled trial allocated 40 participants (mean (SD) age: 33 (6) years, female: 50%) with non-specific chronic LBP to a 12-week intervention or waitlist control. The intervention was a progressive run-walk interval programme comprising three 30-min sessions per week that were digitally delivered and remotely supported by an exercise physiologist. Efficacy outcomes were self-reported pain intensity (100-point visual analogue scale) and disability (Oswestry Disability Index). Acceptability outcomes were attrition, adherence and adverse events. RESULTS: At 12-week follow-up, the intervention improved average pain intensity (mean net difference (95% CI): -15.30 (-25.33, -5.27) points, p=0.003), current pain intensity (-19.35 (-32.01, -6.69) points, p=0.003) and disability (-5.20 (-10.12, -0.24) points, P=0.038), compared with control. There was no attrition, and mean (SD) training adherence was 70% (20%; ie, 2.1 of 3 sessions per week). Nine non-serious adverse events deemed likely study-related were reported (lower limb injury/pain: n=7, syncope associated with an underlying condition: n=1, LBP: n=1). CONCLUSIONS: A run-walk programme was considered an acceptable intervention by the participants to improve the pain intensity and disability in individuals aged 18-45 years with non-specific chronic LBP when compared with the control. An individualised and conservative run-walk programme should be considered a suitable form of physical activity for adults with chronic LBP. TRIAL REGISTRATION NUMBER: Australian New Zealand Clinical Trials Registry: ACTRN12622001276741. Registered on 29 September 2022.

Phase 0 Study of Vandetanib-Eluting Radiopaque Embolics as a Preoperative Embolization Treatment in Patients with Resectable Liver Malignancies.

PURPOSE: To assess the safety and tolerability of a vandetanib-eluting radiopaque embolic (BTG-002814) for transarterial chemoembolization (TACE) in patients with resectable liver malignancies. MATERIALS AND METHODS: The VEROnA clinical trial was a first-in-human, phase 0, single-arm, window-of-opportunity study. Eligible patients were aged ≥18 years and had resectable hepatocellular carcinoma (HCC) (Child-Pugh A) or metastatic colorectal cancer (mCRC). Patients received 1 mL of BTG-002814 transarterially (containing 100 mg of vandetanib) 7-21 days prior to surgery. The primary objectives were to establish the safety and tolerability of BTG-002814 and determine the concentrations of vandetanib and the N-desmethyl vandetanib metabolite in the plasma and resected liver after treatment. Biomarker studies included circulating proangiogenic factors, perfusion computed tomography, and dynamic contrast-enhanced magnetic resonance imaging. RESULTS: Eight patients were enrolled: 2 with HCC and 6 with mCRC. There was 1 grade 3 adverse event (AE) before surgery and 18 after surgery; 6 AEs were deemed to be related to BTG-002814. Surgical resection was not delayed. Vandetanib was present in the plasma of all patients 12 days after treatment, with a mean maximum concentration of 24.3 ng/mL (standard deviation ± 13.94 ng/mL), and in resected liver tissue up to 32 days after treatment (441-404,000 ng/g). The median percentage of tumor necrosis was 92.5% (range, 5%-100%). There were no significant changes in perfusion imaging parameters after TACE. CONCLUSIONS: BTG-002814 has an acceptable safety profile in patients before surgery. The presence of vandetanib in the tumor specimens up to 32 days after treatment suggests sustained anticancer activity, while the low vandetanib levels in the plasma suggest minimal release into the systemic circulation. Further evaluation of this TACE combination is warranted in dose-finding and efficacy studies.

Hemodynamic and perceptual responses to blood flow-restricted exercise among patients undergoing dialysis.

End-stage kidney disease is associated with reduced exercise capacity, muscle atrophy, and impaired muscle function. While these may be improved with exercise, single modalities of exercise do not traditionally elicit improvements across all required physiological domains. Blood flow-restricted exercise may improve all of these physiological domains with low intensities traditionally considered insufficient for these adaptions. Investigation of this technique appeals, but is yet to be evaluated, in patients undergoing dialysis. With the use of a progressive crossover design, 10 satellite patients undergoing hemodialysis underwent three exercise conditions over 2 wk: two bouts (10 min) of unrestricted cycling during two consecutive hemodialysis sessions (condition 1), two bouts of cycling with blood flow restriction while off hemodialysis on 2 separate days (condition 2), and two bouts of cycling with blood flow restriction during two hemodialysis sessions (condition 3). Outcomes included hemodynamic responses (heart rate and blood pressure) throughout all sessions, participant-perceived exertion and discomfort on a Borg scale, and evaluation of ultrafiltration rates and dialysis adequacy (Kt/V) obtained post hoc. Hemodynamic responses were consistent regardless of condition. Significant increases in heart rate, systolic blood pressure, and mean arterial blood pressure (P < 0.05) were observed postexercise followed by a reduction in blood pressures during the 60-min recovery (12, 5, and 11 mmHg for systolic, diastolic, and mean arterial pressures, respectively). Blood pressures returned to predialysis ranges following the recovery period. Blood flow restriction did not affect ultrafiltration achieved or Kt/V. Hemodynamic safety and tolerability of blood flow restriction during aerobic exercise on hemodialysis is comparable to standard aerobic exercise.

Dimensions of ecological validity for usability evaluations in clinical settings.

The development, evaluation, and eventual deployment of novel medical devices is a complex process involving various areas of expertise. Although the need for a User Centred Design approach to the development of both hardware and software has long been established, both current regulatory guidelines and widespread evaluation approaches fail to reflect the challenges encountered during day-to-day clinical practice. As such, the results from these evaluations may not provide a realistic account of the problems encountered by users when introduced to clinical practice. In this paper, we present a case study on designing the evaluation of a novel device to support laparoscopic liver surgery. Through a reflective account of the design of our usability evaluation, we identify and describe seven primary dimensions of ecological validity encountered in clinical usability evaluations. These dimensions are: 'user roles', 'environment', 'training', 'scenario', 'patient involvement', 'software', and 'hardware'. We analyse three recently published clinical usability evaluation articles to assess (and illustrate) the applicability and completeness of these dimensions. Finally, we discuss the compromises encountered during clinical usability evaluations and how to best report on these considerations. The framework presented here aims to further the agenda of ecologically valid evaluation practice, reflecting the constraints of medical practice.

Is there rationale for the cuff pressures prescribed for blood flow restriction exercise? A systematic review.

BACKGROUND: Blood flow restriction exercise has increasingly broad applications among healthy and clinical populations. Ensuring the technique is applied in a safe, controlled, and beneficial way for target populations is essential. Individualized cuff pressures are a favored method for achieving this. However, there remains marked inconsistency in how individualized cuff pressures are applied. OBJECTIVES: To quantify the cuff pressures used in the broader blood flow restriction exercise literature, and determine whether there is clear justification for the choice of pressure prescribed. METHODS: Studies were included in this review from database searches if they employed an experimental design using original data, involved either acute or chronic exercise using blood flow restriction, and they assessed limb or arterial occlusion pressure to determine an individualized cuff pressure. Methodologies of the studies were evaluated using a bespoke quality assessment tool. RESULTS: Fifty-one studies met the inclusion criteria. Individualized cuff pressures ranged from 30% to 100% arterial occlusion pressure. Only 7 out of 52 studies attempted to justify the individualized cuff pressure applied during exercise. The mean quality rating for all studies was 11.1 ± 1.2 out of 13. CONCLUSIONS: The broader blood flow restriction exercise literature uses markedly heterogeneous prescription variables despite using individualized cuff pressures. This is problematic in the absence of any clear justification for the individualized cuff pressures selected. Systematically measuring and reporting all relevant acute responses and training adaptations to the full spectrum of BFR pressures alongside increased clarity around the methodology used during blood flow restriction exercise is paramount.

Exercise interventions for improving objective physical function in patients with end-stage kidney disease on dialysis: a systematic review and meta-analysis.

Patients with end-stage kidney disease on dialysis have increased mortality and reduced physical activity, contributing to impaired physical function. Although exercise programs have demonstrated a positive effect on physiological outcomes such as cardiovascular function and strength, there is a reduced focus on physical function. The aim of this review was to determine whether exercise programs improve objective measures of physical function indicative of activities of daily living for patients with end-stage kidney disease on dialysis. A systematic search of Medline, Embase, the Cochrane Central Register of Controlled Trials, and Cumulative Index to Nursing and Allied Health Literature identified 27 randomized control trials. Only randomized control trials using an exercise intervention or significant muscular activation in the intervention, a usual care, nonexercising control group, and at least one objective measure of physical function were included. Participants were ≥18 yr of age, with end-stage kidney disease, undergoing hemo- or peritoneal dialysis. Systematic review of the literature and quality assessment of the included studies used the Cochrane Collaboration's tool for assessing risk bias. A meta-analysis was completed for the 6-min walk test. Data from 27 studies with 1,156 participants showed that exercise, regardless of modality, generally increased 6-min walk test distance, sit-to-stand time or repetitions, and grip strength as well as step and stair climb times or repetitions, dynamic mobility, and short physical performance battery scores. From the evidence available, exercise, regardless of modality, improved objective measures of physical function for end-stage kidney disease patients undergoing dialysis. It is acknowledged that further well-designed randomized control trials are required.

Efficacy of blood flow restriction exercise during dialysis for end stage kidney disease patients: protocol of a randomised controlled trial.

BACKGROUND: Exercise during haemodialysis improves strength and physical function. However, both patients and clinicians are time poor, and current exercise recommendations add an excessive time burden making exercise a rare addition to standard care. Hypothetically, blood flow restriction exercise performed during haemodialysis can provide greater value for time spent exercising, reducing this time burden while producing similar or greater outcomes. This study will explore the efficacy of blood flow restriction exercise for enhancing strength and physical function among haemodialysis patients. METHODS: This is a randomised controlled trial design. A total of 75 participants will be recruited from haemodialysis clinics. Participants will be allocated to a blood flow restriction cycling group, traditional cycling group or usual care control group. Both exercising groups will complete 3 months of cycling exercise, performed intradialytically, three times per week. The blood flow restriction cycling group will complete two 10-min cycling bouts separated by a 20-min rest at a subjective effort of 15 on a 6 to 20 rating scale. This will be done with pressurised cuffs fitted proximally on the active limbs during exercise at 50% of a pre-determined limb occlusion pressure. The traditional cycling group will perform a continuous 20-min bout of exercise at a subjective effort of 12 on the same subjective effort scale. These workloads and volumes are equivalent and allow for comparison of a common blood flow restriction aerobic exercise prescription and a traditional aerobic exercise prescription. The primary outcome measures are lower limb strength, assessed by a three repetition maximum leg extension test, as well as objective measures of physical function: six-minute walk test, 30-s sit to stand, and timed up and go. Secondary outcome measures include thigh muscle cross sectional area, body composition, routine pathology, quality of life, and physical activity engagement. DISCUSSION: This study will determine the efficacy of blood flow restriction exercise among dialysis patients for improving key physiological outcomes that impact independence and quality of life, with reduced burden on patients. This may have broader implications for other clinical populations with similarly declining muscle health and physical function, and those contraindicated to higher intensities of exercise. TRIAL REGISTRATION: Australian and New Zealand Clinical Trial Register: ACTRN12616000121460.

Utilizing confocal laser endomicroscopy for evaluating the adequacy of laparoscopic liver ablation.

BACKGROUND: Laparoscopic liver ablation therapy can be used for the treatment of primary and secondary liver malignancy. The increased incidence of cancer recurrence associated with this approach, has been attributed to the inability of monitoring the extent of ablated liver tissue. METHODS: The feasibility of assessing liver ablation with probe-based confocal laser endomicroscopy (CLE) was studied in a porcine model of laparoscopic microwave liver ablation. Following the intravenous injection of the fluorophores fluorescein and indocyanine green, CLE images were recorded at 488 nm and 660 nm wavelength and compared to liver histology. Statistical analysis was performed to assess if fluorescence intensity change can predict the presence of ablated liver tissue. RESULTS: CLE imaging of fluorescein at 488 nm provided good visualization of the hepatic microvasculature; whereas, CLE imaging of indocyanine green at 660 nm enabled detailed visualization of hepatic sinusoid architecture and interlobular septations. Fluorescence intensity as measured in relative fluorescence units was found to be 75-100% lower in ablated compared to healthy liver regions. General linear mixed modeling and ROC analysis found the decrease in fluorescence to be statistically significant. CONCLUSION: Laparoscopic, dual wavelength CLE imaging using two different fluorophores enables clinically useful visualization of multiple liver tissue compartments, in greater detail than is possible at a single wavelength. CLE imaging may provide valuable intraoperative information on the extent of laparoscopic liver ablation.

Surgical-DeSAM: decoupling SAM for instrument segmentation in robotic surgery.

PURPOSE: The recent segment anything model (SAM) has demonstrated impressive performance with point, text or bounding box prompts, in various applications. However, in safety-critical surgical tasks, prompting is not possible due to (1) the lack of per-frame prompts for supervised learning, (2) it is unrealistic to prompt frame-by-frame in a real-time tracking application, and (3) it is expensive to annotate prompts for offline applications. METHODS: We develop Surgical-DeSAM to generate automatic bounding box prompts for decoupling SAM to obtain instrument segmentation in real-time robotic surgery. We utilise a commonly used detection architecture, DETR, and fine-tuned it to obtain bounding box prompt for the instruments. We then empolyed decoupling SAM (DeSAM) by replacing the image encoder with DETR encoder and fine-tune prompt encoder and mask decoder to obtain instance segmentation for the surgical instruments. To improve detection performance, we adopted the Swin-transformer to better feature representation. RESULTS: The proposed method has been validated on two publicly available datasets from the MICCAI surgical instruments segmentation challenge EndoVis 2017 and 2018. The performance of our method is also compared with SOTA instrument segmentation methods and demonstrated significant improvements with dice metrics of 89.62 and 90.70 for the EndoVis 2017 and 2018 CONCLUSION: Our extensive experiments and validations demonstrate that Surgical-DeSAM enables real-time instrument segmentation without any additional prompting and outperforms other SOTA segmentation methods.

The distinct roles of reinforcement learning between pre-procedure and intra-procedure planning for prostate biopsy.

PURPOSE: Magnetic resonance (MR) imaging targeted prostate cancer (PCa) biopsy enables precise sampling of MR-detected lesions, establishing its importance in recommended clinical practice. Planning for the ultrasound-guided procedure involves pre-selecting needle sampling positions. However, performing this procedure is subject to a number of factors, including MR-to-ultrasound registration, intra-procedure patient movement and soft tissue motions. When a fixed pre-procedure planning is carried out without intra-procedure adaptation, these factors will lead to sampling errors which could cause false positives and false negatives. Reinforcement learning (RL) has been proposed for procedure plannings on similar applications such as this one, because intelligent agents can be trained for both pre-procedure and intra-procedure planning. However, it is not clear if RL is beneficial when it comes to addressing these intra-procedure errors. METHODS: In this work, we develop and compare imitation learning (IL), supervised by demonstrations of predefined sampling strategy, and RL approaches, under varying degrees of intra-procedure motion and registration error, to represent sources of targeting errors likely to occur in an intra-operative procedure. RESULTS: Based on results using imaging data from 567 PCa patients, we demonstrate the efficacy and value in adopting RL algorithms to provide intelligent intra-procedure action suggestions, compared to IL-based planning supervised by commonly adopted policies. CONCLUSIONS: The improvement in biopsy sampling performance for intra-procedure planning has not been observed in experiments with only pre-procedure planning. These findings suggest a strong role for RL in future prospective studies which adopt intra-procedure planning. Our open source code implementation is available here .

Active learning using adaptable task-based prioritisation.

Supervised machine learning-based medical image computing applications necessitate expert label curation, while unlabelled image data might be relatively abundant. Active learning methods aim to prioritise a subset of available image data for expert annotation, for label-efficient model training. We develop a controller neural network that measures priority of images in a sequence of batches, as in batch-mode active learning, for multi-class segmentation tasks. The controller is optimised by rewarding positive task-specific performance gain, within a Markov decision process (MDP) environment that also optimises the task predictor. In this work, the task predictor is a segmentation network. A meta-reinforcement learning algorithm is proposed with multiple MDPs, such that the pre-trained controller can be adapted to a new MDP that contains data from different institutes and/or requires segmentation of different organs or structures within the abdomen. We present experimental results using multiple CT datasets from more than one thousand patients, with segmentation tasks of nine different abdominal organs, to demonstrate the efficacy of the learnt prioritisation controller function and its cross-institute and cross-organ adaptability. We show that the proposed adaptable prioritisation metric yields converging segmentation accuracy for a new kidney segmentation task, unseen in training, using between approximately 40% to 60% of labels otherwise required with other heuristic or random prioritisation metrics. For clinical datasets of limited size, the proposed adaptable prioritisation offers a performance improvement of 22.6% and 10.2% in Dice score, for tasks of kidney and liver vessel segmentation, respectively, compared to random prioritisation and alternative active sampling strategies.

PitSurgRT: real-time localization of critical anatomical structures in endoscopic pituitary surgery.

PURPOSE: Endoscopic pituitary surgery entails navigating through the nasal cavity and sphenoid sinus to access the sella using an endoscope. This procedure is intricate due to the proximity of crucial anatomical structures (e.g. carotid arteries and optic nerves) to pituitary tumours, and any unintended damage can lead to severe complications including blindness and death. Intraoperative guidance during this surgery could support improved localization of the critical structures leading to reducing the risk of complications. METHODS: A deep learning network PitSurgRT is proposed for real-time localization of critical structures in endoscopic pituitary surgery. The network uses high-resolution net (HRNet) as a backbone with a multi-head for jointly localizing critical anatomical structures while segmenting larger structures simultaneously. Moreover, the trained model is optimized and accelerated by using TensorRT. Finally, the model predictions are shown to neurosurgeons, to test their guidance capabilities. RESULTS: Compared with the state-of-the-art method, our model significantly reduces the mean error in landmark detection of the critical structures from 138.76 to 54.40 pixels in a 1280 × 720-pixel image. Furthermore, the semantic segmentation of the most critical structure, sella, is improved by 4.39% IoU. The inference speed of the accelerated model achieves 298 frames per second with floating-point-16 precision. In the study of 15 neurosurgeons, 88.67% of predictions are considered accurate enough for real-time guidance. CONCLUSION: The results from the quantitative evaluation, real-time acceleration, and neurosurgeon study demonstrate the proposed method is highly promising in providing real-time intraoperative guidance of the critical anatomical structures in endoscopic pituitary surgery.

Competing for Pixels: A Self-play Algorithm for Weakly-supervised Semantic Segmentation.

Weakly-supervised semantic segmentation (WSSS) methods, reliant on image-level labels indicating object presence, lack explicit correspondence between labels and regions of interest (ROIs), posing a significant challenge. Despite this, WSSS methods have attracted attention due to their much lower annotation costs compared to fully-supervised segmentation. Leveraging reinforcement learning (RL) self-play, we propose a novel WSSS method that gamifies image segmentation of a ROI. We formulate segmentation as a competition between two agents that compete to select ROI-containing patches until exhaustion of all such patches. The score at each time-step, used to compute the reward for agent training, represents likelihood of object presence within the selection, determined by an object presence detector pre-trained using only image-level binary classification labels of object presence. Additionally, we propose a game termination condition that can be called by either side upon exhaustion of all ROI-containing patches, followed by the selection of a final patch from each. Upon termination, the agent is incentivised if ROI-containing patches are exhausted or disincentivised if a ROI-containing patch is found by the competitor. This competitive setup ensures minimisation of over- or under-segmentation, a common problem with WSSS methods. Extensive experimentation across four datasets demonstrates significant performance improvements over recent state-of-the-art methods. Code: https://github.com/s-sd/spurl/tree/main/wss.

Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis.

BACKGROUND: Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencoder (SD-VAE) to objectively assess changes following midfacial surgery. MATERIALS AND METHODS: Our model is trained on a dataset of 1405 3D meshes of healthy and syndromic patients which was augmented using a technique based on spectral interpolation. Patients with a diagnosis of Apert and Crouzon syndrome who had undergone sub- or trans-cranial midfacial procedures utilising rigid external distraction were then interpreted using this model as the point of comparison. RESULTS: A total of 56 patients met our inclusion criteria, 20 with Apert and 36 with Crouzon syndrome. By using linear discriminant analysis to project the high-dimensional vectors derived by SD-VAE onto a 2D space, the shape properties of Apert and Crouzon syndrome can be visualised in relation to the healthy population. In this way, we are able to show how surgery elicits global shape changes in each patient. To assess the regional movements achieved during surgery, we use a novel metric derived from the Malahanobis distance to quantify movements through the latent space. CONCLUSION: Objective outcome evaluation, which encourages in-depth analysis and enhances decision making, is essential for the progression of surgical practice. We have demonstrated how artificial intelligence has the ability to improve our understanding of surgery and its effect on craniofacial morphology.

Latent disentanglement in mesh variational autoencoders improves the diagnosis of craniofacial syndromes and aids surgical planning.

BACKGROUND AND OBJECTIVE: The use of deep learning to undertake shape analysis of the complexities of the human head holds great promise. However, there have traditionally been a number of barriers to accurate modelling, especially when operating on both a global and local level. METHODS: In this work, we will discuss the application of the Swap Disentangled Variational Autoencoder (SD-VAE) with relevance to Crouzon, Apert and Muenke syndromes. The model is trained on a dataset of 3D meshes of healthy and syndromic patients which was increased in size with a novel data augmentation technique based on spectral interpolation. Thanks to its semantically meaningful and disentangled latent representation, SD-VAE is used to analyse and generate head shapes while considering the influence of different anatomical sub-units. RESULTS: Although syndrome classification is performed on the entire mesh, it is also possible, for the first time, to analyse the influence of each region of the head on the syndromic phenotype. By manipulating specific parameters of the generative model, and producing procedure-specific new shapes, it is also possible to approximate the outcome of a range of craniofacial surgical procedures. CONCLUSION: This work opens new avenues to advance diagnosis, aids surgical planning and allows for the objective evaluation of surgical outcomes. Our code is available at github.com/simofoti/CraniofacialSD-VAE.

The Effect of Luminance on Depth Perception in Augmented Reality Guided Laparoscopic Surgery.

Depth perception is a major issue in surgical augmented reality (AR) with limited research conducted in this scientific area. This study establishes a relationship between luminance and depth perception. This can be used to improve visualisation design for AR overlay in laparoscopic surgery, providing surgeons a more accurate perception of the anatomy intraoperatively. Two experiments were conducted to determine this relationship. First, an online study with 59 participants from the general public, and second, an in-person study with 10 surgeons as participants. We developed 2 open-source software tools utilising SciKit-Surgery libraries to enable these studies and any future research. Our findings demonstrate that the higher the relative luminance, the closer a structure is perceived to the operating camera. Furthermore, the higher the luminance contrast between the two structures, the higher the depth distance perceived. The quantitative results from both experiments are in agreement, indicating that online recruitment of the general public can be helpful in similar studies. An observation made by the surgeons from the in-person study was that the light source used in laparoscopic surgery plays a role in depth perception. This is due to its varying positioning and brightness which could affect the perception of the overlaid AR. We found that luminance directly correlates with depth perception for both surgeons and the general public, regardless of other depth cues. Future research may focus on comparing different colours used in surgical AR and using a mock operating room (OR) with varying light sources and positions.

3D Generative Model Latent Disentanglement via Local Eigenprojection.

Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state-of-the-art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre-trained models are available at github.com/simofoti/LocalEigenprojDisentangled.