Impact of cancer diagnosis on life expectancy by area-level socioeconomic groups in New South Wales, Australia: a population-based study.

OBJECTIVE: Improvement in cancer survival over recent decades has not been accompanied by a narrowing of socioeconomic disparities. This study aimed to quantify the loss of life expectancy (LOLE) resulting from a cancer diagnosis and examine disparities in LOLE based on area-level socioeconomic status (SES). METHODS: Data were collected for all people between 50 and 89 years of age who were diagnosed with cancer, registered in the NSW Cancer Registry between 2001 and 2019, and underwent mortality follow-up evaluations until December 2020. Flexible parametric survival models were fitted to estimate the LOLE by gender and area-level SES for 12 common cancers. RESULTS: Of 422,680 people with cancer, 24% and 18% lived in the most and least disadvantaged areas, respectively. Patients from the most disadvantaged areas had a significantly greater average LOLE than patients from the least disadvantaged areas for cancers with high survival rates, including prostate [2.9 years (95% CI: 2.5-3.2 years) vs. 1.6 years (95% CI: 1.3-1.9 years)] and breast cancer [1.6 years (95% CI: 1.4-1.8 years) vs. 1.2 years (95% CI: 1.0-1.4 years)]. The highest average LOLE occurred in males residing in the most disadvantaged areas with pancreatic [16.5 years (95% CI: 16.1-16.8 years) vs. 16.2 years (95% CI: 15.7-16.7 years)] and liver cancer [15.5 years (95% CI: 15.0-16.0 years) vs. 14.7 years (95% CI: 14.0-15.5 years)]. Females residing in the least disadvantaged areas with thyroid cancer [0.9 years (95% CI: 0.4-1.4 years) vs. 0.6 years (95% CI: 0.2-1.0 years)] or melanoma [0.9 years (95% CI: 0.8-1.1 years) vs. 0.7 years (95% CI: 0.5-0.8 years)] had the lowest average LOLE. CONCLUSIONS: Patients from the most disadvantaged areas had the highest LOLE with SES-based differences greatest for patients diagnosed with cancer at an early stage or cancers with higher survival rates, suggesting the need to prioritise early detection and reduce treatment-related barriers and survivorship challenges to improve life expectancy.

Computational Analysis of Polymeric Biodegradable and Customizable Airway Stent Designs.

The placement of endotracheal prostheses is a procedure used to treat tracheal lesions when no other surgical options are available. Unfortunately, this technique remains controversial. Both silicon and metallic stents are used with unpredictable success rates, as they have advantages but also disadvantages. Typical side effects include restenosis due to epithelial hyperplasia, obstruction and granuloma formation. Repeat interventions are often required. Biodegradable stents are promising in the field of cardiovascular biomechanics but are not yet approved for use in the respiratory system. The aim of the present study is to summarize important information and to evaluate the role of different geometrical features for the fabrication of a new tracheo-bronchial prosthesis prototype, which should be biodegradable, adaptable to the patient's lesion and producible by 3D printing. A parametric design and subsequent computational analysis using the finite element method is carried out. Two different stent designs are parameterized and analyzed. The biodegradable material chosen for simulations is polylactic acid. Experimental tests are conducted for assessing its mechanical properties. The role of the key design parameters on the radial force of the biodegradable prosthesis is investigated. The computational results allow us to elucidate the role of the pitch angle, the wire thickness and the number of cells or units, among other parameters, on the radial force. This work may be useful for the design of ad hoc airway stents according to the patient and type of lesion.

Implicit 3D Human Reconstruction Guided by Parametric Models and Normal Maps.

Accurate and robust 3D human modeling from a single image presents significant challenges. Existing methods have shown potential, but they often fail to generate reconstructions that match the level of detail in the input image. These methods particularly struggle with loose clothing. They typically employ parameterized human models to constrain the reconstruction process, ensuring the results do not deviate too far from the model and produce anomalies. However, this also limits the recovery of loose clothing. To address this issue, we propose an end-to-end method called IHRPN for reconstructing clothed humans from a single 2D human image. This method includes a feature extraction module for semantic extraction of image features. We propose an image semantic feature extraction aimed at achieving pixel model space consistency and enhancing the robustness of loose clothing. We extract features from the input image to infer and recover the SMPL-X mesh, and then combine it with a normal map to guide the implicit function to reconstruct the complete clothed human. Unlike traditional methods, we use local features for implicit surface regression. Our experimental results show that our IHRPN method performs excellently on the CAPE and AGORA datasets, achieving good performance, and the reconstruction of loose clothing is noticeably more accurate and robust.

GPS Data and Machine Learning Tools, a Practical and Cost-Effective Combination for Estimating Light Vehicle Emissions.

This paper focuses on the emissions of the three most sold categories of light vehicles: sedans, SUVs, and pickups. The research is carried out through an innovative methodology based on GPS and machine learning in real driving conditions. For this purpose, driving data from the three best-selling vehicles in Ecuador are acquired using a data logger with GPS included, and emissions are measured using a PEMS in six RDE tests with two standardized routes for each vehicle. The data obtained on Route 1 are used to estimate the gears used during driving using the K-means algorithm and classification trees. Then, the relative importance of driving variables is estimated using random forest techniques, followed by the training of ANNs to estimate CO2, CO, NOX, and HC. The data generated on Route 2 are used to validate the obtained ANNs. These models are fed with a dataset generated from 324, 300, and 316 km of random driving for each type of vehicle. The results of the model were compared with the IVE model and an OBD-based model, showing similar results without the need to mount the PEMS on the vehicles for long test drives. The generated model is robust to different traffic conditions as a result of its training and validation using a large amount of data obtained under completely random driving conditions.

Assessment of a fully-parametric thoraco-lumbar spine model generator with articulated ribcage.

The present paper describes a novel user-friendly fully-parametric thoraco-lumbar spine CAD model generator including the ribcage, based on 22 independent parameters (1 posterior vertebral body height per vertebra + 4 sagittal alignment parameters, namely pelvic incidence, sacral slope, L1-L5 lumbar lordosis, and T1-T12 thoracic kyphosis). Reliable third-order polynomial regression equations were implemented in Solidworks to analytically calculate 56 morphological dependent parameters and to automatically generate the spine CAD model based on primitive geometrical features. A standard spine CAD model, representing the case-study of an average healthy adult, was then created and positively assessed in terms of spinal anatomy, ribcage morphology, and sagittal profile. The immediate translation from CAD to FEM for relevant biomechanical analyses was successfully demonstrated, first, importing the CAD model into Abaqus, and then, iteratively calibrating the constitutive parameters of one lumbar and three thoracic FSUs, with particular interest on the hyperelastic material properties of the IVD, and the spinal and costo-vertebral ligaments. The credibility of the resulting lumbo-sacral and thoracic spine FEM with/without ribcage were assessed and validated throughout comparison with extensive in vitro and in vivo data both in terms of kinematics (range of motion) and dynamics (intradiscal pressure) either collected under pure bending moments and complex loading conditions (bending moments + axial compressive force).

Comparison of wave overtopping estimation models for urban beaches. Towards an early warning system on the Basque coast.

This study compares the performance of different wave overtopping estimation models at urban beaches. The models selected for comparison are the Mase et al. (2013) and EurOtop parametric models and the XBeach process-based model in surfbeat and non-hydrostatic mode. Seven energetic storms are selected between 2015 and 2022 with offshore significant wave height ranging between 3 m and 8 m and peak period between 12 s and 20 s to perform the model comparison. The information required to run and validate the models (beach slope, shoreface shape, absence/presence of overtopping) was collected for each storm from coastal videometry. To account for the uncertainties derived from the incident waves randomness and the bathymetry shape when using the process-based model, a series of simulations with random seed boundary conditions were run over two different realistic profile shapes for each storm. The present study is a pilot study on the beach of Zarautz; however, it can be extended to other beaches of the Basque coast. Results indicate that while Mase et al. (2013) and EurOtop tend to reasonably predict the absence or presence of overtopping events, they tend to underestimate the hazard level at the beach of Zarautz. Additionally, the beach underwater profile shape can affect the process-based model performance at intermediate intensity storms and to a lesser extend during moderate storms. Finally, the hazard level at the beach of Zarautz varies significantly alongshore due to the configuration of the seawall, highlighting the need for local adaptation measures. Considering that there is no model that systematically performs better than others, it might be reasonable to use model assemble techniques to draw conclusions from a probabilistic perspective.

Incidence and predictors of recurrent acute coronary syndrome among adult patients with acute coronary syndrome in West Amhara, Ethiopia: a multicenter retrospective follow-up study.

Introduction: Acute coronary syndrome (ACS) is the most common cause of morbidity and mortality in patients with coronary heart disease. Furthermore, the recurrence of this problem has significant adverse outcomes. However, there is insufficient information pertaining to this problem in Ethiopia; hence, this study aims to assess the incidence rate and identify the predictors of ACS recurrence in the West Amhara region. Methods: A retrospective follow-up study was conducted among 469 patients diagnosed with primary ACS. Data from the patient chart were collected using a pre-tested structured data extraction tool. The study employed the Weibull regression analysis model, and the effect size was measured using an adjusted hazard ratio (HR) with a 95% confidence interval (CI). The statistical significance of the findings was established based on a p-value <0.05. Result: A total of 429 patients were included in the final analysis [average age, 60 ± 13.9 years; and 245 (57.1%) men]. A total of 53 patients (12.35%; 95% CI: 9.55%-15.83%) experienced recurrent ACS. The overall risk time was found to be 93,914 days (3,130.47 months), and the recurrence rate was 17/1,000 patients/month. The identified predictors were the typical symptoms of ACS such as syncope (HR: 3.54, p = 0.013), fatigue (HR: 5.23, p < 0.001), history of chronic kidney disease (HR: 8.22, p < 0.001), left ventricular ejection fraction of <40% (HR: 2.34, p = 0.009), not taking in-hospital treatments [aspirin (HR: 9.22, p < 0.001), clopidogrel (HR: 4.11, p = 0.001), statins (HR: 2.74, p = 0.012)], and medication at discharge [statins (HR: 4.56, p < 0.001)]. Conclusion: This study found a higher incidence rate of recurrent ACS. Hence, the implementation of guideline-recommended anti-ischemic treatment should be strengthened.

A geometry-based finite element tool for evaluating mitral valve biomechanics.

Mitral valve function depends on its complex geometry and tissue health, with alterations in shape and tissue response affecting the long-term restorarion of function. Previous computational frameworks for biomechanical assessment are mostly based on patient-specific geometries; however, these are not flexible enough to yield a variety of models and assess mitral closure for individually tuned morphological parameters or material property representations. This study details the finite element approach implemented in our previously developed toolbox to assess mitral valve biomechanics and showcases its flexibility through the generation and biomechanical evaluation of different models. A healthy valve geometry was generated and its computational predictions for biomechanics validated against data in the literature. Moreover, two mitral valve models including geometric alterations associated with disease were generated and analysed. The healthy mitral valve model yielded biomechanical predictions in terms of valve closure dynamics, leaflet stresses and papillary muscle and chordae forces comparable to previous computational and experimental studies. Mitral valve function was compromised in geometries representing disease, expressed by the presence of regurgitating areas, elevated stress on the leaflets and unbalanced subvalvular apparatus forces. This showcases the flexibility of the toolbox concerning the generation of a range of mitral valve models with varying geometric definitions and material properties and the evaluation of their biomechanics.

Predicting food waste in households with children: socio-economic and food-related behavior factors.

Introduction: The consumption phase accounts for approximately half of the food waste generated within the food system. Numerous studies have identified families with children as the primary contributors to food waste. The aims of this paper is to enhance the comprehension of food waste behaviors in households with children by characterizing it and studying how socioeconomic characteristics and food-related behaviors can predict it. Methods: A survey was conducted among 806 families with children, categorized by the child's age and family structure. The study utilized descriptive statistics to summarize the food waste behaviors and binary regression to evaluate the predictive abilities of 12 variable related to the socio-economic characteristic, purchase, and preparation behaviors and diet quality factors. Results: Perishable food items, such as fruits, vegetables, cereal-based product, and dairy products, were the primary items wasted in households with children. Two patterns of food waste were identified: inadequate food management leading to small amounts of waste in families with young and middle-aged children, and over-purchasing perishable items leading to waste in other households with children. Household type and purchasing habits were significant predictors, while the purchaser's age and buying channel showed lower predictive capacity. Discussion: Policies to reduce food waste should prioritize raising awareness among children, promoting good practices at the household level, and creating favorable conditions during purchases. Strategies include enlisting children's participation in meal planning and food preparation as well as limiting the promotion of ultra-processed products and incentivizing the sale of bulk products at supermarket.

An improved multiply robust estimator for the average treatment effect.

BACKGROUND: In observational studies, double robust or multiply robust (MR) approaches provide more protection from model misspecification than the inverse probability weighting and g-computation for estimating the average treatment effect (ATE). However, the approaches are based on parametric models, leading to biased estimates when all models are incorrectly specified. Nonparametric methods, such as machine learning or nonparametric double robust approaches, are robust to model misspecification, but the efficiency of nonparametric methods is low. METHOD: In the study, we proposed an improved MR method combining parametric and nonparametric models based on the previous MR method (Han, JASA 109(507):1159-73, 2014) to improve the robustness to model misspecification and the efficiency. We performed comprehensive simulations to evaluate the performance of the proposed method. RESULTS: Our simulation study showed that the MR estimators with only outcome regression (OR) models, where one of the models was a nonparametric model, were the most recommended because of the robustness to model misspecification and the lowest root mean square error (RMSE) when including a correct parametric OR model. And the performance of the recommended estimators was comparative, even if all parametric models were misspecified. As an application, the proposed method was used to estimate the effect of social activity on depression levels in the China Health and Retirement Longitudinal Study dataset. CONCLUSIONS: The proposed estimator with nonparametric and parametric models is more robust to model misspecification.

Extra-Articular Distal Humerus Plate 3D Model Creation by Using the Method of Anatomical Features.

Proper fixation techniques are crucial in orthopedic surgery for the treatment of various medical conditions. Fractures of the distal humerus can occur due to either high-energy trauma with skin rupture or low-energy trauma in osteoporotic bone. The recommended surgical approach for treating these extra-articular distal humerus fractures involves performing an open reduction and internal fixation procedure using plate implants. This surgical intervention plays a crucial role in enhancing patient recovery and minimizing soft tissue complications. Dynamic Compression Plates (DCPs) and Locking Compression Plates (LCPs) are commonly used for bone fixation, with LCP extra-articular distal humerus plates being the preferred choice for extra-articular fractures. These fixation systems have anatomically shaped designs that provide angular stability to the bone. However, depending on the shape and position of the bone fracture, additional plate bending may be required during surgery. This can pose challenges such as increased surgery time and the risk of incorrect plate shaping. To enhance the accuracy of plate placement, the study introduces the Method of Anatomical Features (MAF) in conjunction with the Characteristic Product Features methodology (CPF). The utilization of the MAF enables the development of a parametric model for the contact surface between the plate and the humerus. This model is created using specialized Referential Geometrical Entities (RGEs), Constitutive Geometrical Entities (CGEs), and Regions of Interest (ROI) that are specific to the human humerus bone. By utilizing this anatomically tailored contact surface model, the standard plate model can be customized (bent) to precisely conform to the distinct shape of the patient's humerus bone during the pre-operative planning phase. Alternatively, the newly designed model can be fabricated using a specific manufacturing technology. This approach aims to improve geometrical accuracy of plate fixation, thus optimizing surgical outcomes and patient recovery.

Determination of a Representative and 3D-Printable Root Canal Geometry for Endodontic Investigations and Pre-Clinical Endodontic Training-An Ex Vivo Study.

Models of artificial root canals are used in several fields of endodontic investigations and pre-clinical endodontic training. They allow the physical testing of dental treatments, the operating of instruments used and the interaction between these instruments and the tissues. Currently, a large number of different artificial root canal models exist whose geometry is created either on the basis of selected natural root canal systems or to represent individual geometrical properties. Currently, only a few geometric properties such as the root canal curvature or the endodontic working width are taken into consideration when generating these models. To improve the representational capability of the artificial root canal models, the aim of the current study is therefore to generate an artificial root canal based on the statistical evaluation of selected natural root canals. Here, the approach introduced by Kucher for determining the geometry of a root canal model is used, which is based on the measurement and statistical evaluation of the root canal center line's curvatures and their cross-sectional dimensions. Using the example of unbranched distal root canals of mandibular molars (n = 29), an artificial root canal model representing the mean length, curvature, torsion and cross-sectional dimensions of these teeth could be derived.

3D vessel extraction using a scale-adaptive hybrid parametric tracker.

3D vessel extraction has great significance in the diagnosis of vascular diseases. However, accurate extraction of vessels from computed tomography angiography (CTA) data is challenging. For one thing, vessels in different body parts have a wide range of scales and large curvatures; for another, the intensity distributions of vessels in different CTA data vary considerably. Besides, surrounding interfering tissue, like bones or veins with similar intensity, also seriously affects vessel extraction. Considering all the above imaging and structural features of vessels, we propose a new scale-adaptive hybrid parametric tracker (SAHPT) to extract arbitrary vessels of different body parts. First, a geometry-intensity parametric model is constructed to calculate the geometry-intensity response. While geometry parameters are calculated to adapt to the variation in scale, intensity parameters can also be estimated to meet non-uniform intensity distributions. Then, a gradient parametric model is proposed to calculate the gradient response based on a multiscale symmetric normalized gradient filter which can effectively separate the target vessel from surrounding interfering tissue. Last, a hybrid parametric model that combines the geometry-intensity and gradient parametric models is constructed to evaluate how well it fits a local image patch. In the extraction process, a multipath spherical sampling strategy is used to solve the problem of anatomical complexity. We have conducted many quantitative experiments using the synthetic and clinical CTA data, asserting its superior performance compared to traditional or deep learning-based baselines.

Multilevel survival analysis of factors associated with under-five mortality in Manipur.

Background: Child mortality is a major public health issue. The studies on under-five mortality that ignore the hierarchical facts mislead the interpretation of the results due to observations in the same cluster sharing common cluster-level random effects. Objectives: The present study uses a multilevel model to analyze under-five mortality and identify the significant factors for under-five mortality in Manipur. Methods: National Family Health Survey-5 (2019-21) data are used in the present study. A multilevel mixed-effect Weibull parameter survival model was fitted to determine the factors affecting under-five mortality. We construct three-level data, individual levels are nested within primary sampling units (PSUs), and PSUs are nested within districts. Results: Out of the 3225 under-five children, 85 (2.64%) died. The three-level mixed-effects Weibull parametric survival model with PSUs nested within the districts, the likelihood-ratio test with Chi-square value = 10.98 and P = 0.004 < 0.05 indicated that the model with random-intercept effects model with PSUs nested within the districts fits the data better than the fixed effect model. The four covariates, namely the number of birth in the last 5 years, age of mother at first birth, use of contraceptive, and size of child at birth, were found as the risk factor for under-five mortality at a 5% level of significance. Conclusions: In the random-intercept effect model, the two estimated variances of the random-intercept effects for district and PSU levels are 0.27 and 0.31, respectively. The values indicate variations (unobserved heterogeneities) in the risk of death of the under-five children between districts and PSUs levels.

Finite element analysis of conductive hearing loss caused by fixation and detachment of ligament and tendon in the middle ear.

BACKGROUND AND OBJECTIVE: The fixation of ligament and tendon of the middle ear often occurs after chronic otitis media surgery. However, there are relatively few studies on the effect of ligament and tendon on sound transmission in the human middle ear. Here, the finite element model and lumped parameter model are used to study the effect of ligament and tendon fixation and detachment on sound transmission in human ear. METHODS: In this paper, the finite element model including the external auditory canal, middle ear and simplified inner ear is used to calculate and compare the middle ear frequency response of the normal and tympanosclerosis under pure tone stimulation. In addition, the lumped parametric model is taken into account to illustrate the effect of ligament and tendon stiffness on the human ear transmission system. RESULTS: The results indicate that the motion of the tympanic membrane and stapes is reduced by ligament and tendon fixation. Although ligament and tendon detachment have a limited effect in the piston-motion direction, the stability of motion in the plane perpendicular to the piston-motion direction is significantly reduced. Most significantly, the ligament and tendon fixation cause a hearing effect of about 18 dB, which is greater in the plane perpendicular to the piston-motion direction after ligament and tendon detachment than in the piston-motion direction. CONCLUSIONS: In this study, the calculation accuracy of the lumped parameter and the finite element model is studied, and the effect of ligament and tendon on hearing loss is further explored through the finite element model with high calculation accuracy, which is helpful to understand the role of ligament and tendon in the sound transmission mechanism of the human middle ear. The study of ligament and tendon on conductive hearing loss provides a reference for clinical treatment of tympanosclerosis.

A parametric geometry model of the aortic valve for subject-specific blood flow simulations using a resistive approach.

Cardiac valves simulation is one of the most complex tasks in cardiovascular modeling. Fluid-structure interaction is not only highly computationally demanding but also requires knowledge of the mechanical properties of the tissue. Therefore, an alternative is to include valves as resistive flow obstacles, prescribing the geometry (and its possible changes) in a simple way, but, at the same time, with a geometry complex enough to reproduce both healthy and pathological configurations. In this work, we present a generalized parametric model of the aortic valve to obtain patient-specific geometries that can be included into blood flow simulations using a resistive immersed implicit surface (RIIS) approach. Numerical tests are presented for geometry generation and flow simulations in aortic stenosis patients whose parameters are extracted from ECG-gated CT images.

3D real-time human reconstruction with a single RGBD camera.

3D human reconstruction is an important technology connecting the real world and the virtual world, but most of previous work needs expensive computing resources, making it difficult in real-time scenarios. We propose a lightweight human body reconstruction system based on parametric model, which employs only one RGBD camera as input. To generate a human model end to end, we build a fast and lightweight deep-learning network named Fast Body Net (FBN). The network pays more attention on the face and hands to enrich the local details. Additionally, we train a denoising auto-encoder to reduce unreasonable states of human model. Due to the lack of human dataset based on RGBD images, we propose an Indoor-Human dataset to train the network, which contains a total of 2500 frames of action data of five actors collected by Azure Kinect camera. Depth images avoid using RGB to extract depth features, which makes FBN lightweight and high-speed in reconstructing parametric human model. Qualitative and quantitative analysis on experimental results show that our method can improve at least 57% in efficiency with similar accuracy, as compared to state-of-the-art methods. Through our study, it is also demonstrated that consumer-grade RGBD cameras can provide great applications in real-time display and interaction for virtual reality.

Non-parametric mixture modeling of cognitive psychological data: A new method to disentangle hidden strategies.

In a wide variety of cognitive domains, participants have access to several alternative strategies to perform a particular task and, on each trial, one specific strategy is selected and executed. Determining how many strategies are used by a participant as well as their identification at a trial level is a challenging problem for researchers. In the current paper, we propose a new method - the non-parametric mixture model - to efficiently disentangle hidden strategies in cognitive psychological data, based on observed response times. The developed method derived from standard hidden Markov modeling. Importantly, we used a model-free approach where a particular shape of a response time distribution does not need to be assumed. This has the considerable advantage of avoiding potentially unreliable results when an inappropriate response time distribution is assumed. Through three simulation studies and two applications to real data, we repeatedly demonstrated that the non-parametric mixture model is able to reliably recover hidden strategies present in the data as well as to accurately estimate the number of concurrent strategies. The results also showed that this new method is more efficient than a standard parametric approach. The non-parametric mixture model is therefore a useful statistical tool for strategy identification that can be applied in many areas of cognitive psychology. To this end, practical guidelines are provided for researchers wishing to apply the non-parametric mixture models on their own data set.

Estimation of the Average Causal Effect in Longitudinal Data With Time-Varying Exposures: The Challenge of Nonpositivity and the Impact of Model Flexibility.

There are important challenges to the estimation and identification of average causal effects in longitudinal data with time-varying exposures. Here, we discuss the difficulty in meeting the positivity condition. Our motivating example is the per-protocol analysis of the Effects of Aspirin in Gestation and Reproduction (EAGeR) Trial. We estimated the average causal effect comparing the incidence of pregnancy by 26 weeks that would have occurred if all women had been assigned to aspirin and complied versus the incidence if all women had been assigned to placebo and complied. Using flexible targeted minimum loss-based estimation, we estimated a risk difference of 1.27% (95% CI: -9.83, 12.38). Using a less flexible inverse probability weighting approach, the risk difference was 5.77% (95% CI: -1.13, 13.05). However, the cumulative probability of compliance conditional on covariates approached 0 as follow-up accrued, indicating a practical violation of the positivity assumption, which limited our ability to make causal interpretations. The effects of nonpositivity were more apparent when using a more flexible estimator, as indicated by the greater imprecision. When faced with nonpositivity, one can use a flexible approach and be transparent about the uncertainty, use a parametric approach and smooth over gaps in the data, or target a different estimand that will be less vulnerable to positivity violations.

Estimation of left ventricular parameters based on deep learning method.

Estimating material properties of personalized human left ventricular (LV) modelling is a central problem in biomechanical studies. In this work we use deep learning (DL) method to evaluating the passive myocardial mechanical properties inversely. In the first part of the paper, we establish a standardized geometric model of the LV. The geometric model parameters are optimized based on 27 different healthy volunteers. In the second part, we use statistical methods and Latin hypercube sampling (LHS) to obtain the geometric parameters data. The LV myocardium is described using a structure-based orthotropic Holzapfel-Ogden constitutive law. The LV diastolic pressure-volume (PV) curves are calculated by numerical simulation. Tn the third part, we establish the multiple neural networks to pblackict PV curve parameters. Then, instead of using constrained optimization problems to solve constitutive parameters, DL was used to establish the nonlinear mapping relationship of geometric parameters, PV curve parameters and constitutive parameters. The results show that the deep learning method can greatly improve the computational efficiency of numerical simulation and increase the possibility of its application in rapid feedback of clinical data.