Neural network-based left ventricle geometry prediction from CMR images with application in biomechanics

Romaszko, Łukasz; Borowska, Agnieszka; Lazarus, Alan; Dalton, David R.; Berry, Colin; Luo, Xiaoyu; Husmeier, Dirk; Gao, Hao

doi:10.1016/j.artmed.2021.102140

Cited by 11 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, we note that the goal of our group's research agenda is to make the whole inference pipeline automatic, that is to estimate the myocardial properties directly from CMR images. One of the stepping stones towards that goal was our work on an automatic framework for LV geometry prediction directly from CMR images based on convolutional neural networks 72 …”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian optimisation for efficient parameter inference in a cardiac mechanics model of the left ventricle

Borowska

Gao

Lazarus

et al. 2022

Numer Methods Biomed Eng

Self Cite

View full text Add to dashboard Cite

We consider parameter inference in cardio‐mechanic models of the left ventricle, in particular the one based on the Holtzapfel‐Ogden (HO) constitutive law, using clinical in vivo data. The equations underlying these models do not admit closed form solutions and hence need to be solved numerically. These numerical procedures are computationally expensive making computational run times associated with numerical optimisation or sampling excessive for the uptake of the models in the clinical practice. To address this issue, we adopt the framework of Bayesian optimisation (BO), which is an efficient statistical technique of global optimisation. BO seeks the optimum of an unknown black‐box function by sequentially training a statistical surrogate‐model and using it to select the next query point by leveraging the associated exploration‐exploitation trade‐off. To guarantee that the estimates based on the in vivo data are realistic also for high‐pressures, unobservable in vivo, we include a penalty term based on a previously published empirical law developed using ex vivo data. Two case studies based on real data demonstrate that the proposed BO procedure outperforms the state‐of‐the‐art inference algorithm for the HO constitutive law.

show abstract

Section: Discussionmentioning

confidence: 99%

“…One of the stepping stones towards that goal was our work on an automatic framework for LV geometry prediction directly from CMR images based on convolutional neural networks. 72 …”

Section: Discussionmentioning

confidence: 99%

Bayesian optimisation for efficient parameter inference in a cardiac mechanics model of the left ventricle

Borowska

Gao

Lazarus

et al. 2022

Numer Methods Biomed Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several approaches have been proposed to incorporate prior knowledge of cardiac anatomy in image segmentation and geometry reconstruction tasks. This includes the use of shape priors (Duan et al, 2019;Oktay et al, 2017), constraining the reconstructed geometry to lie on a linear PCA subspace (Romaszko et al, 2021), as well as warping methods based on a low-dimensional embedding of the LV anatomy found with a constrained variational autoencoder (Painchaud et al, 2020). To date, however, incorporating prior anatomical knowledge into volume estimation tasks has received less attention.…”

Section: Application Of Deep Learning and Limitationsmentioning

confidence: 99%

“…To obtain the ground truth values of the LV cavity volumes, we still rely on manual segmentation. Manual segmentation is still the current state of the art for reconstruction of ventricular geometry (Romaszko et al, 2021). In this study, we used 5 to 8 short-axis images, as well as 3 long-axis images, to perform manual segmentation at the early diastole stage of the heart using a home-made graphical user interface (GUI).…”

Section: Manual Segmentationmentioning

confidence: 99%

Image-based estimation of the left ventricular cavity volume using deep learning and Gaussian process with cardio-mechanical applications

Rabbani

Gao

Lazarus

et al. 2023

Computerized Medical Imaging and Graphics

Self Cite

View full text Add to dashboard Cite

“…The fast and accurate predictions made by the deep learning model have been used in diverse elds of studies of cardiovascular mechanics (Dabiri et al 2020;Galati et al 2022; Kadem et al 2022;Liang et al 2018;Madani et al 2019). Moreover, emerging advancements in medical imaging techniques and computational modeling methods enable the generation of patientspeci c computational ventricular models (Litjens et al 2019;Miller et al 2021;Romaszko et al 2021; Tang et al 2010). As a result, the development of deep learning models in conjunction with constitutive analysis represents a feasible opportunity for conducting further clinical studies using non-invasive procedures in realistic patient-speci c settings.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Model for the Identification of Active Contraction Properties of the Myocardium Using Limited Clinical Metrics

Nobrega

Mao

2023

Preprint

View full text Add to dashboard Cite

Technological breakthroughs have enhanced our understanding of myocardial mechanics and physiological responses to detect early disease indicators. Using constitutive models to represent myocardium structure is critical for understanding the intricacies of such complex tissues. Several models have been developed to depict both passive response and active contraction of myocardium, however they require careful adjustment of material parameters for patient-specific scenarios and substantial time and computing resources. Thus, most models are unsuitable for employment outside of research. Deep learning (DL) has sparked interest in data-driven computational modeling for complex system analysis. We developed a DL model for assessing and forecasting the behavior of an active contraction model of the left ventricular (LV) myocardium under a patient-specific clinical setting. Our original technique analyzes a context in which clinical measures are limited: as model input, just a handful of clinical parameters and a pressure-volume (PV) loop are required. This technique aims to bridge the gap between theoretical calculations and clinical applications by allowing doctors to use traditional metrics without administering additional data and processing resources. Our DL model's main objectives are to produce a waveform of active contraction property that properly portrays patient-specific data during a cardiac cycle and to estimate fiber angles at the endocardium and epicardium. Our model accurately represented the mechanical response of the LV myocardium for various PV curves, and it applies to both idealized and patient-specific geometries. Integrating artificial intelligence with constitutive-based models allows for the autonomous selection of hidden model parameters and facilitates their application in clinical settings.

show abstract

Neural network-based left ventricle geometry prediction from CMR images with application in biomechanics

Cited by 11 publications

References 35 publications

Bayesian optimisation for efficient parameter inference in a cardiac mechanics model of the left ventricle

Bayesian optimisation for efficient parameter inference in a cardiac mechanics model of the left ventricle

Image-based estimation of the left ventricular cavity volume using deep learning and Gaussian process with cardio-mechanical applications

A Deep Learning Model for the Identification of Active Contraction Properties of the Myocardium Using Limited Clinical Metrics

Contact Info

Product

Resources

About