AI in medical imaging informatics: current challenges and future directions
This paper reviews state-of-the-art research solutions across the spectrum of medical
imaging informatics, discusses clinical translation, and provides future directions for …
imaging informatics, discusses clinical translation, and provides future directions for …
Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers
M Khened, VA Kollerathu, G Krishnamurthi - Medical image analysis, 2019 - Elsevier
Deep fully convolutional neural network (FCN) based architectures have shown great
potential in medical image segmentation. However, such architectures usually have millions …
potential in medical image segmentation. However, such architectures usually have millions …
Real-time multilead convolutional neural network for myocardial infarction detection
W Liu, M Zhang, Y Zhang, Y Liao… - IEEE journal of …, 2017 - ieeexplore.ieee.org
In this paper, a novel algorithm based on a convolutional neural network (CNN) is proposed
for myocardial infarction detection via multilead electrocardiogram (ECG). A beat …
for myocardial infarction detection via multilead electrocardiogram (ECG). A beat …
[HTML][HTML] Personalising left-ventricular biophysical models of the heart using parametric physics-informed neural networks
We present a parametric physics-informed neural network for the simulation of personalised
left-ventricular biomechanics. The neural network is constrained to the biophysical problem …
left-ventricular biomechanics. The neural network is constrained to the biophysical problem …
[HTML][HTML] Machine learning approaches for myocardial motion and deformation analysis
Information about myocardial motion and deformation is key to differentiate normal and
abnormal conditions. With the advent of approaches relying on data rather than pre …
abnormal conditions. With the advent of approaches relying on data rather than pre …
Topology-preserving shape reconstruction and registration via neural diffeomorphic flow
Abstract Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed
distance functions learned through deep neural nets. Recently DIFs-based methods have …
distance functions learned through deep neural nets. Recently DIFs-based methods have …
Activator anion influences the nanostructure of alkali-activated slag cements
Alkali-activated materials are promising low-carbon alternatives to Portland cement;
however, there remains an absence of a fundamental understanding of the effect of different …
however, there remains an absence of a fundamental understanding of the effect of different …
Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow
We propose a method to classify cardiac pathology based on a novel approach to extract
image derived features to characterize the shape and motion of the heart. An original semi …
image derived features to characterize the shape and motion of the heart. An original semi …
Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture
Abstract Changes in mechanical properties of myocardium caused by a infarction can lead
to kinematic abnormalities. This phenomenon has inspired us to develop this work for …
to kinematic abnormalities. This phenomenon has inspired us to develop this work for …
Sdf4chd: Generative modeling of cardiac anatomies with congenital heart defects
Congenital heart disease (CHD) encompasses a spectrum of cardiovascular structural
abnormalities, often requiring customized treatment plans for individual patients …
abnormalities, often requiring customized treatment plans for individual patients …