Development of automated neural network prediction for echocardiographic left ventricular ejection fraction.

Introduction: The echocardiographic measurement of left ventricular ejection fraction (LVEF) is fundamental to the diagnosis and classification of patients with heart failure (HF).

Methods: This paper aimed to quantify LVEF automatically and accurately with the proposed pipeline method based on deep neural networks and ensemble learning. Within the pipeline, an Atrous Convolutional Neural Network (ACNN) was first trained to segment the left ventricle (LV), before employing the area-length formulation based on the ellipsoid single-plane model to calculate LVEF values.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches.

Learning a Model-Driven Variational Network for Deformable Image Registration.

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this issue and meanwhile retain the fast inference speed of deep learning, we propose VR-Net, a novel cascaded variational network for unsupervised deformable image registration. Using a variable splitting optimization scheme, we first convert the image registration problem, established in a generic variational framework, into two sub-problems, one with a point-wise, closed-form solution and the other one being a denoising problem.

Immortalisation of primary human alveolar epithelial lung cells using a non-viral vector to study respiratory bioreactivity in vitro.

To overcome the scarcity of primary human alveolar epithelial cells for lung research, and the limitations of current cell lines to recapitulate the phenotype, functional and molecular characteristics of the healthy human alveolar epithelium, we have developed a new method to immortalise primary human alveolar epithelial lung cells using a non-viral vector to transfect the telomerase catalytic subunit (hTERT) and the simian virus 40 large-tumour antigen (SV40). Twelve strains of immortalised cells (ICs) were generated and characterised using molecular, immunochemical and morphological techniques. Cell proliferation and sensitivity to polystyrene nanoparticles (PS) were evaluated.

Microphysiological lung models to evaluate the safety of new pharmaceutical modalities: a biopharmaceutical perspective.

The lung is a complex organ; it is both the initial barrier for inhaled agents and the site of metabolism and therapeutic effect for a subset of systemically administered drugs. Comprised of more than 40 cell types that are responsible for various important functions, the lung's complexity contributes to the subsequent challenges in developing complex in vitro co-culture models (also called microphysiological systems (MPS), complex in vitro models or organs-on-a-chip). Although there are multiple considerations and limitations in the development and qualification of such in vitro systems, MPS exhibit great promise in the fields of pharmacology and toxicology.