Deep Learning-Based Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction: A Point-of-Care Solution.

BACKGROUND: We have recently tested an automated machine-learning algorithm that quantifies left ventricular (LV) ejection fraction (EF) from guidelines-recommended apical views. However, in the point-of-care (POC) setting, apical 2-chamber views are often difficult to obtain, limiting the usefulness of this approach. Since most POC physicians often rely on visual assessment of apical 4-chamber and parasternal long-axis views, our algorithm was adapted to use either one of these 3 views or any combination. This study aimed to (1) test the accuracy of these automated estimates; (2) determine whether they could be used to accurately classify LV function. METHODS: Reference EF was obtained using conventional biplane measurements by experienced echocardiographers. In protocol 1, we used echocardiographic images from 166 clinical examinations. Both automated and reference EF values were used to categorize LV function as hyperdynamic (EF>73%), normal (53%-73%), mildly-to-moderately (30%-52%), or severely reduced (<30%). Additionally, LV function was visually estimated for each view by 10 experienced physicians. Accuracy of the detection of reduced LV function (EF<53%) by the automated classification and physicians' interpretation was assessed against the reference classification. In protocol 2, we tested the new machine-learning algorithm in the POC setting on images acquired by nurses using a portable imaging system. RESULTS: Protocol 1: the agreement with the reference EF values was good (intraclass correlation, 0.86-0.95), with biases <2%. Machine-learning classification of LV function showed similar accuracy to that by physicians in most views, with only 10% to 15% cases where it was less accurate. Protocol 2: the agreement with the reference values was excellent (intraclass correlation=0.84) with a minimal bias of 2.5±6.4%. CONCLUSIONS: The new machine-learning algorithm allows accurate automated evaluation of LV function from echocardiographic views commonly used in the POC setting. This approach will enable more POC personnel to accurately assess LV function.

Achieving Minimal Heat Conductivity by Ballistic Confinement in Phononic Metalattices.

Controlling the thermal conductivity of semiconductors is of practical interest in optimizing the performance of thermoelectric and phononic devices. The insertion of inclusions of nanometer size in a semiconductor is an effective means of achieving such control; it has been proposed that the thermal conductivity of silicon could be reduced to 1 W/m/K using this approach and that a minimum in the heat conductivity would be reached for some optimal size of the inclusions. Yet the experimental verification of this design rule has been limited. In this work, we address this question by studying the thermal properties of silicon metalattices that consist of a periodic distribution of spherical inclusions with radii from 7 to 30 nm, embedded into silicon. Experimental measurements confirm that the thermal conductivity of silicon metalattices is as low as 1 W/m/K for silica inclusions and that this value can be further reduced to 0.16 W/m/K for silicon metalattices with empty pores. A detailed model of ballistic phonon transport suggests that this thermal conductivity is close to the lowest achievable by tuning the radius and spacing of the periodic inhomogeneities. This study is a significant step in elucidating the scaling laws that dictate ballistic heat transport at the nanoscale in silicon and other semiconductors.

Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction Without Volume Measurements Using a Machine Learning Algorithm Mimicking a Human Expert.

BACKGROUND: Echocardiographic quantification of left ventricular (LV) ejection fraction (EF) relies on either manual or automated identification of endocardial boundaries followed by model-based calculation of end-systolic and end-diastolic LV volumes. Recent developments in artificial intelligence resulted in computer algorithms that allow near automated detection of endocardial boundaries and measurement of LV volumes and function. However, boundary identification is still prone to errors limiting accuracy in certain patients. We hypothesized that a fully automated machine learning algorithm could circumvent border detection and instead would estimate the degree of ventricular contraction, similar to a human expert trained on tens of thousands of images. METHODS: Machine learning algorithm was developed and trained to automatically estimate LVEF on a database of >50 000 echocardiographic studies, including multiple apical 2- and 4-chamber views (AutoEF, BayLabs). Testing was performed on an independent group of 99 patients, whose automated EF values were compared with reference values obtained by averaging measurements by 3 experts using conventional volume-based technique. Inter-technique agreement was assessed using linear regression and Bland-Altman analysis. Consistency was assessed by mean absolute deviation among automated estimates from different combinations of apical views. Finally, sensitivity and specificity of detecting of EF ≤35% were calculated. These metrics were compared side-by-side against the same reference standard to those obtained from conventional EF measurements by clinical readers. RESULTS: Automated estimation of LVEF was feasible in all 99 patients. AutoEF values showed high consistency (mean absolute deviation =2.9%) and excellent agreement with the reference values: r=0.95, bias=1.0%, limits of agreement =±11.8%, with sensitivity 0.90 and specificity 0.92 for detection of EF ≤35%. This was similar to clinicians' measurements: r=0.94, bias=1.4%, limits of agreement =±13.4%, sensitivity 0.93, specificity 0.87. CONCLUSIONS: Machine learning algorithm for volume-independent LVEF estimation is highly feasible and similar in accuracy to conventional volume-based measurements, when compared with reference values provided by an expert panel.

Donor and acceptor levels of organic photovoltaic compounds from first principles.

Accurate and efficient approaches to predict the optical properties of organic semiconducting compounds could accelerate the search for efficient organic photovoltaic materials. Nevertheless, predicting the optical properties of organic semiconductors has been plagued by the inaccuracy or computational cost of conventional first-principles calculations. In this work, we demonstrate that orbital-dependent density-functional theory based upon Koopmans' condition [Phys. Rev. B, 2010, 82, 115121] is apt for describing donor and acceptor levels for a wide variety of organic molecules, clusters, and oligomers within a few tenths of an electron-volt relative to experiment, which is comparable to the predictive performance of many-body perturbation theory methods at a fraction of the computational cost.

Switchable conductance in functionalized carbon nanotubes via reversible sidewall bond cleavage.

We propose several covalent functionalizations for carbon nanotubes that display switchable on/off conductance in metallic tubes. The switching action is achieved by reversible control of bond-cleavage chemistry in [1 + 2] cycloadditions via the sp(3) ⇌ sp(2) rehybridization that it induces; this leads to remarkable changes of conductance even at very low degrees of functionalization. Reversible bond-cleavage chemistry is achieved by identifying addends that provide optimal compensation between the bond-preserving through-space π orbital interactions with the tube against the bond-breaking strain energy of the cyclopropane moiety. Several strategies for real-time control, based on redox or hydrolysis reactions, cis-trans isomerization or excited-state proton transfer are proposed. Such designer functional groups would allow for the first time direct control of the electrical properties of metallic carbon nanotubes, with extensive applications in nanoscale devices.