Abstract
Speckle tracking echocardiography (STE) is a clinical tool to noninvasively assess regional myocardial function through the quantification of regional motion and deformation. Even if the time resolution of STE can be improved by high-frame-rate (HFR) imaging, dedicated HFR STE algorithms have to be developed to detect very small interframe motions. Therefore, in this article, we propose a novel 2-D STE method, purposely developed for HFR echocardiography. The 2-D motion estimator consists of a two-step algorithm based on the 1-D cross correlations to separately estimate the axial and lateral displacements. The method was first optimized and validated on simulated data giving an accuracy of 3.3% and 10.5% for the axial and lateral estimates, respectively. Then, it was preliminarily tested in vivo on ten healthy volunteers showing its clinical applicability and feasibility. Moreover, the extracted clinical markers were in the same range as those reported in the literature. Also, the estimated peak global longitudinal strain was compared with that measured with a clinical scanner showing good correlation and negligible differences (-20.94% versus -20.31%, ${p}$ -value = 0.44). In conclusion, a novel algorithm for STE was developed: the radio frequency (RF) signals were preferred for the axial motion estimation, while envelope data were preferred for the lateral motion. Furthermore, using 2-D kernels, even for 1-D cross correlation, makes the method less sensitive to noise. © 1986-2012 IEEE.

Abstract
Currently, lung cancer is the most lethal in the world. In order to make screening and follow-up a little more systematic, guidelines have been proposed. Therefore, this study aimed to create a diagnostic support approach by providing a patient label based on the LUNG-RADSTM guidelines. The only input required by the system is the nodule centroid to take the region of interest for the input of the classification system. With this in mind, two deep learning networks were evaluated: a Wide Residual Network and a DenseNet. Taking into account the annotation uncertainty we proposed to use sample weights that are introduced in the loss function, allowing nodules with a high agreement in the annotation process to take a greater impact on the training error than its counterpart. The best result was achieved with the Wide Residual Network with sample weights achieving a nodule-wise LUNG-RADSTM labelling accuracy of 0.735 +/- 0.003.

Abstract
Diabetic macular edema is a leading cause of visual loss for patients with diabetes. While diagnosis can only be performed by optical coherence tomography, diabetic macular edema risk assessment is often performed in eye fundus images in screening scenarios through the detection of hard exudates. Such screening scenarios are often associated with large amounts of data, high costs and high burden on specialists, motivating then the development of methodologies for automatic diabetic macular edema risk prediction. Nevertheless, significant dataset domain bias, due to different acquisition equipment, protocols and/or different populations can have significantly detrimental impact on the performance of automatic methods when transitioning to a new dataset, center or scenario. As such, in this study, a method based on residual neural networks is proposed for the classification of diabetic macular edema risk. This method is then validated across multiple public datasets, simulating the deployment in a multi-center setting and thereby studying the method’s generalization capability and existing dataset domain bias. Furthermore, the method is tested on a private dataset which more closely represents a realistic screening scenario. An average area under the curve across all public datasets of 0.891 ± 0.013 was obtained with a ResNet50 architecture trained on a limited amount of images from a single public dataset (IDRiD). It is also shown that screening scenarios are significantly more challenging and that training across multiple datasets leads to an improvement of performance (area under the curve of 0.911 ± 0.009). © Springer Nature Switzerland AG 2020.

Abstract
Lung cancer is the deadliest type of cancer worldwide and late detection is the major factor for the low survival rate of patients. Low dose computed tomography has been suggested as a potential screening tool but manual screening is costly and time-consuming. This has fuelled the development of automatic methods for the detection, segmentation and characterisation of pulmonary nodules. In spite of promising results, the application of automatic methods to clinical routine is not straightforward and only a limited number of studies have addressed the problem in a holistic way. With the goal of advancing the state of the art, the Lung Nodule Database (LNDb) Challenge on automatic lung cancer patient management was organized. The LNDb Challenge addressed lung nodule detection, segmentation and characterization as well as prediction of patient follow-up according to the 2017 Fleischner society pulmonary nodule guidelines. 294 CT scans were thus collected retrospectively at the Centro Hospitalar e Universitrio de So Joo in Porto, Portugal and each CT was annotated by at least one radiologist. Annotations comprised nodule centroids, segmentations and subjective characterization. 58 CTs and the corresponding annotations were withheld as a separate test set. A total of 947 users registered for the challenge and 11 successful submissions for at least one of the sub-challenges were received. For patient follow-up prediction, a maximum quadratic weighted Cohen's kappa of 0.580 was obtained. In terms of nodule detection, a sensitivity below 0.4 (and 0.7) at 1 false positive per scan was obtained for nodules identified by at least one (and two) radiologist(s). For nodule segmentation, a maximum Jaccard score of 0.567 was obtained, surpassing the interobserver variability. In terms of nodule texture characterization, a maximum quadratic weighted Cohen's kappa of 0.733 was obtained, with part solid nodules being particularly challenging to classify correctly. Detailed analysis of the proposed methods and the differences in performance allow to identify the major challenges remaining and future directions data collection, augmentation/generation and evaluation of under-represented classes, the incorporation of scan-level information for better decision making and the development of tools and challenges with clinical-oriented goals. The LNDb Challenge and associated data remain publicly available so that future methods can be tested and benchmarked, promoting the development of new algorithms in lung cancer medical image analysis and patient followup recommendation.

Abstract
Abstract Background Recently, cardiac shear wave (SW) elastography, based on high frame rate (HFR) echocardiography, has been proposed as new non-invasive technique for assessing myocardial stiffness. As myocardial stiffness increases with increasing wall stress, differences in measured operating myocardial stiffness do not necessarily reflect differences in intrinsic myocardial properties, but can also be caused by mere changes in loading or chamber geometry. This complicates myocardial stiffness interpretation for different types of pathologic hypertrophy. Purpose To explore the relationship between myocardial stiffness and underlying pathological substrates for cardiac hypertrophy. Methods We included 20 patients with hypertension (HT) and myocardial remodelling (59±14 years, 75% male), 20 patients with hypertrophic cardiomyopathy (HCM) (59±16 years, 60% male) and 20 healthy controls (56±14 years, 75% male). Left ventricular (LV) parasternal long axis views were acquired with an experimental HFR scanner at 1293±362 frames per seconds. Propagation velocity of SW occurring after mitral valve closure in the interventricular septum (IVS) served as measure of operating myocardial stiffness (Figure A). To compare myocardial stiffness among hearts with differing loading conditions and chamber geometry, SW velocities were normalized to end-diastolic wall stress, estimated at IVS from regional wall thickness, longitudinal and circumferential regional radii of curvature, and non-invasively estimated LV end-diastolic pressure (EDP). Results SW velocities differed significantly between groups (p<0.001). The controls had the lowest SW velocities (4.02±0.97 m/s), whereas values between HT and HCM group were comparable (6.46±0.99 m/s vs. 7.00±2.10 m/s; p=0.738). Considering end-diastolic wall stress, HCM patients had the same SW velocity at lower wall stress compared to HT (Figure B), indicating higher myocardial stiffness in the HCM group. SW velocities normalized for wall stress indicated significantly different myocardial stiffness among all groups (p<0.001) (Figure C). In a multiple linear regression model, the underlying pathological substrate independently influenced SW velocity (beta 1.37, 95% CI (0.78–1.96); p<0.001), while wall stress did not significantly affect its value (p=0.479). Conclusions Our study demonstrated that SW elastography can detect differences in myocardial stiffness in hypertensive heart and hypertrophic cardiomyopathy. Additionally, our results suggest that SW velocity is dominated by underlying myocardial tissue properties. We hypothesize that differential changes in cardiomyocytes and/or the extracellular matrix contribute to the differential myocardial stiffening in different pathologic entities of LV hypertrophy. Thus, SW elastography could provide useful novel diagnostic information in the evaluation of LV hypertrophy. Figure A, B, C Funding Acknowledgement Type of funding source: None

Abstract
Objectives: The purpose of this study was to investigate whether propagation velocities of naturally occurring shear waves (SWs) at mitral valve closure (MVC) increase with the degree of diffuse myocardial injury (DMI) and with invasively determined LV filling pressures as a reflection of an increase in myocardial stiffness in heart transplantation (HTx) recipients. Background: After orthotopic HTx, allografts undergo DMI that contributes to functional impairment, especially to increased passive myocardial stiffness, which is an important pathophysiological determinant of left ventricular (LV) diastolic dysfunction. Echocardiographic SW elastography is an emerging approach for measuring myocardial stiffness in vivo. Natural SWs occur after mechanical excitation of the myocardium, for example, after MVC, and their propagation velocity is directly related to myocardial stiffness, thus providing an opportunity to assess myocardial stiffness at end-diastole. Methods: A total of 52 HTx recipients who underwent right heart catheterization (all) and cardiac magnetic resonance (CMR) (n = 23) during their annual check-up were prospectively enrolled. Echocardiographic SW elastography was performed in parasternal long axis views of the LV using an experimental scanner at 1,135 ± 270 frames per second. The degree of DMI was quantified with T1 mapping. Results: SW velocity at MVC correlated best with native myocardial T1 values (r = 0.75; p < 0.0001) and was the best noninvasive parameter that correlated with pulmonary capillary wedge pressures (PCWP) (r = 0.54; p < 0.001). Standard echocardiographic parameters of LV diastolic function correlated poorly with both native T1 and PCWP values. Conclusions: End-diastolic SW propagation velocities, as measure of myocardial stiffness, showed a good correlation with CMR-defined diffuse myocardial injury and with invasively determined LV filling pressures in patients with HTx. Thus, these findings suggest that SW elastography has the potential to become a valuable noninvasive method for the assessment of diastolic myocardial properties in HTx recipients. © 2020 American College of Cardiology Foundation