Predicting adverse cardiac events in sarcoidosis: deep learning from automated characterization of regional myocardial remodeling.

Recognizing early cardiac sarcoidosis (CS) imaging phenotypes can help identify opportunities for effective treatment before irreversible myocardial pathology occurs. We aimed to characterize regional CS myocardial remodeling features correlating with future adverse cardiac events by coupling automated image processing and data analysis on cardiac magnetic resonance (CMR) imaging datasets. A deep convolutional neural network (DCNN) was used to process a CMR database of a 10-year cohort of 117 consecutive biopsy-proven sarcoidosis patients.

Regional Myocardial Remodeling Characteristics Correlates With Cardiac Events in Sarcoidosis.

Background: The poor prognosis of cardiac sarcoidosis (CS) underscores the need for risk stratification.

Purpose: To investigate the prognostic significance of ventricular/myocardial remodeling features in sarcoidosis.

Study Type: Retrospective.

Discrepant myocardial microvascular perfusion and mechanics after acute myocardial infarction: Characterization of the "Tako-tsubo effect" with real-time myocardial perfusion contrast echocardiograph.

Background: In patients with acute anterior myocardial infarction (MI), sometimes an "apical ballooning" contractile dysfunction pattern that exceeds factual myocardial injury is identified in the ventriculography and bedside echocardiography. The hemodynamic consequences/sequela of this "Tako-tsobu effect" has not been well delineated. Of note, this anatomic imaging finding often misleads frontline physicians who assume reciprocal causation of persistent cardiac pump failure and ventricular pressure overload.

Infimal convolution-based regularization for SPECT reconstruction.

Purpose: Total variation (TV) regularization is efficient in suppressing noise, but is known to suffer from staircase artifacts. The goal of this work was to develop a regularization method using the infimal convolution of the first- and the second-order derivatives to reduce or even prevent staircase artifacts in the reconstructed images, and to investigate if the advantage in noise suppression by this TV-type regularization can be translated into dose reduction.

Methods: In the present work, we introduce the infimal convolution of the first- and the second-order total variation (ICTV) as the regularization term in penalized maximum likelihood reconstruction.