Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning

<pre> In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem.</pre>

Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning

<pre> In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem.</pre>

A Generative Adversarial Network Technique for High-Quality Super-Resolution Reconstruction of Cardiac Magnetic Resonance Images

Objective: In this paper, we proposed a Denoising Super-resolution Generative Adversarial Network (DnSRGAN) method for high-quality super-resolution reconstruction of noisy cardiac magnetic resonance (CMR) images.Methods: This method is based on feed-forward denoising convolutional neural network (DnCNN) and SRGAN architecture. Firstly, we used a feed-forward denoising neural network to pre-denoise the CMR image to ensure that the input is a clean image. Secondly, we use the gradient penalty (GP) method to solve the problem of the discriminator gradient disappearing, which improves the convergence speed of the model. Finally, a new loss function is added to the original SRGAN loss function to monitor GAN gradient descent to achieve more stable and efficient model training, thereby providing higher perceptual quality for the super-resolution of CMR images.Results: We divided the tested cardiac images into 3 groups, each group of 25 images, calculated the Peak Signal to Noise Ratio (PSNR) /Structural Similarity (SSIM) between Ground Truth (GT) and the images generated by super-resolution, used them to evaluate our model, and Compared with the current widely used method: Bicubic ESRGAN and SRGAN, our method has better reconstruction quality and higher PSNR/SSIM score.Conclusion: We used DnCNN to denoise the CMR image, and then using the improved SRGAN to perform super-resolution reconstruction of the denoised image, we can solve the problem of high noise and artifacts that cause the cardiac image to be reconstructed incorrectly during super-resolution. Furthermore, our method is capable of high-quality reconstruction of noisy cardiac images.

Coregistration and Spatial Compounding of Optoacoustic Cardiac Images via Fourier Analysis of Four-Dimensional Data

Volumetric optoacoustic tomography has been shown to provide unprecedented capabilities for ultrafast imaging of cardiovascular dynamics in mice. Three-dimensional imaging rates in the order of 100 Hz have been achieved, which enabled the visualization of transient cardiac events such as arrhythmias or contrast agent perfusion without the need for retrospective gating. The fast murine heart rates (400–600 beats per minute) yet impose limitations when it comes to compounding of multiple frames or accurate registration of multi-spectral data. Herein, we investigate on the capabilities of Fourier analysis of four-dimensional data for coregistration of independent volumetric optoacoustic image sequences of the heart. The fundamental frequencies and higher harmonics of respiratory and cardiac cycles could clearly be distinguished, which facilitated efficient retrospective gating without additional readings. The performance of the suggested methodology was successfully demonstrated by compounding cardiac images acquired by raster-scanning of a spherical transducer array as well as by unmixing of oxygenated and deoxygenated hemoglobin from multi-spectral optoacoustic data.

Heuristic Search for Homology Localization Problem and Its Application in Cardiac Trabeculae Reconstruction

Cardiac trabeculae are fine rod-like muscles whose ends are attached to the inner walls of ventricles. Accurate extraction of trabeculae is important yet challenging, due to the background noise and limited resolution of cardiac images. Existing works proposed to handle this task by modeling the trabeculae as topological handles for better extraction. Computing optimal representation of these handles is essential yet very expensive. In this work, we formulate the problem as a heuristic search problem, and propose novel heuristic functions based on advanced topological techniques. We show in experiments that the proposed heuristic functions improve the computation in both time and memory.