Coronary Artery Disease and Gallbladder Inflammatory Pseudopolyps

Axial MR image demonstrating multiple small gallbladder polypoid lesions characterized by contrast enhancement in a 78-year-old male hospitalized for acute chest pain due to coronary artery disease who showed fever and emesis during hospitalization and had signs of acute acalculous cholecystitis at computed tomography. Given the overall clinical conditions and the MR features, the inflammatory origin of the polyps was considered. The patient underwent cholecystectomy and the histological diagnosis of gallbladder inflammatory pseudopolyps was confirmed. This rare entity represents 5–10% of all gallbladder polyps, and their differentiation from benign and malignant tumors might be challenging especially in acalculous patients, thus surgery is often performed.

Automated Extraction of Cerebral Infarction Region in Head MR Image Using Pseudo Cerebral Infarction Image by CycleGAN

Since recognizing the location and extent of infarction is essential for diagnosis and treatment, many methods using deep learning have been reported. Generally, deep learning requires a large amount of training data. To overcome this problem, we generated pseudo patient images using CycleGAN, which performed image transformation without paired images. Then, we aimed to improve the extraction accuracy by using the generated images for the extraction of cerebral infarction regions. First, we used CycleGAN for data augmentation. Pseudo-cerebral infarction images were generated from healthy images using CycleGAN. Finally, U-Net was used to segment the cerebral infarction region using CycleGAN-generated images. Regarding the extraction accuracy, the Dice index was 0.553 for U-Net with CycleGAN, which was an improvement over U-Net without CycleGAN. Furthermore, the number of false positives per case was 3.75 for U-Net without CycleGAN and 1.23 for U-Net with CycleGAN, respectively. The number of false positives was reduced by approximately 67% by introducing the CycleGAN-generated images to training cases. These results indicate that utilizing CycleGAN-generated images was effective and facilitated the accurate extraction of the infarcted regions while maintaining the detection rate.

Compressive Sensing Magnetic Resonance Image Reconstruction and Denoising using Convolutional Neural Network

Restoration of high-quality brain Magnetic Resonance Image (MRI) from the sparse under-sampled complex k-space signal is a widely studied ill-posed inverse transform problem. A deep learning-based data-adaptive and data-driven convolutional technique has been proposed for high-quality MRI recovery from its under-sampled complex domain k-space signal. The uniform subsampling process is very slow in phase-encoding to generate high-resolution images. The longer scan times degrade the perceptual image quality. Various factors contribute to image degradation during data acquisition such as the inception of body motion artifacts, the thermal energy effects of the body, and random noise artifacts due to voltage fluctuations. Keeping in view the patient’s critical condition and comfort, longer scan times are not preferred in practice. To reduce the image acquisition time, noise levels, and motion artifacts in the MR images, Compressive Sensing (CS) provides an accelerated way to reconstructs the high-quality MR image from very limited signal measurements acquired much below the Nyquist rate. However, such data acquisition strategies require advanced computer algorithms for the reconstruction of high-quality MRI from the undersampled MRI data. An improved CNN-based MRI reconstructed algorithm has been presented in this paper which shows better performance to reconstruct high-quality MRI than similar other MR image reconstruction algorithms. The performance of the proposed algorithm is measured by image quality checking tools such as normalized-MSE, PSNR, and SSIM.

POCS-Augmented CycleGAN for MR Image Reconstruction

Recent years have seen increased research interest in replacing the computationally intensive Magnetic resonance (MR) image reconstruction process with deep neural networks. We claim in this paper that the traditional image reconstruction methods and deep learning (DL) are mutually complementary and can be combined to achieve better image reconstruction quality. To test this hypothesis, a hybrid DL image reconstruction method was proposed by combining a state-of-the-art deep learning network, namely a generative adversarial network with cycle loss (CycleGAN), with a traditional data reconstruction algorithm: Projection Onto Convex Set (POCS). The output of the first iteration’s training results of the CycleGAN was updated by POCS and used as the extra training data for the second training iteration of the CycleGAN. The method was validated using sub-sampled Magnetic resonance imaging data. Compared with other state-of-the-art, DL-based methods (e.g., U-Net, GAN, and RefineGAN) and a traditional method (compressed sensing), our method showed the best reconstruction results.

Compressed Sensing Based Dynamic MR Image Reconstruction By Using 3D-Total Generalized Variation and Tensor Decomposition: k-t TGV-TD

Purpose: Compressed Sensing Magnetic Resonance Imaging (CS-MRI) is a promising technique to accelerate dynamic cardiac MR imaging (DCMRI). For DCMRI, the CS-MRI usually exploits image signal sparsity and low-rank property to reconstruct dynamic images from the undersampled k-space data. In this paper, a novel CS algorithm is investigated to improve dynamic cardiac MR image reconstruction quality under the condition of minimizing the k-space recording.Methods: The sparse representation of 3D cardiac magnetic resonance data is implemented by synergistically integrating 3D TGV algorithm and high order singular value decomposition (HOSVD) based Tensor Decomposition, termed as k-t TGV-TD method. In the proposed method, the low rank structure of the 3D dynamic cardiac MR data is performed by the HOSVD method, and the localized image sparsity is achieved by the 3D TGV method. Moreover, the Fast Composite Splitting Algorithm (FCSA) method, combining the variable splitting with operator splitting techniques, is employed to solve the low-rank and sparse problem. Two different cardiac MR datasets (cardiac cine and cardiac perfusion MR data) are used to evaluate the performance of the proposed method.Results: Compared with the state-of-art methods, such as the k-t SLR method, 3D TGV method and HOSVD based tensor decomposition method, the proposed method can offer improved reconstruction accuracy in terms of higher signal-to-error ratio (SER).Conclusions: This work proved that the k-t TGV-TD method was an effective sparse representation way for DC-MRI, which was capable of significantly improving the reconstruction accuracy with different reduction factor.

Diagnostic Classification of Patients with Dilated Cardiomyopathy Using Ventricular Strain Analysis Algorithm

Dilated cardiomyopathy (DCM) is a cardiomyopathy with left ventricle or double ventricle enlargement and systolic dysfunction. It is an important cause of sudden cardiac death and heart failure and is the leading indication for cardiac transplantation. Major heart diseases like heart muscle damage and valvular problems are diagnosed using cardiac MRI. However, it takes time for cardiologists to measure DCM-related parameters to decide whether patients have this disease. We have presented a method for automatic ventricular segmentation, parameter extraction, and diagnosing DCM. In this paper, left ventricle and right ventricle are segmented by parasternal short-axis cardiac MR image sequence; then, related parameters are extracted in the end-diastole and end-systole of the heart. Machine learning classifiers use extracted parameters as input to predict normal people and patients with DCM, among which Random forest classifier gives the highest accuracy. The results show that the proposed system can be effectively utilized to detect and diagnose DCM automatically. The experimental results suggest the capabilities and advantages of the proposed method to diagnose DCM. A small amount of sample input can generate results comparable to more complex methods.