arXiv subjects

Tolga Çukur

Publications and source records attributed to Tolga Çukur.

45 records · Page 3Linked to original sources

arXiv2020

A Blind Deconvolution Technique Based on Projection Onto Convex Sets for Magnetic Particle Imaging

Magnetic Particle Imaging (MPI) is an emerging imaging modality that maps the spatial distribution of magnetic nanoparticles. The x-space reconstruction in MPI results in highly blurry images, where the resolution depends on both system parameters and nanoparticle type. Previous techniques to counteract this blurring rely on the knowledge of the imaging point spread function (PSF), which may not be available or may require additional measurements. This work proposes a blind deconvolution algorithm for MPI to recover the precise spatial distribution of nanoparticles. The proposed algorithm exploits the observation that the imaging PSF in MPI has zero phase in Fourier domain. Thus, even though the reconstructed images are highly blurred, phase remains unaltered. We leverage this powerful property to iteratively enforce consistency of phase and bounded l1 energy information, using an orthogonal Projections Onto Convex Sets (POCS) algorithm. To demonstrate the method, comprehensive simulations were performed without and with nanoparticle relaxation effects, and at various noise levels. In addition, imaging experiments were performed on an in-house MPI scanner using a three-vial phantom that contained different nanoparticle types. Image quality was compared with conventional deconvolution methods, Wiener deconvolution and Lucy-Richardson method, which explicitly rely on the knowledge of PSF. Both the simulation results and experimental imaging results show that the proposed blind deconvolution algorithm outperforms the conventional deconvolution methods. Without utilizing the imaging PSF, the proposed algorithm improves image quality and resolution even in the case of different nanoparticle types, while displaying reliable performance against loss of the fundamental harmonic, nanoparticle relaxation effects, and noise.

physics.med-ph↗

arXiv2019

mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis

Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts is limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts can alleviate this limitation to improve clinical utility. Common approaches for multi-contrast MRI involve either one-to-one and many-to-one synthesis methods. One-to-one methods take as input a single source contrast, and they learn a latent representation sensitive to unique features of the source. Meanwhile, many-to-one methods receive multiple distinct sources, and they learn a shared latent representation more sensitive to common features across sources. For enhanced image synthesis, here we propose a multi-stream approach that aggregates information across multiple source images via a mixture of multiple one-to-one streams and a joint many-to-one stream. The shared feature maps generated in the many-to-one stream and the complementary feature maps generated in the one-to-one streams are combined with a fusion block. The location of the fusion block is adaptively modified to maximize task-specific performance. Qualitative and quantitative assessments on T1-, T2-, PD-weighted and FLAIR images clearly demonstrate the superior performance of the proposed method compared to previous state-of-the-art one-to-one and many-to-one methods.

eess.IV↗

arXiv2019

A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networks

Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this study is to introduce a transfer-learning approach to address the problem of data scarcity in training deep networks for accelerated MRI. Methods: Neural networks were trained on thousands of samples from public datasets of either natural images or brain MR images. The networks were then fine-tuned using only few tens of brain MR images in a distinct testing domain. Domain-transferred networks were compared to networks trained directly in the testing domain. Network performance was evaluated for varying acceleration factors (2-10), number of training samples (0.5-4k) and number of fine-tuning samples (0-100). Results: The proposed approach achieves successful domain transfer between MR images acquired with different contrasts (T1- and T2-weighted images), and between natural and MR images (ImageNet and T1- or T2-weighted images). Networks obtained via transfer-learning using only tens of images in the testing domain achieve nearly identical performance to networks trained directly in the testing domain using thousands of images. Conclusion: The proposed approach might facilitate the use of neural networks for MRI reconstruction without the need for collection of extensive imaging datasets.

cs.CV↗

arXiv2019

Projection onto Epigraph Sets for Rapid Self-Tuning Compressed Sensing MRI

The compressed sensing (CS) framework leverages the sparsity of MR images to reconstruct from undersampled acquisitions. CS reconstructions involve one or more regularization parameters that weigh sparsity in transform domains against fidelity to acquired data. While parameter selection is critical for reconstruction quality, the optimal parameters are subject and dataset specific. Thus, commonly practiced heuristic parameter selection generalizes poorly to independent datasets. Recent studies have proposed to tune parameters by estimating the risk of removing significant image coefficients. Line searches are performed across the parameter space to identify the parameter value that minimizes this risk. Although effective, these line searches yield prolonged reconstruction times. Here, we propose a new self-tuning CS method for multi-coil multi-acquisition reconstructions. The proposed method uses computationally efficient projections onto epigraph sets of the $l_1$ and total-variation norms to simultaneously achieve parameter selection and regularization. In vivo demonstrations are provided for balanced steady-state free precession, time-of-flight, and T1-weighted imaging. The proposed method achieves nearly an order of magnitude improvement in computational efficiency over line-search methods while maintaining near-optimal parameter selection.

physics.med-ph↗

arXiv2018

Synergistic Reconstruction and Synthesis via Generative Adversarial Networks for Accelerated Multi-Contrast MRI

Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of information available for diagnosis. Yet, excessive scan times associated with additional contrasts may be a limiting factor. Two mainstream approaches for enhanced scan efficiency are reconstruction of undersampled acquisitions and synthesis of missing acquisitions. In reconstruction, performance decreases towards higher acceleration factors with diminished sampling density particularly at high-spatial-frequencies. In synthesis, the absence of data samples from the target contrast can lead to artefactual sensitivity or insensitivity to image features. Here we propose a new approach for synergistic reconstruction-synthesis of multi-contrast MRI based on conditional generative adversarial networks. The proposed method preserves high-frequency details of the target contrast by relying on the shared high-frequency information available from the source contrast, and prevents feature leakage or loss by relying on the undersampled acquisitions of the target contrast. Demonstrations on brain MRI datasets from healthy subjects and patients indicate the superior performance of the proposed method compared to previous state-of-the-art. The proposed method can help improve the quality and scan efficiency of multi-contrast MRI exams.

cs.CV↗

arXiv2018

Learning-Based Compressive MRI

In the area of magnetic resonance imaging (MRI), an extensive range of non-linear reconstruction algorithms have been proposed that can be used with general Fourier subsampling patterns. However, the design of these subsampling patterns has typically been considered in isolation from the reconstruction rule and the anatomy under consideration. In this paper, we propose a learning-based framework for optimizing MRI subsampling patterns for a specific reconstruction rule and anatomy, considering both the noiseless and noisy settings. Our learning algorithm has access to a representative set of training signals, and searches for a sampling pattern that performs well on average for the signals in this set. We present a novel parameter-free greedy mask selection method, and show it to be effective for a variety of reconstruction rules and performance metrics. Moreover we also support our numerical findings by providing a rigorous justification of our framework via statistical learning theory.

eess.IV↗

arXiv2018

Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks

Acquiring images of the same anatomy with multiple different contrasts increases the diversity of diagnostic information available in an MR exam. Yet, scan time limitations may prohibit acquisition of certain contrasts, and images for some contrast may be corrupted by noise and artifacts. In such cases, the ability to synthesize unacquired or corrupted contrasts from remaining contrasts can improve diagnostic utility. For multi-contrast synthesis, current methods learn a nonlinear intensity transformation between the source and target images, either via nonlinear regression or deterministic neural networks. These methods can in turn suffer from loss of high-spatial-frequency information in synthesized images. Here we propose a new approach for multi-contrast MRI synthesis based on conditional generative adversarial networks. The proposed approach preserves high-frequency details via an adversarial loss; and it offers enhanced synthesis performance via a pixel-wise loss for registered multi-contrast images and a cycle-consistency loss for unregistered images. Information from neighboring cross-sections are utilized to further improved synthesis quality. Demonstrations on T1- and T2-weighted images from healthy subjects and patients clearly indicate the superior performance of the proposed approach compared to previous state-of-the-art methods. Our synthesis approach can help improve quality and versatility of multi-contrast MRI exams without the need for prolonged examinations.

cs.CV↗

arXiv2017

Reconstruction by Calibration over Tensors for Multi-Coil Multi-Acquisition Balanced SSFP Imaging

Purpose: To develop a rapid imaging framework for balanced steady-state free precession (bSSFP) that jointly reconstructs undersampled data (by a factor of R) across multiple coils (D) and multiple acquisitions (N). To devise a multi-acquisition coil compression technique for improved computational efficiency. Methods: The bSSFP image for a given coil and acquisition is modeled to be modulated by a coil sensitivity and a bSSFP profile. The proposed reconstruction by calibration over tensors (ReCat) recovers missing data by tensor interpolation over the coil and acquisition dimensions. Coil compression is achieved using a new method based on multilinear singular value decomposition (MLCC). ReCat is compared with iterative self-consistent parallel imaging (SPIRiT) and profile encoding (PE-SSFP) reconstructions. Results: Compared to parallel imaging or profile-encoding methods, ReCat attains sensitive depiction of high-spatial-frequency information even at higher R. In the brain, ReCat improves peak SNR (PSNR) by 1.1$\pm$1.0 dB over SPIRiT and by 0.9$\pm$0.3 dB over PE-SSFP (mean$\pm$std across subjects; average for N=2-8, R=8-16). Furthermore, reconstructions based on MLCC achieve 0.8$\pm$0.6 dB higher PSNR compared to those based on geometric coil compression (GCC) (average for N=2-8, R=4-16). Conclusion: ReCat is a promising acceleration framework for banding-artifact-free bSSFP imaging with high image quality; and MLCC offers improved computational efficiency for tensor-based reconstructions.

physics.med-ph↗

arXiv2017

Fast 3D Variable-FOV Reconstruction for Parallel Imaging with Localized Sensitivities

Several successful iterative approaches have recently been proposed for parallel-imaging reconstructions of variable-density (VD) acquisitions, but they often induce substantial computational burden for non-Cartesian data. Here we propose a generalized variable-FOV PILS reconstruction 3D VD Cartesian and non-Cartesian data. The proposed method separates k-space into non-intersecting annuli based on sampling density, and sets the 3D reconstruction FOV for each annulus based on the respective sampling density. The variable-FOV method is compared against conventional gridding, PILS, and ESPIRiT reconstructions. Results indicate that the proposed method yields better artifact suppression compared to gridding and PILS, and improves noise conditioning relative to ESPIRiT, enabling fast and high-quality reconstructions of 3D datasets.

physics.med-ph↗