Showing papers by "Kyunghyun Sung published in 2015"
05 Oct 2015
TL;DR: Experimental results on 16 clinical kidney datasets demonstrate that the proposed method reaches a very high level of agreement with manual results and achieves superior performance to three existing baseline methods.
Abstract: In this paper, we introduce a method for automatic renal compartment segmentation from Dynamic Contrast-Enhanced MRI DCE-MRI images, which is an important problem but existing solutions cannot achieve high accuracy robustly for a wide range of data. The proposed method consists of three main steps. First, the whole kidney is segmented based on the concept of Maximally Stable Temporal Volume MSTV. The proposed MSTV detects anatomical structures that are stable in both spatial domain and temporal dynamics. MSTV-based kidney segmentation is robust to noises and does not require a training phase. It can well adapt to kidney shape variations caused by renal dysfunction. Second, voxels in the segmented kidney are described by principal components PCs to remove temporal redundancy and noises. And then k-means clustering of PCs is applied to separate voxels into cortex, medulla and pelvis. Third, a refinement method is introduced to further remove noises in each segmented compartment. Experimental results on 16 clinical kidney datasets demonstrate that our method reaches a very high level of agreement with manual results and achieves superior performance to three existing baseline methods. The code of the proposed method will be made publicly available with the publication of this paper.
11 citations
TL;DR: The objective was to develop a fast 3D T2‐weighted sequence for prostate imaging at 3T using a variable flip angle transition into driven equilibrium (T2‐TIDE) scheme.
Abstract: Author(s): Srinivasan, Subashini; Wu, Holden H; Sung, Kyunghyun; Margolis, Daniel JA; Ennis, Daniel B | Abstract: PurposeThree-dimensional (3D) T2 -weighted fast spin echo (FSE) imaging of the prostate currently requires long acquisition times. Our objective was to develop a fast 3D T2 -weighted sequence for prostate imaging at 3T using a variable flip angle transition into driven equilibrium (T2 -TIDE) scheme.Methods3D T2 -TIDE uses interleaved spiral-out phase encode ordering to efficiently sample the ky -kz phase encodes and also uses the transient balanced steady-state free precession signal to acquire the center of k-space for T2 -weighted imaging. Bloch simulations and images from 10 healthy subjects were acquired to evaluate the performance of 3D T2 -TIDE compared to 3D FSE.Results3D T2 -TIDE images were acquired in 2:54 minutes compared to 7:02 minutes for 3D FSE with identical imaging parameters. The signal-to-noise ratio (SNR) efficiency was significantly higher for 3D T2 -TIDE compared to 3D FSE in nearly all tissues, including periprostatic fat (45 ± 12 vs. 31 ± 7, P l 0.01), gluteal fat (48 ± 8 vs. 41 ± 10, P = 0.12), right peripheral zone (20 ± 4 vs. 16 ± 8, P = 0.12), left peripheral zone (17 ± 2 vs. 12 ± 3, P l 0.01), and anterior fibromuscular stroma (12 ± 4 vs. 4 ± 2, P l 0.01).Conclusion3D T2 -TIDE images of the prostate can be acquired quickly with SNR efficiency that exceeds that of 3D FSE.
6 citations
16 Apr 2015
TL;DR: This work presents a calibration-free parallel magnetic resonance imaging (pMRI) reconstruction approach by exploiting the fact that image structures typically tend to repeat themselves in several locations in the image domain, and proposes an iterative algorithm which is based on a variable splitting strategy.
Abstract: In this work we present a calibration-free parallel magnetic resonance imaging (pMRI) reconstruction approach by exploiting the fact that image structures typically tend to repeat themselves in several locations in the image domain. We use this prior information along with the correlation that exists among the different MR images, which are acquired from multiple receiver coils, to improve reconstructions from under-sampled data with arbitrary k-space trajectories. To accomplish this, we follow a variational approach and cast the pMRI reconstruction problem as the minimization of an energy functional that involves a vectorial non-local total variation (NLTV) regularizer. Further, to solve the posed optimization problem we propose an iterative algorithm which is based on a variable splitting strategy. To assess the reconstruction quality of the proposed method, we provide comparisons with alternative techniques and show that our results can be very competitive.
4 citations