arXiv subjects

Georges El Fakhri

Publications and source records attributed to Georges El Fakhri.

59 records · Page 4Linked to original sources

arXiv2018

Speech Map: A Statistical Multimodal Atlas of 4D Tongue Motion During Speech from Tagged and Cine MR Images

Quantitative measurement of functional and anatomical traits of 4D tongue motion in the course of speech or other lingual behaviors remains a major challenge in scientific research and clinical applications. Here, we introduce a statistical multimodal atlas of 4D tongue motion using healthy subjects, which enables a combined quantitative characterization of tongue motion in a reference anatomical configuration. This atlas framework, termed Speech Map, combines cine- and tagged-MRI in order to provide both the anatomic reference and motion information during speech. Our approach involves a series of steps including (1) construction of a common reference anatomical configuration from cine-MRI, (2) motion estimation from tagged-MRI, (3) transformation of the motion estimations to the reference anatomical configuration, and (4) computation of motion quantities such as Lagrangian strain. Using this framework, the anatomic configuration of the tongue appears motionless, while the motion fields and associated strain measurements change over the time course of speech. In addition, to form a succinct representation of the high-dimensional and complex motion fields, principal component analysis is carried out to characterize the central tendencies and variations of motion fields of our speech tasks. Our proposed method provides a platform to quantitatively and objectively explain the differences and variability of tongue motion by illuminating internal motion and strain that have so far been intractable. The findings are used to understand how tongue function for speech is limited by abnormal internal motion and strain in glossectomy patients.

cs.CV↗

arXiv2018

Simulation study of light transport in laser-processed LYSO:Ce detectors with single-side readout

A tightly focused pulsed laser can locally modify the crystal structure inside the bulk of a scintillator. The result is incorporation of so-called optical barriers with a refractive index (RI) different from that of the crystal bulk, that can be used to redirect the scintillation light and control the light spread in the detector. We systematically study the scintillation light transport in detectors fabricated using the Laser Induced Optical Barrier technique, and objectively compare their potential performance characteristics with the two mainstream detector types: monolithic and mechanically pixelated arrays. Among countless optical barrier patterns, we explore barriers arranged in a pixel-like pattern extending all-way or half-way through a 20 mm thick LYSO:Ce crystal. We analyze the performance of the detectors coupled to MPPC arrays, in terms of light response functions, position histograms, line profiles, and light collection efficiency. Our results show that laser-processed detectors constitute a new detector category with a behavior between the two standard detector types. When the barrier-crystal interface is smooth, no DOI information can be obtained regardless of barrier RI. However, with a rough barrier-crystal interface we can extract multiple DOI levels. Lower barrier RI results in larger light confinement, leading to better transverse resolution. Laser-processed crystals can also potentially increase the light collection efficiency, which could lead to improved energy resolution and timing resolution due to higher signals. For a laser-processed detector with smooth barrier-crystal interfaces the light collection efficiency is simulated to >44%, and for rough interfaces >73%. The numbers for a monolithic crystal is 39% with polished surfaces, and 71% with rough surfaces, and for a mechanically pixelated array 33% with polished pixel surfaces and 51% with rough surfaces.

physics.med-ph↗

arXiv2018

Attenuation correction for brain PET imaging using deep neural network based on dixon and ZTE MR images

Positron Emission Tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as Magnetic Resonance (MR) images do not reflect attenuation coefficients directly. To address this issue, we present deep neural network methods to derive the continuous attenuation coefficients for brain PET imaging from MR images. With only Dixon MR images as the network input, the existing U-net structure was adopted and analysis using forty patient data sets shows it is superior than other Dixon based methods. When both Dixon and zero echo time (ZTE) images are available, we have proposed a modified U-net structure, named GroupU-net, to efficiently make use of both Dixon and ZTE information through group convolution modules when the network goes deeper. Quantitative analysis based on fourteen real patient data sets demonstrates that both network approaches can perform better than the standard methods, and the proposed network structure can further reduce the PET quantification error compared to the U-net structure.

physics.med-ph↗

arXiv2017

Iterative PET Image Reconstruction Using Convolutional Neural Network Representation

PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently deep neural networks have been widely and successfully used in computer vision tasks and attracted growing interests in medical imaging. In this work, we trained a deep residual convolutional neural network to improve PET image quality by using the existing inter-patient information. An innovative feature of the proposed method is that we embed the neural network in the iterative reconstruction framework for image representation, rather than using it as a post-processing tool. We formulate the objective function as a constraint optimization problem and solve it using the alternating direction method of multipliers (ADMM) algorithm. Both simulation data and hybrid real data are used to evaluate the proposed method. Quantification results show that our proposed iterative neural network method can outperform the neural network denoising and conventional penalized maximum likelihood methods.

cs.CV↗

arXiv2017

A Cascaded Convolutional Neural Network for X-ray Low-dose CT Image Denoising

Image denoising techniques are essential to reducing noise levels and enhancing diagnosis reliability in low-dose computed tomography (CT). Machine learning based denoising methods have shown great potential in removing the complex and spatial-variant noises in CT images. However, some residue artifacts would appear in the denoised image due to complexity of noises. A cascaded training network was proposed in this work, where the trained CNN was applied on the training dataset to initiate new trainings and remove artifacts induced by denoising. A cascades of convolutional neural networks (CNN) were built iteratively to achieve better performance with simple CNN structures. Experiments were carried out on 2016 Low-dose CT Grand Challenge datasets to evaluate the method's performance.

cs.CV↗