arXiv subjects

Ruiyang Zhao

Publications and source records attributed to Ruiyang Zhao.

22 records · Page 2Linked to original sources

arXiv2022

A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction

Interventional magnetic resonance imaging (i-MRI) for surgical guidance could help visualize the interventional process such as deep brain stimulation (DBS), improving the surgery performance and patient outcome. Different from retrospective reconstruction in conventional dynamic imaging, i-MRI for DBS has to acquire and reconstruct the interventional images sequentially online. Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling. By using an initializer and Conv-LSTM blocks, the priors from the pre-operative reference image and intra-operative frames were exploited for reconstructing the current frame. Data consistency for radial sampling was implemented by a soft-projection method. To improve the reconstruction accuracy, an adversarial learning strategy was adopted. A set of interventional images based on the pre-operative and post-operative MR images were simulated for algorithm validation. Results showed with only 10 radial spokes, ConvLR provided the best performance compared with state-of-the-art methods, giving an acceleration up to 40 folds. The proposed algorithm has the potential to achieve real-time i-MRI for DBS and can be used for general purpose MR-guided intervention.

cs.CV↗

arXiv2022

Galaxy power spectrum and biasing results from the LOFAR Two-metre Sky Survey (first data release)

The LOFAR Two-metre Sky Survey (LoTSS) is an ongoing survey aiming to observe the entire Northern sky, providing an excellent opportunity to study the distribution and evolution of the large-scale structure of the Universe. The source catalogue from the public LoTSS first data release (DR1) covers 1% of the sky, and shows correlated noise or fluctuations of the flux density calibration on few degree scales. We explore the LoTSS DR1 to understand the survey systematics and data quality of this first data release. We produce catalog mocks to estimate uncertainties, and measure the angular clustering statistics of LoTSS galaxies, which fit the $Λ$CDM cosmology reasonably well. We employ a Markov chain Monte Carlo (MCMC) based Bayesian analysis to recover the best galaxy biasing scheme and multi-component source fraction for LoTSS DR1 above $1$ mJy assuming different possible redshift templates. After masking some noisy and uneven patches and with suitable flux density cuts, the LOFAR survey appears qualified for large-scale cosmological studies. The upcoming data releases from LOFAR are expected to be deeper and wider, and will therefore provide improved cosmological measurements.

astro-ph.CO↗

arXiv2021

End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction

Deep learning techniques have emerged as a promising approach to highly accelerated MRI. However, recent reconstruction challenges have shown several drawbacks in current deep learning approaches, including the loss of fine image details even using models that perform well in terms of global quality metrics. In this study, we propose an end-to-end deep learning framework for image reconstruction and pathology detection, which enables a clinically aware evaluation of deep learning reconstruction quality. The solution is demonstrated for a use case in detecting meniscal tears on knee MRI studies, ultimately finding a loss of fine image details with common reconstruction methods expressed as a reduced ability to detect important pathology like meniscal tears. Despite the common practice of quantitative reconstruction methodology evaluation with metrics such as SSIM, impaired pathology detection as an automated pathology-based reconstruction evaluation approach suggests existing quantitative methods do not capture clinically important reconstruction outcomes.

cs.CV↗

arXiv2021

fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Data

Improving speed and image quality of Magnetic Resonance Imaging (MRI) via novel reconstruction approaches remains one of the highest impact applications for deep learning in medical imaging. The fastMRI dataset, unique in that it contains large volumes of raw MRI data, has enabled significant advances in accelerating MRI using deep learning-based reconstruction methods. While the impact of the fastMRI dataset on the field of medical imaging is unquestioned, the dataset currently lacks clinical expert pathology annotations, critical to addressing clinically relevant reconstruction frameworks and exploring important questions regarding rendering of specific pathology using such novel approaches. This work introduces fastMRI+, which consists of 16154 subspecialist expert bounding box annotations and 13 study-level labels for 22 different pathology categories on the fastMRI knee dataset, and 7570 subspecialist expert bounding box annotations and 643 study-level labels for 30 different pathology categories for the fastMRI brain dataset. The fastMRI+ dataset is open access and aims to support further research and advancement of medical imaging in MRI reconstruction and beyond.

eess.IV↗