Yilong Liu
University of Hong Kong
Rank (linear algebra)Imaging phantomDeep learningAlgorithmImage (mathematics)AccelerationImage segmentationJoint (audio engineering)UndersamplingHausdorff distanceSense (electronics)Magnetic resonance imagingArtificial intelligenceTensor (intrinsic definition)ResidualNoise reductionCalibrationNeurosciencePattern recognitionImage resolutionLinear phaseSensitivity (control systems)Singular value decompositionArtifact (error)MultisliceWhite matterNyquist–Shannon sampling theoremMedical imagingComputer visionComputer scienceConvolutional neural networkSegmentationSensory system
17Publications
7H-index
72Citations
Publications 18
Newest
#1Linfang Xiao (HKU: University of Hong Kong)H-Index: 4
#2Yilong Liu (HKU: University of Hong Kong)H-Index: 7
Last. Ed X. Wu (HKU: University of Hong Kong)H-Index: 55
view all 8 authors...
PURPOSE: To provide a complex-valued deep learning approach for partial Fourier (PF) reconstruction of complex MR images. METHODS: Conventional PF reconstruction methods, such as projection onto convex sets (POCS), uses low-resolution image phase information from the central symmetrically sampled k-space for image reconstruction. However, this smooth phase constraint undermines the phase estimation accuracy in presence of rapid local phase variations, causing image artifacts and limiting the ext...
Source
#1Zheyuan Yi (HKU: University of Hong Kong)H-Index: 2
#2Yilong Liu (HKU: University of Hong Kong)H-Index: 7
Last. Ed X. Wu (HKU: University of Hong Kong)H-Index: 55
view all 8 authors...
PURPOSE To jointly reconstruct highly undersampled multicontrast two-dimensional (2D) datasets through a low-rank Hankel tensor completion framework. METHODS A multicontrast Hankel tensor completion (MC-HTC) framework is proposed to exploit the shareable information in multicontrast datasets with respect to their highly correlated image structure, common spatial support, and shared coil sensitivity for joint reconstruction. This is achieved by first organizing multicontrast k-space datasets into...
Source
#4Yifan Chen (University of Electronic Science and Technology of China)H-Index: 18
Stroke is a serious manifestation of various cerebrovascular diseases and one of the most dangerous diseases in the world today. Volume quantification and location detection of chronic stroke lesions provide vital biomarkers for stroke rehabilitation. Recently, deep learning has seen a rapid growth, with a great potential in segmenting medical images. In this work, unlike most deep learning-based segmentation methods utilizing only magnetic resonance (MR) images as the input, we propose and vali...
Source
#1Yilong Liu (HKU: University of Hong Kong)H-Index: 7
#2Zheyuan Yi (HKU: University of Hong Kong)H-Index: 2
Last. Ed X. Wu (HKU: University of Hong Kong)H-Index: 55
view all 8 authors...
PURPOSE To provide joint calibrationless parallel imaging reconstruction of highly accelerated multislice 2D MR k-space data. METHODS Adjacent image slices in multislice MR data have similar coil sensitivity maps, spatial support, and image content. Such similarities can be utilized to improve image quality by reconstructing multiple slices jointly with low-rank tensor completion. Specifically, the multichannel k-space data from multiple slices are constructed into a block-wise Hankel tensor and...
Source
#4Yifan Chen (University of Electronic Science and Technology of China)H-Index: 18
Dice loss is the most widely used loss function in deep learning methods for unbalanced medical image segmentation. The main limitation of Dice loss is that it weighs different parts of the to-be-segmented region of interest (ROI) equally, which is inappropriate given that the fuzzy boundary is typically more challenging to segment than central parts. A recently-proposed boundary loss weighs different parts of an ROI according to their distances to the ROI’s boundary, thus providing complementar...
Source
#6Yifan Chen (University of Electronic Science and Technology of China)H-Index: 18
Liver and liver tumor segmentation provides vital biomarkers for surgical planning and hepatic diagnosis. In this paper, we propose and validate a novel level-set method integrating an enhanced edge indicator and an automatically derived initial curve for CT based liver tumor segmentation. At the preprocessing step, the CT image intensity values were truncated to lie in a fixed range to enhance the image contrast surrounding liver and liver tumor. To remove non-liver tissues for subsequent tumor...
Source
#5Yifan Chen (University of Electronic Science and Technology of China)H-Index: 18
In this paper, we propose and validate a location prior guided automatic pancreas segmentation framework based on 3D convolutional neural network (CNN). To guide pancreas segmentation, centroid of the pancreas used to determine its bounding box is calculated using the location of the liver which is firstly segmented by a 2D CNN. A linear relationship between centroids of the pancreas and the liver is proposed. After that, a 3D CNN is employed the input of which is the bounding box of the pancrea...
Source
#1Xunda Wang (HKU: University of Hong Kong)H-Index: 3
#2Alex T. L. Leong (HKU: University of Hong Kong)H-Index: 5
Last. Ed X. Wu (HKU: University of Hong Kong)H-Index: 55
view all 5 authors...
Abstract Blood-oxygen-level-dependent (BOLD) resting-state functional MRI (rsfMRI) has emerged as a valuable tool to map complex brain-wide functional networks, predict cognitive performance and identify biomarkers for neurological diseases. However, interpreting these findings poses challenges, as the neural basis of rsfMRI connectivity remains poorly understood. The thalamus serves as a relay station and modulates diverse long-range cortical functional integrations, yet few studies directly in...
Source
#1Qianqian Zhang (Southern Medical University)H-Index: 1
#2Guohui Ruan (Southern Medical University)H-Index: 1
Last. Yanqiu Feng (Southern Medical University)H-Index: 16
view all 9 authors...
PURPOSE: To develop a machine learning approach using convolutional neural network for reducing MRI Gibbs-ringing artifact. THEORY AND METHODS: Gibbs-ringing artifact in MR images is caused by insufficient sampling of the high frequency data. Existing methods exploit smooth constraints to reduce intensity oscillations near sharp edges at the cost of blurring details. In this work, we developed a machine learning approach for removing the Gibbs-ringing artifact from MR images. The ringing artifac...
Source
Jul 23, 2019 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
#7Yifan Chen (University of Electronic Science and Technology of China)H-Index: 18
White matter hyperintensity (WMH) is associated with various aging and neurodegenerative diseases. In this paper, we proposed and validated a fully automatic system which integrated classical image processing and deep neural network for segmenting WMH from fluid attenuation inversion recovery (FLAIR) and T1-weighed magnetic resonance (MR) images. A novel skip connection U-net (SC U-net) was proposed and compared with the classical U-net. Experiments were performed on a dataset of 60 images, acqu...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.