Haotian Hong

SeqEyes : An Open‐Source Toolbox for Synchronized Waveform/Trajectory Visualization in Pulseq

Xingwang Yong, Zheng Liu, Yiyun Dong, Haotian Hong et autres

Pulseq enables vendor-neutral description of MRI pulse sequences in human-readable .seq files and is widely used for sequence development and sharing. During design and debugging, rapid evaluation of sequence timing across RF pulses, gradient waveforms, and ADC events is essential. This is …

us, cn, kr (code pays fourni par la source)

Intrinsic modality disparity augmentation without database via cross-modal routing

Hua Wu, Haotian Hong, Yang Zhou, Yanxiong Wu et autres

Current augmentation of Large Language Models (LLMs) primarily relies on external corpora, which constrains performance based on database availability and leaves models vulnerable to input perturbations. Inspired by the human perceptual system’s ability to leverage mutual augmentation across different modalities, We propose …

cn (code pays fourni par la source)

Peripheral Nerve Stimulation Optimized Pulses for EPI (POPE) allows high-resolution fMRI

Laurentius Renzo Huber, Dominik Rattenbacher, Bastien Guérin, Haotian Hong et autres

Purpose: Recent improvements in MRI gradient design and amplifiers, advanced MRI scanners are now routinely utilizing slew rates of several hundred T/m/s. However, full gradient performance cannot be exploited in high-resolution EPI due to peripheral nerve stimulation (PNS) limits. We aim to …

us, nl, de (code pays fourni par la source)

A Flexible Graphite–Silicone Pad for Improved Fat Suppression in Cervical Spine MRI at 5 T via Passive B 0 Shimming

Y S Yang, Z LIU, Haotian Hong, Weijun Zhang et autres

ABSTRACT Purpose Susceptibility‐induced inhomogeneity at the posterior neck degrades spectral fat suppression in cervical spine MRI at 5 T and above. We describe a flexible graphite–silicone pad for passive shimming and assess its effect on field homogeneity and fat‐suppressed imaging alongside the …

cn (code pays fourni par la source)

Multi‐Echo SSFP: A Method for Synthetic bSSFP MRI Contrast Without Banding Artifacts at High Field

Haotian Hong, Michael N. Hoff, Wenchao Yang, Yiyun Dong et autres

Purpose Balanced steady‐state free precession (bSSFP) is an important MRI sequence paradigm with a high signal‐to‐noise ratio (SNR) and inherent contrast, but suffers from banding artifacts due to inhomogeneity, especially in high‐field MRI. This study introduces a multi‐echo SSFP (MESS) sequence that …

cn, us (code pays fourni par la source)

Simultaneous myocardial T1, T2, T1ρ and fat fraction mapping with hybrid dual-echo cartesian acquisition and dictionary matching

Zhenfeng Lyu, Hongzhang Huang, Haotian Hong, Junpu Hu et autres

BACKGROUND: T1, T2, T1ρ and fat fraction (FF) are important parameters for diagnosing various pathological changes in the myocardium. However, existing methods either require repeated breath-holds to quantify multiple parameters, or rely on complex image reconstruction to remove artifacts arising from highly …

cn (code pays fourni par la source)

Fully self-gated dual-venc five-dimensional flow magnetic resonance imaging for simultaneous imaging of the cardiovascular and portal venous systems: A feasibility study

Yuyang Ren, Wen Ye, Wenchao Yang, Wenjian Liu et autres

PURPOSE: To develop and evaluate a fully self-gated dual-venc five-dimensional (5D) flow cardiovascular magnetic resonance (CMR) technique for joint assessment of cardiovascular and portal venous hemodynamics under free breathing. METHODS: A dual-venc 5D flow sequence using a spiral-in Cartesian sampling trajectory was …

cn (code pays fourni par la source)

Hyperbolic Prompt Learning for Incremental Event Detection with LLMs

Xiujin Zhang, Wenxin Jin, Haotian Hong, Pengfei Zhang et autres

Class-incremental event detection (CIED) is essential for real-world information extraction systems, which must continually recognize new event types without forgetting past knowledge. The main challenge lies in balancing stability and adaptability under data imbalance. Existing methods often underuse the hierarchical and syntactic …

cn (code pays fourni par la source)

Deep contrastive graph clustering with information preservation

Hu Lu, Haotian Hong, Fuhao Shi, Shengli Wu et autres

cn, gb (code pays fourni par la source)

Simultaneous Myocardial T1, T2, T1ρ and Fat Fraction Mapping with Hybrid Dual-echo Cartesian Acquisition and Dictionary Matching

Zhenfeng Lyu, Hongzhang Huang, Haotian Hong, Junpu Hu et autres

Motivation: Simultaneous cardiac parameters and fat quantification enables comprehensive myocardial tissue characterization. However, the water-fat MR fingerprinting techniques have complex image processing. Goal(s): To develop a cardiac water-fat multi-parametric mapping technique with single-shot Cartesian acquisition and dictionary matching. Approach: A novel Dixon-MultiMap …

Unsupervised phase unwrapping for aortic 4D flow MRI using deep image prior

Haotian Hong, Zijian Zhou, Hu Peng

Motivation: 4D flow MRI can acquire high flow velocity resolved images using low velocity encoding (venc) and phase unwrapping, conditioned on the unwrapping algorithm is reliable and robust. Goal(s): Evaluating an unsupervised phase unwrapping method using deep image prior (PUDIP) in aortic …

Deep Self-Supervised Attributed Graph Clustering for Social Network Analysis

Hu Lu, Haotian Hong, Xia Geng

Abstract Deep graph clustering is an unsupervised learning task that divides nodes in a graph into disjoint regions with the help of graph auto-encoders. Currently, such methods have several problems, as follows. (1) The deep graph clustering method does not effectively utilize …

cn (code pays fourni par la source)