Yuemeng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yuemeng Li has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Amar Dhanantwari
Philips Healthcare, Cleveland, OH, 44143, USA
1 shared publication Anas Fares
Harrington Heart & Vascular Institute, University Hospitals Cleveland Medical Center, Cleveland, Ohio, UNITED STATES
1 shared publication- Bochen Li
Sub-Institute of High and New Technology Standardization, China National Institute of Standardization (China)
1 shared publication - Brendan Lee Eck
Imaging Institute, Cleveland Clinic, 9500 Euclid Avenue, Cleveland, OH 44195, USA
1 shared publication - Chen Li
Institute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication David L Wilson
Biomedical engineering, Case Western Reserve University, Cleveland, Ohio, UNITED STATES
1 shared publication
Latest Publications
- 20 August 2023
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 91 (1) , 105-117
Learning ADC maps from accelerated radial k‐space diffusion‐weighted MRI in mice using a deep CNN‐transformer model
Purpose: To accelerate radially sampled diffusion weighted spin‐echo (Rad‐DW‐SE) acquisition method for generating high quality ADC maps.Methods: A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad‐DW‐SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4× and 8× compared to the original acquisition parameters.Results: Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles.Conclusions: The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad‐DW‐SE method.
- 20 August 2023
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 91 (1) , 105-117
Learning ADC maps from accelerated radial k‐space diffusion‐weighted MRI in mice using a deep CNN‐transformer model
Purpose: To accelerate radially sampled diffusion weighted spin‐echo (Rad‐DW‐SE) acquisition method for generating high quality ADC maps.Methods: A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad‐DW‐SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4× and 8× compared to the original acquisition parameters.Results: Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles.Conclusions: The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad‐DW‐SE method.
- 20 October 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12350, 44-535
The implementation of air defense large data management application platform based on Internet of Things
Concerning the traditional GIS-based civil air defense management application system not meeting the requirements of the internet of things big data, the construction ideas and key technologies of the air defense big data management application platform based on Internet of Things (IoT) technology are studied. After analyzing big data of civil air defense, five-layer SOA architecture is proposed to build the cloud framework of topological structure. Then, the design of the database and distributed storage of images is described. Finally, aiming at the practical application requirements, four modules of real-time data acquisition, large data management, real-time statistical analysis of data, and online data display are realized. The system is of great significance to the management and application of large data information for civil air defense projects.
- 20 October 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12350, 44-535
The implementation of air defense large data management application platform based on Internet of Things
Concerning the traditional GIS-based civil air defense management application system not meeting the requirements of the internet of things big data, the construction ideas and key technologies of the air defense big data management application platform based on Internet of Things (IoT) technology are studied. After analyzing big data of civil air defense, five-layer SOA architecture is proposed to build the cloud framework of topological structure. Then, the design of the database and distributed storage of images is described. Finally, aiming at the practical application requirements, four modules of real-time data acquisition, large data management, real-time statistical analysis of data, and online data display are realized. The system is of great significance to the management and application of large data information for civil air defense projects.
- 23 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 832-837
Analysis on Visual Tracking Algorithms
Target Tracking is a popular question in computer vision, with numerous works are proposed. To this end, the brief introduction of visual object tracking should be proposed. In this paper, we aim to review the most popular target representing methods in target tracking. We begin with classification of current target tracking methods, explaining the details in every method. Then we illustrate the merits and weaknesses of each category. At last, we discuss the challenges that target tracking faces and the future develop trend of it. Through our reviewing, we can provide reference for relevant researchers to have a better understanding of target tracking technology.
- 23 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 832-837
Analysis on Visual Tracking Algorithms
Target Tracking is a popular question in computer vision, with numerous works are proposed. To this end, the brief introduction of visual object tracking should be proposed. In this paper, we aim to review the most popular target representing methods in target tracking. We begin with classification of current target tracking methods, explaining the details in every method. Then we illustrate the merits and weaknesses of each category. At last, we discuss the challenges that target tracking faces and the future develop trend of it. Through our reviewing, we can provide reference for relevant researchers to have a better understanding of target tracking technology.
- 22 June 2022
- Published by Elsevier in Applied Materials Today
- Vol. 29, 101553
Incorporating Metal Precursors towards a Library of High-resolution Metal Parts by Stereolithography
- 22 June 2022
- Published by Elsevier in Applied Materials Today
- Vol. 29, 101553
Incorporating Metal Precursors towards a Library of High-resolution Metal Parts by Stereolithography
- 1 September 2018
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 63 (18) , 185011
The role of acquisition and quantification methods in myocardial blood flow estimability for myocardial perfusion imaging CT
In this work, we clarified the role of acquisition parameters and quantification methods in myocardial blood flow (MBF) estimability for myocardial perfusion imaging using CT (MPI-CT). We used a physiologic model with a CT simulator to generate time-attenuation curves across a range of imaging conditions, i.e. tube current-time product, imaging duration, and temporal sampling, and physiologic conditions, i.e. MBF and arterial input function width. We assessed MBF estimability by precision (interquartile range of MBF estimates) and bias (difference between median MBF estimate and reference MBF) for multiple quantification methods. Methods included: six existing model-based deconvolution models, such as the plug-flow tissue uptake model (PTU), Fermi function model, and single-compartment model (SCM); two proposed robust physiologic models (RPM1, RPM2); model-independent singular value decomposition with Tikhonov regularization determined by the L-curve criterion (LSVD); and maximum upslope (MUP). Simulations show that MBF estimability is most affected by changes in imaging duration for model-based methods and by changes in tube current-time product and sampling interval for model-independent methods. Models with three parameters, i.e. RPM1, RPM2, and SCM, gave least biased and most precise MBF estimates. The average relative bias (precision) for RPM1, RPM2, and SCM was ⩽11% (⩽10%) and the models produced high-quality MBF maps in CT simulated phantom data as well as in a porcine model of coronary artery stenosis. In terms of precision, the methods ranked best-to-worst are: RPM1 > RPM2 > Fermi > SCM > LSVD > MUP other methods. In terms of bias, the models ranked best-to-worst are: SCM > RPM2 > RPM1 > PTU > LSVD other methods. Models with four or more parameters, particularly five-parameter models, had very poor precision (as much as 310% uncertainty) and/or significant bias (as much as 493%) and were sensitive to parameter initialization, thus suggesting the presence of multiple local minima. For improved estimates of MBF from MPI-CT, it is recommended to use reduced models that incorporate prior knowledge of physiology and contrast agent uptake, such as the proposed RPM1 and RPM2 models.
- 1 September 2018
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 63 (18) , 185011
The role of acquisition and quantification methods in myocardial blood flow estimability for myocardial perfusion imaging CT
In this work, we clarified the role of acquisition parameters and quantification methods in myocardial blood flow (MBF) estimability for myocardial perfusion imaging using CT (MPI-CT). We used a physiologic model with a CT simulator to generate time-attenuation curves across a range of imaging conditions, i.e. tube current-time product, imaging duration, and temporal sampling, and physiologic conditions, i.e. MBF and arterial input function width. We assessed MBF estimability by precision (interquartile range of MBF estimates) and bias (difference between median MBF estimate and reference MBF) for multiple quantification methods. Methods included: six existing model-based deconvolution models, such as the plug-flow tissue uptake model (PTU), Fermi function model, and single-compartment model (SCM); two proposed robust physiologic models (RPM1, RPM2); model-independent singular value decomposition with Tikhonov regularization determined by the L-curve criterion (LSVD); and maximum upslope (MUP). Simulations show that MBF estimability is most affected by changes in imaging duration for model-based methods and by changes in tube current-time product and sampling interval for model-independent methods. Models with three parameters, i.e. RPM1, RPM2, and SCM, gave least biased and most precise MBF estimates. The average relative bias (precision) for RPM1, RPM2, and SCM was ⩽11% (⩽10%) and the models produced high-quality MBF maps in CT simulated phantom data as well as in a porcine model of coronary artery stenosis. In terms of precision, the methods ranked best-to-worst are: RPM1 > RPM2 > Fermi > SCM > LSVD > MUP other methods. In terms of bias, the models ranked best-to-worst are: SCM > RPM2 > RPM1 > PTU > LSVD other methods. Models with four or more parameters, particularly five-parameter models, had very poor precision (as much as 310% uncertainty) and/or significant bias (as much as 493%) and were sensitive to parameter initialization, thus suggesting the presence of multiple local minima. For improved estimates of MBF from MPI-CT, it is recommended to use reduced models that incorporate prior knowledge of physiology and contrast agent uptake, such as the proposed RPM1 and RPM2 models.