Yinsheng Li

Dr. Yinsheng Li


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YLYinsheng Li
Yinsheng Li
KLKe Li
Ke Li
CZChengzhu Zhang
Chengzhu Zhang
JMJuan Montoya
Juan Montoya
GCGuang-Hong Chen
Guang-Hong Chen
Computed tomography (CT) is widely used in medical diagnosis and non-destructive detection. Image reconstruction in CT aims to accurately recover pixel values from measured line integrals, i.e., the summed pixel values along straight lines. Provided that the acquired data satisfy the data sufficiency condition as well as other conditions regarding the view angle sampling interval and the severity of transverse data truncation, researchers have discovered many solutions to accurately reconstruct the image. However, if these conditions are violated, accurate image reconstruction from line integrals remains an intellectual challenge. In this paper, a deep learning method with a common network architecture, termed iCT-Net, was developed and trained to accurately reconstruct images for previously solved and unsolved CT reconstruction problems with high quantitative accuracy. Particularly, accurate reconstructions were achieved for the case when the sparse view reconstruction problem (i.e., compressed sensing problem) is entangled with the classical interior tomographic problems.

19 September 2019 in Physics in Medicine & Biology
Verified
Journal Article
Open access
EHEvan Cary Harvey
Evan Cary Harvey
MFMang Feng
Mang Feng
XJXu Ji
Xu Ji
RZRan Zhang
Ran Zhang
YLYinsheng Li
Yinsheng Li
KLKe Li
Ke Li
While CTA is an established clinical gold standard for imaging large cerebral arteries and veins, an important challenge that currently remains for CTA is its limited performance in imaging small perforating arteries with diameters below 0.5 mm. The purpose of this work was to theoretically and experimentally study the potential benefits of using photon counting detector (PCD)-based CT (PCCT) to improve the performance of CTA in imaging these small arteries. In particular, the study focused on an important component of the CTA image package known as the maximum intensity projection (MIP) image. To help understand how the physical properties of a detector quantitatively influence the MIP image quality, a theoretical model on the statistical properties of MIP images was developed. After validating this model, it was used to explore the individual and joint contribution of the following detector properties to the MIP signal-to-noise ratio (SNR): inter-slice noise covariance, spatial resolution along the z direction, and native pixel pitch along z . The model demonstrated that superior slice sensitivity, reduced inter-slice noise correlation, and smaller native pixel pitch along z provided by PCDs lead to improved vessel SNR in MIP images. Finally, experiments were performed by scanning an anthropomorphic cerebral angiographic phantom using a benchtop PCCT system and a commercial MDCT system. The experimental MIP results consistently demonstrated that compared with MDCT, PCCT provides superior vessel conspicuity and reduced artifactual stenosis.

25 May 2021 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
JHJohn W. Hayes
John W. Hayes
JMJuan Montoya
Juan Montoya
ABAdam Budde
Adam Budde
CZChengzhu Zhang
Chengzhu Zhang
YLYinsheng Li
Yinsheng Li
GCGuang-Hong Chen
Guang-Hong Chen
To avoid severe limited-view artifacts in reconstructed CT images, current multi-row detector CT (MDCT) scanners with a single x-ray source-detector assembly need to limit table translation speeds such that the pitch ${p}$ (viz., normalized table translation distance per gantry rotation) is lower than 1.5. When ${p}>{1.5}$ , it remains an open question whether one can reconstruct clinically useful helical CT images without severe artifacts. In this work, we show that a synergistic use of advanced techniques in conventional helical filtered backprojection, compressed sensing, and more recent deep learning methods can be properly integrated to enable accurate reconstruction up to ${p}={4}$ without significant artifacts for single source MDCT scans.

22 March 2018 in American Journal of Neuroradiology
Verified
Journal Article
Open access
PDF file
JMJ.C. Montoya
J.C. Montoya
YLYinsheng Li
Yinsheng Li
CSC. Strother
C. Strother
GCG.-H. Chen
G.-H. Chen
BACKGROUND AND PURPOSE: Deep learning is a branch of artificial intelligence that has demonstrated unprecedented performance in many medical imaging applications. Our purpose was to develop a deep learning angiography method to generate 3D cerebral angiograms from a single contrast-enhanced C-arm conebeam CT acquisition in order to reduce image artifacts and radiation dose. MATERIALS AND METHODS: A set of 105 3D rotational angiography examinations were randomly selected from an internal data base. All were acquired using a clinical system in conjunction with a standard injection protocol. More than 150 million labeled voxels from 35 subjects were used for training. A deep convolutional neural network was trained to classify each image voxel into 3 tissue types (vasculature, bone, and soft tissue). The trained deep learning angiography model was then applied for tissue classification into a validation cohort of 8 subjects and a final testing cohort of the remaining 62 subjects. The final vasculature tissue class was used to generate the 3D deep learning angiography images. To quantify the generalization error of the trained model, we calculated the accuracy, sensitivity, precision, and Dice similarity coefficients for vasculature classification in relevant anatomy. The 3D deep learning angiography and clinical 3D rotational angiography images were subjected to a qualitative assessment for the presence of intersweep motion artifacts. RESULTS: Vasculature classification accuracy and 95% CI in the testing dataset were 98.7% (98.3%–99.1%). No residual signal from osseous structures was observed for any 3D deep learning angiography testing cases except for small regions in the otic capsule and nasal cavity compared with 37% (23/62) of the 3D rotational angiographies. CONCLUSIONS: Deep learning angiography accurately recreated the vascular anatomy of the 3D rotational angiography reconstructions without a mask. Deep learning angiography reduced misregistration artifacts induced by intersweep motion, and it reduced radiation exposure required to obtain clinically useful 3D rotational angiography.

30 August 2017 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YLYinsheng Li
Yinsheng Li
MSMichael A. Speidel
Michael A. Speidel
Christopher FrancoisChristopher Francois
Christopher Francois
GCGuang-Hong Chen
Guang-Hong Chen
In this paper, a newly developed statistical model-based image reconstruction [referred to as Simultaneous Multiple Artifacts Reduction in Tomographic RECONstruction (SMART-RECON)] is applied to low dose computer tomography (CT) myocardial perfusion imaging (CT-MPI). This method uses the nuclear norm of the spatial-temporal image matrix of the CT-MPI images as a regularizer, rather than a conventional spatial regularizer that incorporates image smoothness, edge preservation, or spatial sparsity into the reconstruction. In addition to providing the needed noise reduction for low-dose CT-MPI, SMART-RECON provides images with spatial resolution and noise power spectrum (NPS) properties, which are independent of contrast and dose levels. Both numerical simulations and in vivo animal studies were performed to validate the proposed method. In these studies, it was found that: 1) quantitative accuracy of perfusion maps in CT-MPI was well maintained for radiation dose level as low as 10 mAs per image frame, compared with the reference standard of 200 mAs for conventional filtered backprojection; 2) flow-occluded myocardium in the porcine heart was well delineated by SMART-RECON at 10 mAs per frame when compared with model-based image reconstruction using spatial total variation (TV) as the regularizer (referred to as TV-SIR) or spatial-temporal TV (ST-TV-SIR); the CT-MPI results were confirmed with positron-emission tomography imaging; 3) image sharpness in SMART-RECON images was nearly independent of image contrast level and radiation dose level, in stark contrast to TV-SIR and ST-TV-SIR, which displayed a strong dependence on both image contrast and radiation dose levels; and 4) the structure of the dose-normalized NPS for the SMART-RECON method did not depend on dose, while the TV-SIR and ST-TV-SIR NPS structure was dose-dependent.

20 December 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YLYinsheng Li
Yinsheng Li
JGJohn Garrett
John Garrett
KLKe Li
Ke Li
CSCharles Strother
Charles Strother
GCGuang-Hong Chen
Guang-Hong Chen
Temporal resolution in time-resolved cone-beam CT (TR-CBCT) imaging is often limited by the time needed to acquire a complete data set for image reconstruction. With the recent developments of performing nearly limited-view artifact-free reconstruction from data in a limited-view angle range and a prior image, temporal resolution of TR-CBCT imaging can be improved. One such an example is the use of Simultaneous Multiple Artifacts Reduction in Tomographic RECONstruction (SMART-RECON) [1] technique. However, with SMART-RECON, one can only improve temporal resolution up to 1 frame per second (fps) which is an improvement of 4.5 times over that of the conventional FBP reconstruction. In this paper, a new technique referred to as enhanced SMART-RECON (eSMART-RECON) was introduced to enhance the temporal performance of SMART-RECON in a multi-sweep CBCT data acquisition protocol. Both numerical simulation studies with ground truth and in vivo human subject studies using C-arm CBCT acquisition systems were conducted to demonstrate the following key results: for a multi-sweep CBCT acquisition protocol, eSMART-RECON enables 4-7.5 fps temporal resolution for TR-CBCT which is 4-7.5 times better than that offered by the original SMART-RECON, and 18-34 times better than that offered by the conventional FBP reconstruction.