Jinyi Qi
University of California, Davis
Imaging phantomAlgorithmOpticsPhysicsIterative reconstructionArtificial intelligenceIterative methodTomographyPattern recognitionMonte Carlo methodImage resolutionPositron emission tomographyScannerNuclear medicineComputer visionMathematicsComputer scienceImage qualityDetectorMaximum a posteriori estimation
239Publications
52H-index
7,242Citations
Publications 225
Newest
#1Junwei Du (UC Davis: University of California, Davis)H-Index: 11
#2Qian Wang (UC Davis: University of California, Davis)H-Index: 1
Last. Simon R. Cherry (UC Davis: University of California, Davis)H-Index: 93
view all 5 authors...
OBJECTIVE Dual-ended readout depth-encoding detectors based on bismuth germanate (BGO) scintillation crystal arrays are good candidates for high-sensitivity small animal positron emission tomography used for very-low-dose imaging. In this paper, the performance of three dual-ended readout detectors based on 15 × 15 BGO arrays with three different reflector arrangements and 8 × 8 silicon photomultiplier arrays were evaluated and compared. APPROACH The three BGO arrays, denoted wo-ILG (without int...
Source
#1Zhaoheng Xie (UC Davis: University of California, Davis)H-Index: 3
#2Tiantian Li (UC Davis: University of California, Davis)H-Index: 2
Last. Jinyi Qi (UC Davis: University of California, Davis)H-Index: 52
view all 6 authors...
PURPOSE The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning 3D convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction. METHODS We used a pre-trained deep neural network to represent PET images. The network was trai...
Source
#1Guobao Wang (UC Davis: University of California, Davis)H-Index: 17
#2Lorenzo Nardo (UC Davis: University of California, Davis)H-Index: 29
Last. Ramsey D. Badawi (UC Davis: University of California, Davis)H-Index: 29
view all 9 authors...
1447 Objectives: Patients with cancer are at increased risk for cardiovascular disease due to common risk factors and anticancer treatments that may lead to toxic effects in the heart. In response to the increasing awareness of the issue of heart health in cancer patients, cardio-oncology is emerging as a new specialty. Whole-body 18F-FDG PET is routinely used for oncological imaging but conventional protocols are not well suited to cardiac imaging. 30-40% of standard oncological FDG-PET scans d...
#1Tiantian Li (UC Davis: University of California, Davis)H-Index: 2
#2Xuezhu Zhang (UC Davis: University of California, Davis)H-Index: 13
Last. Jinyi Qi (UC Davis: University of California, Davis)H-Index: 52
view all 7 authors...
60 Objectives: The uEXPLORER PET/CT system with ultra-high sensitivity and total-body coverage provides potential for more accurate quantification of a wide range of physiological parameters in vivo. Motion during dynamic PET data acquisition can cause image blurring and reduce quantitative accuracy. In this work, we apply our previously developed deep learning-based data-driven gating and motion compensation methods to improve the image quality of total-body parametric imaging. We demonstrate t...
54 null Introduction: null null Total-body dynamic PET can provide tracer kinetic assays of physiologically and biologically relevant information across the entire human body. Our previous work has demonstrated the capability of performing dynamic PET imaging with 100-ms temporal resolution on the uEXPLORER scanner. Sub-second dynamic PET imaging allows clear visualization of fast tracer dynamics after bolus injection with physiological (cardiac and respiratory) motion in real-time. In this work...
#1Wen Chen (CSU: Central South University)
#2Yimin Li (UC Davis: University of California, Davis)H-Index: 5
Last. Yi Rong (UC Davis: University of California, Davis)H-Index: 19
view all 10 authors...
Abstract Purpose: To assess image quality and uncertainty in organ-at-risk segmentation on cone beam computed tomography (CBCT) enhanced by deep-learning convolutional neural network (DCNN) for head and neck cancer. Methods: An in-house DCNN was trained using forty post-operative head and neck cancer patients with their planning CT and first-fraction CBCT images. Additional fifteen patients with repeat simulation CT (rCT) and CBCT scan taken on the same day (oCBCT) were used for validation and c...
Source
#1Youfang Lai (UTA: University of Texas at Arlington)H-Index: 6
#2Qian Wang (UC Davis: University of California, Davis)H-Index: 1
Last. Junwei Du (UC Davis: University of California, Davis)H-Index: 11
view all 9 authors...
With the goal of developing a total-body small-animal PET system with a high spatial resolution of ~ 0.5 mm and a high sensitivity > 10% for mouse/rat studies, we simulated four scanners using the graphical processing unit (GPU)-based Monte Carlo simulation package (gPET) and compared their performance in terms of spatial resolution and sensitivity. We also investigated the effect of depth-of-interaction (DOI) resolution on the spatial resolution. All the scanners are built upon 128 DOI encoding...
Source
#1Jinyi Qi (UC Davis: University of California, Davis)H-Index: 52
#2Samuel Matej (UPenn: University of Pennsylvania)H-Index: 22
Last. Xuezhu Zhang (UC Davis: University of California, Davis)H-Index: 13
view all 4 authors...
Total-body PET image reconstruction follows a similar procedure to the image reconstruction process for standard whole-body PET scanners. One unique aspect of total-body imaging is simultaneous coverage of the entire human body, which makes it convenient to perform total-body dynamic PET scans. Therefore, four-dimensional dynamic PET reconstruction and parametric imaging are of great interest in total-body imaging. This article covers some basics of PET image reconstruction and then focuses on t...
Source
#1Nimu Yuan (UC Davis: University of California, Davis)H-Index: 3
#3Jinyi Qi (UC Davis: University of California, Davis)H-Index: 52
Reducing radiation dose of x-ray computed tomography (CT) and thereby decreasing the potential risk to patients are desirable in CT imaging. Deep neural network (DNN) has been proposed to reduce noise in low-dose CT images and showed promising results. However, most existing DNN-based methods require training a neural network using high-quality CT images as a reference. Lack of high-quality reference data has therefore been the bottleneck in the current DNN-based methods. Recently, a noise-to-no...
4 CitationsSource
#1Tao Feng (BP)H-Index: 9
#2Gang YangH-Index: 1
Last. Ramsey D. Badawi (UC Davis: University of California, Davis)H-Index: 29
view all 0 authors...
The conventional gating approach creates a dilemma for systems with large field-of-view (FOV) such as the uExplorer system. The motion effect is localized with variable motion amplitude across the whole FOV. A conventional gating approach would increase the noise for regions without motion, or with small motion amplitude. Existing local gating approach that allows optimized locally adaptive gating numbers requires a 4D reconstruction, which is time-consuming for generating of a 3D image. Image-d...
Source