A5100339183- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Radiation Dose and Imaging
- Radiation Detection and Scintillator Technologies
- Radiopharmaceutical Chemistry and Applications
- Advanced Radiotherapy Techniques
- Toxoplasma gondii Research Studies
- Pediatric Urology and Nephrology Studies
- Radiation Therapy and Dosimetry
- Medical Imaging and Pathology Studies
- Cell Image Analysis Techniques
- Advanced X-ray and CT Imaging
- Optical measurement and interference techniques
- Image and Signal Denoising Methods
- Traditional Chinese Medicine Studies
- MRI in cancer diagnosis
- Effects of Radiation Exposure
- Cytomegalovirus and herpesvirus research
- Brain Tumor Detection and Classification
- Advanced Image Processing Techniques
- 3D Surveying and Cultural Heritage
- Advanced MRI Techniques and Applications
- Herpesvirus Infections and Treatments
- Functional Brain Connectivity Studies
Lieber Institute for Brain Development
2021-2024
Beijing Chest Hospital
2024
Capital Medical University
2023-2024
Shenzhen Institutes of Advanced Technology
2021-2024
Johns Hopkins University
2015-2023
Chinese Academy of Sciences
2019-2023
Harvard University
2011-2023
Massachusetts General Hospital
2022-2023
Nanchang Hangkong University
2022
Beijing University of Chinese Medicine
2022
Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been improve PET image quality. Though successful efficient local feature extraction, CNN cannot capture long-range dependencies well limited receptive field. Global multi-head self-attention (MSA) a popular approach information. However, the calculation of global MSA for...
Toxoplasma gondii is an obligate intracellular parasite with worldwide distribution. Felines are the definitive hosts supporting complete life cycle of T. gondii. However, other warm-blooded animals such as rodents and humans can also be infected. Infection secondary results in long-term infection characterized by presence tissue cysts brain organs. While it known that associated behavioral changes, mechanisms behind these changes remain unclear. Alterations host intestinal microflora...
Computerized phantoms have been widely used in nuclear medicine imaging for system optimization and validation. Although the existing computerized can model anatomical variations through organ phantom scaling, they do not provide a way to fully reproduce details seen humans. In this work, we present novel registration-based method creating highly anatomically detailed phantoms. We experimentally show substantially improved image similarity of generated patient image.We propose...
Inositol hexakisphosphate kinases (IP6Ks) have been studied for their role in glucose homeostasis, metabolic disease, fatty liver chronic kidney neurological development, and psychiatric disease. IP6Ks phosphorylate inositol (IP6) to the pyrophosphate, 5-diphosphoinositol-1,2,3,4,6-pentakisphosphate (5-IP7). Most of currently known potent IP6K inhibitors contain a critical carboxylic acid which limits blood-brain barrier (BBB) penetration. In this work, synthesis testing variety isosteres...
MRI and PET are important modalities can provide complementary information for the diagnosis of brain diseases because structural obtain functional brain. However, is usually missing. Especially, simultaneous imaging not achievable at ultrahigh field in current. Thus, synthetic using essential. In this paper, we as a guide by joint probability distribution diffusion model (JPDDM). Meanwhile, We utilized our fields.
Balancing the tradeoff between radiation dose, acquisition duration and diagnostic image quality is essential for medical imaging modalities involving ionizing radiation. Lower administered activities to patient can reduce absorbed but result in reduced or require longer durations. In pediatric nuclear medicine, it desirable use lowest amount of radiopharmaceutical activity shortest that gives sufficient clinical diagnosis. However, a complex function factors including body morphometry. this...
Quantitative bone single-photon emission computed tomography (QBSPECT) has the potential to provide a better quantitative assessment of metastasis than planar scintigraphy due its ability quantify activity in overlapping structures. An important element assessing response is accurate image segmentation. However, limited by properties QBSPECT images, segmentation anatomical regions-of-interests (ROIs) still relies heavily on manual delineation experts. This work proposes fast and robust...
Purpose In the current clinical practice, administered activity (AA) for pediatric molecular imaging is often based on North American expert consensus guidelines or European Association of Nuclear Medicine dosage card, both which were developed best practice. These not formulated using a rigorous evaluation diagnostic image quality (IQ) relative to AA. guidelines, AA determined by weight‐based scaling adult AA, along with minimum and maximum constraints. this study, we use task‐based IQ...
Children generally are at greater risk from radiation exposure due to their sensitivity and the longer time frame after during which effects can manifest themselves. Thus, reducing is a major concern in pediatric nuclear medicine imaging. Lower administered activities (AA) reduce patient exposure, but also result reduced diagnostic accuracy. Typically, activity for imaging of children based on weight, our previous studies have shown that weight alone may not be sufficient accurately...
Abstract Current guidelines for administered activity (AA) in pediatric nuclear medicine imaging studies are based on a 2016 harmonization of the 2010 North American Consensus and 2007 European Association Nuclear Medicine dosage card. These assign AA scaled to patient body mass, with further constraints maximum minimum values radiopharmaceutical activity. guidelines, however, not formulated upon rigor-ous evaluation diagnostic image quality. In recent study renal cortex agent 99m Tc-DMSA...
Purpose: We propose a deep learning-based anthropomorphic model observer (DeepAMO) for image quality evaluation of multi-orientation, multi-slice sets with respect to clinically realistic 3D defect detection task. Approach: The DeepAMO is developed based on hypothetical the decision process human reader performing task using volume. comprised three sequential stages: segmentation, confirmation (DC), and rating value inference. input composite image, typical that used view volumes in clinical...