A5060712269- Liver Disease Diagnosis and Treatment
- Hepatocellular Carcinoma Treatment and Prognosis
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- MRI in cancer diagnosis
- Ultrasound Imaging and Elastography
- Stellar, planetary, and galactic studies
- Astrophysics and Star Formation Studies
- Gallbladder and Bile Duct Disorders
- Astro and Planetary Science
- Ultrasound and Hyperthermia Applications
- Cardiovascular Health and Risk Factors
- Cardiovascular Disease and Adiposity
- Artificial Intelligence in Healthcare
- Liver Disease and Transplantation
- Liver Diseases and Immunity
- Brain Tumor Detection and Classification
- Bee Products Chemical Analysis
University of California, Los Angeles
2024
University of California, San Diego
2019-2024
To assess feasibility of training a convolutional neural network (CNN) to automate liver segmentation across different imaging modalities and techniques used in clinical practice apply this enable automation biometry.We trained 2D U-Net CNN for two stages using 330 abdominal MRI CT exams acquired at our institution. First, we the with non-contrast multi-echo spoiled-gradient-echo (SGPR)images 300 provide multiple signal-weightings. Then, transfer learning generalize additional images from 30...
Background Various limitations have impacted research evaluating reader agreement for Liver Imaging Reporting and Data System (LI-RADS). Purpose To assess of LI-RADS in an international multicenter multireader setting using scrollable images. Materials Methods This retrospective study used deidentified clinical multiphase CT MRI reports with at least one untreated observation from six institutions three countries; only qualifying examinations were submitted. Examination dates October 2017 to...
Abstract Objectives To assess reproducibility and fibrosis classification accuracy of magnetic resonance elastography (MRE)–determined liver stiffness measured manually at two different centers, by automated analysis software in adults with nonalcoholic fatty disease (NAFLD), using histopathology as a reference standard. Methods This retrospective, cross-sectional study included 91 NAFLD who underwent MRE biopsy. MRE-determined was independently for this an image analyst each centers...
Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series compared its manual registration.Three hundred fourteen patients, including internal external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance for...
Conventional liver magnetic resonance elastography (MRE) requires breath-holding (BH) to avoid motion artifacts, which is challenging for children. While radial free-breathing (FB)-MRE an alternative quantifying stiffness (LS), previous methods had limitations of long scan times, acquiring two slices in 5 minutes, and not resolving during reconstruction. To reduce FB-MRE time 4 minutes four investigate the impact self-gated (SG) compensation on LS quantification terms agreement, intrasession...
Abstract We present high-spectral-resolution M -band spectra from iSHELL on NASA’s Infrared Telescope Facility along the line of sight to debris disk host star HD 32297. also a Gemini Planet Imager H polarimetric image 131488 disk. search for fundamental CO absorption lines in 32297, but do not detect any. place an upper limit column density ∼6 × 10 15 cm −2 . By combining limit, mass measured with Atacama Large Millimeter/submillimeter Array (ALMA), and geometrical properties disk, we...
Previous work has proposed self-navigated golden-angle (GA) radial free-breathing (FB) MR elastography (MRE) of the liver. This employed a standard DC-based motion compensation framework that proved suboptimal. Here we propose an image-space based motion-compensation for 2D MRE. The method is compared to by measuring signal-to-noise (SNR) after each (8 subjects). median (interquartile range) SNR across subjects was 4.8 (3.6-5.7) and 6.8 (6.3-7.5) methods, respectively. Inclusion data may...
Hepatic stiffness measured by MR elastography (MRE) is a biomarker for fibrosis. Standard liver MRE requires breath-holding (BH) to avoid motion artifacts, but BH challenging children. Radial free-breathing (FB) can overcome this challenge longer scan times. FB-MRE using rapid wave encoding decreases the time and self-navigation supports compensation. With help of fractional reduce echo times, image quality be further improved. This work demonstrated that self-navigated methods measure...
Motivation: MR elastography (MRE) detects liver fibrosis by measuring hepatic stiffness (HS). Breath-holding (BH) is required to avoid motion artifacts, but this challenging in children. Previous radial free-breathing (FB) MRE eliminated the BH, 2 min/slice. Goal(s): To reduce scan time for FB-MRE and analyze effects of self-gating on HS. Approach: Radial was modified acquire lower resolution perform spatial interpolation, which reduced time. Self-gating performed compensate breathing...
Motivation: To improve liver vessel segmentation on MRI under annotation constraints.Goal(s): Apply an advanced unpaired image translation technique, SynDiff, to create synthetic MR images from CT data.Approach: By incorporating masks in the process, optimized SynDiff models generated that facilitated more effective pretraining of models.Results: Validated across multiple settings, refined approach surpassed standard nnU-Net and other pretraining-based methods, substantially improving...
Motivation: Hepatic stiffness (HS), detected by MR elastography (MRE), is a biomarker for hepatic fibrosis. Liver MRE requires breath-holding (BH), which challenging in children or people with liver disease. Spin-echo echo-planar-imaging (SE-EPI) can quantify HS rapidly(~10 s), even iron overload. Goal(s): To evaluate free-breathing (FB) SE-EPI without respiratory triggering motion compensation terms of agreement, repeatability, and measurable area [%] respect to BH MRE. Approach: FB were...
The purpose of this study was to identify the prognostic value baseline MRI-determined imaging biomarkers for liver volume changes following low-calorie liquid diet in bariatric surgery patients
We present high-spectral resolution M-band spectra from iSHELL on NASA's Infrared Telescope Facility (IRTF) along the line of sight to debris disk host star HD 32297. also a Gemini Planet Imager (GPI) H-band polarimetric image 131488 disk. search for fundamental CO absorption lines in 32297 but do not detect any. place an upper limit column density $\sim$6$\times10^{15}$ cm$^{-2}$. By combining limit, mass measured with ALMA, and geometrical properties disk, we estimate scale height be...