A5018106832- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Cell Image Analysis Techniques
- Cancer Genomics and Diagnostics
- Drilling and Well Engineering
- Lung Cancer Treatments and Mutations
- Oil and Gas Production Techniques
- Tunneling and Rock Mechanics
- Advanced MRI Techniques and Applications
- Cancer Cells and Metastasis
- Machine Learning in Healthcare
- RNA modifications and cancer
- Cancer-related molecular mechanisms research
- Ferroptosis and cancer prognosis
- Cancer, Hypoxia, and Metabolism
- Systemic Lupus Erythematosus Research
- Molecular Biology Techniques and Applications
- NMR spectroscopy and applications
- MRI in cancer diagnosis
- COVID-19 diagnosis using AI
- Hydraulic Fracturing and Reservoir Analysis
- Hepatitis C virus research
- Advanced Neural Network Applications
- Topic Modeling
The University of Texas Southwestern Medical Center
2017-2025
Southwestern Medical Center
2019-2025
Yunnan University
2024
Beijing University of Posts and Telecommunications
2022-2024
China University of Petroleum, Beijing
2022-2023
EY Technologies (United States)
2022
The University of Melbourne
2020
Washington University in St. Louis
2011-2017
State Street (United States)
2017
Schlumberger (United States)
2016
Abstract Existing natural language processing (NLP) methods to convert free-text clinical notes into structured data often require problem-specific annotations and model training. This study aims evaluate ChatGPT’s capacity extract information from medical efficiently comprehensively. We developed a large (LLM)-based workflow, utilizing systems engineering methodology spiral “prompt engineering” process, leveraging OpenAI’s API for batch querying ChatGPT. evaluated the effectiveness of this...
Microscopic examination of pathology slides is essential to disease diagnosis and biomedical research. However, traditional manual tissue laborious subjective. Tumor whole-slide image (WSI) scanning becoming part routine clinical procedures produces massive data that capture tumor histologic details at high resolution. Furthermore, the rapid development deep learning algorithms has significantly increased efficiency accuracy analysis. In light this progress, digital fast a powerful tool...
Purpose To determine the intracellular water preexchange lifetime, τ i , “average residence time” of water, in milieu neurons and astrocytes. The lifetime is important for modeling a variety MR data sets, including relaxation, diffusion‐sensitive, dynamic contrast–enhanced sets. Methods Herein, astrocytes determined microbead‐adherent, cultured cell system. In concert with thin‐slice selection, rapid flow extracellular media suppresses signal, allowing determination...
Abstract This study aims to develop an artificial intelligence (AI)-based model assist radiologists in pneumoconiosis screening and staging using chest radiographs. The model, based on radiographs, was developed a training cohort validated independent test cohort. Every image the datasets were labeled by experienced double-blinded fashion. computational started segmenting lung field into six subregions. Then, convolutional neural network classification used predict opacity level for each...
Recent advancements in tissue imaging techniques have facilitated the visualization and identification of various cell types within physiological pathological contexts. Despite emergence cell-cell interaction studies, there is a lack methods for evaluating individual spatial interactions. In this study, we introduce Ceograph, organization-based graph convolutional network designed to analyze organization (for example,. distribution, morphology, proximity, interactions) derived from pathology...
Tyrosine kinase inhibitors (TKIs) targeting epidermal growth factor receptor (EGFR) are effective for many patients with lung cancer EGFR mutations. However, not all responsive to TKIs, including even those harboring EGFR-sensitizing In this study, we quantified the cells and cellular interaction features of tumor microenvironment (TME) using routine H&E-stained biopsy sections. These TME were used develop a prediction model survival benefit from TKI therapy in adenocarcinoma mutations Lung...
Background: Sample size and power analysis are essential in biomedical research investigations, particularly clinical trial design, as they ensure sufficient statistical to detect meaningful effects. However, the complexity of these calculations often requires specialized expertise, making process inconvenient limiting accessibility for researchers during early-stage study planning. Methods: We developed N-Power AI, an agentic framework leveraging large language models (LLMs) perform sample...
Recent advances in deep learning show significant potential analyzing continuous monitoring electronic health records (EHR) data for clinical outcome prediction. We aim to develop a Transformer-based, Encounter-level Clinical Outcome (TECO) model predict mortality the intensive care unit (ICU) using inpatient EHR data. The TECO was developed multiple baseline and time-dependent variables from 2579 hospitalized COVID-19 patients ICU validated externally an acute respiratory distress syndrome...
Hypoxic-ischemic (H-I) injury to the developing brain is a significant cause of morbidity and mortality in humans. Other than hypothermia, there no effective treatment prevent or lessen consequences neonatal H-I. Increased expression NAD synthesizing enzyme nicotinamide mononucleotide adenylyl transferase 1 (Nmnat1) has been shown be neuroprotective against axonal peripheral nervous system. To investigate role Nmnat1 acute neurodegeneration CNS, we exposed wild-type mice overexpressing...
ABSTRACT Objective Recent advances in deep learning show significant potential analyzing continuous monitoring electronic health records (EHR) data for clinical outcome prediction. We aim to develop a Transformer-based, Encounter-level Clinical Outcome (TECO) model predict mortality the intensive care unit (ICU) using inpatient EHR data. Materials and Methods TECO was developed multiple baseline time-dependent variables from 2579 hospitalized COVID-19 patients ICU mortality, validated...
ABSTRACT Introduction Social and behavioral determinants of health (SBDH) are increasingly recognized as essential for prognostication informing targeted interventions. While medical notes contain rich SBDH details, these unstructured conventional extraction methods tend to be labor intensive, inaccurate, and/or unscalable. The emergence large language models (LLMs) presents an opportunity develop more effective approaches extracting data. Materials Methods We developed the SBDH-Reader,...
Racial and ethnic minority groups in the United States experience a disproportionate burden of COVID-19 deaths.
Managed pressure drilling (MPD) is an essential technology for safe and efficient in deep high-temperature high-pressure formations with narrow safety windows. However, the complex conditions wells make mechanism of multiphase flow annulus complicated increase difficulty accurate prediction bottomhole (BHP). Recently, increasing volume research shows that intelligent means accurately predicting BHP. few studies have focused on temporal properties variation In this paper, hybrid neural...
Formation evaluation of unconventional reservoirs is challenging due to the coexistence different phases such as kerogen, bitumen, movable and bound light hydrocarbon water. Current low-frequency (0.05 T) nuclear magnetic resonance (NMR) laboratory logging methods are incapable quantitatively separating phases. We demonstrate utility high-field (9 NMR 2D T1-T2 measurements for clay-interacting aqueous in shale based on difference frequency dependence spin-lattice relaxation time....
The quality of cement in cased boreholes is related to the production and life wells. At present, most commonly used method use CBL-VDL evaluate, but interpretation process complicated, decisions associated with significant risks may be taken based on results. Therefore, cementing evaluation must interpreted by experienced experts, which time-consuming labor-intensive. To improve efficiency interpretation, this paper VGG, ResNet, other convolutional neural networks automatically evaluate...