A5013485575- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Dementia and Cognitive Impairment Research
- Machine Learning in Healthcare
- COVID-19 Clinical Research Studies
- Brain Tumor Detection and Classification
- Advanced Data Compression Techniques
- Sepsis Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Radiology practices and education
- Domain Adaptation and Few-Shot Learning
- Image and Signal Denoising Methods
- SARS-CoV-2 and COVID-19 Research
- Anomaly Detection Techniques and Applications
- Digital Radiography and Breast Imaging
- Artificial Intelligence in Healthcare
- Gait Recognition and Analysis
- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- Advanced SAR Imaging Techniques
- Medical Imaging Techniques and Applications
- Dental Radiography and Imaging
- Cell Image Analysis Techniques
SA Technologies (United States)
2016-2025
The University of Texas at El Paso
2014-2022
United Imaging Healthcare (China)
2020-2022
Northeastern University
2014-2015
Signature Research (United States)
2011-2014
Caelum Research Corporation (United States)
1991-2002
Kodak (Japan)
2002
Kodak (United States)
1996-1998
Advanced Imaging Research (United States)
1998
Carestream (United States)
1998
It is critical to have a deep learning-based system validated on an external dataset before it used assist clinical prognoses. The aim of this study was assess the performance artificial intelligence (AI) detect tuberculosis (TB) in large-scale dataset.An artificial, convolutional neural network (DCNN) developed differentiate TB from other common abnormalities lung chest X-ray radiographs. An internal with 7,025 images develop AI system, including were five sources U.S. and China, after...
Indoor fall monitoring is challenging for community-dwelling older adults due to the need high accuracy and privacy concerns. Doppler radar promising, given its low-cost contactless sensing mechanism. However, line-of-sight restriction limits application of in practice, as signature will vary when angle changes, signal strength substantially degrade with large aspect angles. Additionally, similarity signatures among different types makes classification challenging. To address these problems,...
Abnormal gait is a significant noncognitive biomarker for Alzheimer's disease (AD) and AD-related dementia (ADRD). Micro-Doppler radar (MDR), nonwearable technology, can capture human movements potential early ADRD risk assessment. In this article, we propose to design systematic intelligence analysis ARDR evaluation (STRIDE) integrating MDR sensors with advanced artificial (AI) technologies. STRIDE embeds new deep learning (DL) classification framework. As proof of concept, develop "digital...
To help improve efficacy of screening mammography by eventually establishing a new optimal personalized paradigm, the authors investigated potential using quantitative multiscale texture and density feature analysis digital mammograms to predict near-term breast cancer risk.The authors' dataset includes acquired from 340 women. Among them, 141 were positive 199 negative/benign cases. The negative "prior" examinations used in study. Based on intensity value distributions, five subregions at...
Diagnosis of tuberculosis (TB) in multi-slice spiral computed tomography (CT) images is a difficult task many TB prevalent locations which experienced radiologists are lacking. To address this difficulty, we develop an automated detection system based on artificial intelligence (AI) study to simplify the diagnostic process active (ATB) and improve accuracy using CT images.A image dataset 846 patients retrospectively collected from large teaching hospital. The gold standard for ATB sputum...
Background: Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine treatment. Purpose: In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance radiologists with without assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans. Methods: For development validation, total number 694 cases 111,066 slides were retrospectively collected as...
Early diagnosis of Alzheimer's disease (AD) is an important task that facilitates the development treatment and prevention strategies may potentially improve patient outcomes. Neuroimaging has shown great promise, including amyloid-PET which measures accumulation amyloid plaques in brain - a hallmark AD. It desirable to train end-to-end deep learning models predict progression AD for individuals at early stages based on 3D amyloid-PET. However, commonly used are trained fully supervised...
Radar sensors, leveraging the Doppler effect, enable nonintrusive capture of kinetic and physiological motions while preserving privacy. Deep learning (DL) facilitates radar sensing for healthcare applications such as gait recognition vital-sign measurement. However, band-dependent patterns, indicating variations in patterns power scales associated with frequencies time–frequency representation (TFR), challenge using DL. Frequency-dependent characteristics features lower may be overlooked...
A multi-resolution unsharp masking (USM) technique is developed for image feature enhancement in digital mammogram images. This includes four processing phases: (1) determination of parameters analysis (MRA) based on the properties images; (2) decomposition original images into sub-band via wavelet transformation with perfect reconstruction filters; (3) modification adaptive technique; and (4) from modified sub- band inverse transformation. An applied to order modify pixel values edge...
This paper describes the effect of a computer-aided detection (CAD) system's false positive marks on observer performance when interpreting films containing lung cancer. We compared location/no location chosen initially by radiologists and stability or change in that followed provision CAD information. found difference radiologists' behavior depended whether initial interpretation was true detection. When radiologist made an incorrect decision, decision less stable than correct.
This paper presents an approach using a stepwise binary decision classification to enable significant reduction of non-AFB false positive (FP) objects while maintaining similar true (TP) detection improve performance.
In this article, we analyze and report cases of three patients who were admitted to Renmin Hospital, Wuhan University, China, for treating COVID-19 pneumonia in February 2020 unresponsive initial treatment steroids. They then received titrated steroids based on the assessment computed tomography (CT) images augmented analyzed with artificial intelligence (AI) tool output. Three finally recovered discharged. The result indicated that sufficient may be effective after frequent evaluation...
Purpose: Given the recent COVID-19 pandemic and its stress on global medical resources, presented here is development of a machine intelligent method for thoracic computed tomography (CT) to inform management patients steroid treatment. Approach: Transfer learning has demonstrated strong performance when applied imaging, particularly only limited data are available. A cascaded transfer approach extracted quantitative features from CT sections using fine-tuned VGG19 network. The slice were...
The goal of the study was to compare a cathode-ray-tube (CRT) digital display with film by using task-dependent image quality assessment methods. Contrast-detail analysis utilized. Human observers performed simple detection task, specifically, detecting pillbox target in uniform Poisson field, either or that employed CRT monitor. Observers equally well on both and when window settings were established subjectively radiologist. Changing match average background luminance film-illuminator...
An artificial neural network (ANN) based hybrid detection system is proposed and developed for fast, accurate, automatically processing multispectral satellite cloud imagery to identify ship tracks. Imagery observed at both 11.0, 3.7 0.67 /spl mu/m by Advanced Very High Resolution Radiometer (AVHRR) NOAA polar-orbiting used in this development. A data base containing 5 different categories of tracks on their contrast edge information have been created. After image enhancement morphology...