A5002245327- COVID-19 diagnosis using AI
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Lung Cancer Diagnosis and Treatment
- Video Surveillance and Tracking Methods
- Image Retrieval and Classification Techniques
- Cardiac Imaging and Diagnostics
- Advanced X-ray and CT Imaging
- Dementia and Cognitive Impairment Research
- Radiation Dose and Imaging
- Machine Learning in Healthcare
- Image and Object Detection Techniques
- Infrared Target Detection Methodologies
- Artificial Intelligence in Healthcare and Education
- Advanced Image and Video Retrieval Techniques
- Tuberculosis Research and Epidemiology
- Radiology practices and education
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Dental Radiography and Imaging
- Medical Imaging and Analysis
- Advanced Neural Network Applications
- Image Processing Techniques and Applications
- Mycobacterium research and diagnosis
The Ohio State University
2019-2023
The Ohio State University Wexner Medical Center
2019-2023
National Institutes of Health
2014-2021
Novartis (Switzerland)
2020
Eli Lilly (United States)
2020
Alzheimer’s Disease Neuroimaging Initiative
2020
Janssen (Belgium)
2020
Sunesis (United States)
2020
Piramal (India)
2020
Alzheimer's Drug Discovery Foundation
2020
The U.S. National Library of Medicine has made two datasets postero-anterior (PA) chest radiographs available to foster research in computer-aided diagnosis pulmonary diseases with a special focus on tuberculosis (TB). were acquired from the Department Health and Human Services, Montgomery County, Maryland, USA Shenzhen No. 3 People's Hospital China. Both contain normal abnormal X-rays manifestations TB include associated radiologist readings.
The National Library of Medicine (NLM) is developing a digital chest X-ray (CXR) screening system for deployment in resource constrained communities and countries worldwide with focus on early detection tuberculosis. A critical component the computer-aided diagnosis CXRs automatic lung regions. In this paper, we present nonrigid registration-driven robust segmentation method using image retrieval-based patient specific adaptive models that detects boundaries, surpassing state-of-the-art...
Pneumonia affects 7% of the global population, resulting in 2 million pediatric deaths every year. Chest X-ray (CXR) analysis is routinely performed to diagnose disease. Computer-aided diagnostic (CADx) tools aim supplement decision-making. These process handcrafted and/or convolutional neural network (CNN) extracted image features for visual recognition. However, CNNs are perceived as black boxes since their performance lack explanations. This a serious bottleneck applications involving...
Tuberculosis (TB) is a major global health threat. An estimated one-third of the world's population has history TB infection, and millions new infections are occurring every year. The advent powerful hardware software techniques triggered attempts to develop computer-aided diagnostic systems for detection in support inexpensive mass screening developing countries. In this paper, we describe medical background chest X-rays present survey recent approaches using detection. After thorough...
Chest x-ray (CXR) analysis is a common part of the protocol for confirming active pulmonary Tuberculosis (TB). However, many TB endemic regions are severely resource constrained in radiological services impairing timely detection and treatment. Computer-aided diagnosis (CADx) tools can supplement decision-making while simultaneously addressing gap expert interpretation during mobile field screening. These use hand-engineered and/or convolutional neural networks (CNN) computed image features....
The view information of a chest X-ray (CXR), such as frontal or lateral, is valuable in computer aided diagnosis (CAD) CXRs. For example, it helps for the selection atlas models automatic lung segmentation. However, very often, image header does not provide information. In this paper, we present new method classifying CXR into two categories: vs. lateral view. consists three major components: pre-processing, feature extraction, and classification. features selected are profile, body size...
Tuberculosis is a major global health threat claiming millions of lives each year. While the total number tuberculosis cases has been decreasing over last years, rise drug-resistant reduced chance controlling disease. The purpose to implement timely diagnosis tuberculosis, which essential administering adequate treatment regimens and stopping further transmission tuberculosis.A main tool for diagnosing conventional chest X-ray. We are investigating possibility discriminating automatically...
According to the World Health Organization (WHO), tuberculosis (TB) remains most deadly infectious disease in world. In a 2015 global annual TB report, 1.5 million related deaths were reported. The conditions worsened 2016 with 1.7 reported and more than 10 people infected disease. Analysis of frontal chest X-rays (CXR) is one popular methods for initial screening, however, method impacted by lack experts screening radiographs. Computer-aided diagnosis (CADx) tools have gained significance...
Pneumonia is a severe inflammatory condition of the lungs that leads to formation pus and other liquids in air sacs. The disease reported affect approximately 450 million people across world, resulting 2 pediatric deaths every year. Chest X-ray (CXR) analysis most frequently performed radiographic examination for diagnosing disease. Unlike pneumonia adults, poorly studied. Computer-aided diagnostic (CADx) tools aim improve diagnosis supplement decision making while simultaneously bridging...
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...
To delineate image data curation needs and describe a locally designed graphical user interface (GUI) to aid radiologists in annotation for artificial intelligence (AI) applications medical imaging.GUI components support analysis toolboxes, picture archiving communication system integration, third-party applications, processing of scripting languages, integration deep learning libraries. For clinical AI GUI included two-dimensional segmentation classification; three-dimensional...
This study investigates using deep convolutional neural networks (CNN) for automatic detection of cardiomegaly in digital chest X-rays (CXRs). First, we employ and fine-tune several CNN architectures to detect presence CXRs. Next, introduce a CXR-based pre-trained model where first fully train an architecture with very large CXR dataset then the system Finally, investigate correlation between softmax probability severity disease. We use two publicly available datasets, NLM-Indiana Collection...
Accurate lung segmentation in chest Computed Tomography (CT) scans is a challenging problem because of variations volume shape, susceptibility to partial effects that affect thin antero-posterior junction lines, and lack contrast between the surrounding tissues. To address need for robust method segmentation, we present new method, called Pixel-based two-Scan Connected Component Labeling-Convex Hull-Closed Principal Curve (PSCCL-CH-CPC), which automatically detects boundaries, surpasses...
Tuberculosis (TB) is a major public health problem worldwide, and highly prevalent in developing countries. According to the World Health Organization (WHO), over 95% of TB deaths occur low- middle- income countries that often have under-resourced care systems. In an effort aid population screening such resource challenged settings, U.S. National Library Medicine has developed chest X-ray (CXR) system provides pre-decision on pulmonary abnormalities. When presented with digital CXR image...
Automatic analysis of chest X-ray images is one important approach for screening/identifying pulmonary diseases. The existence foreign objects in the hinders performance such processing. In this paper, we focus on type that often shown a large dataset X-rays are working on-the buttons gown patient wearing. method propose involves four major steps: intensity normalization, low contrast image identification and enhancement, segmentation lung regions, button object extraction. Based...
This study proposes a novel automated method for cardiomegaly detection in chest X-rays (CXRs). The algo- rithm has two main stages: i) heart and lung region localization on CXRs, ii) radiographic index extraction from the boundaries. We employed algorithm extended it to automatically compute typical models of regions are learned using public CXR dataset with boundary markings. estimates location these candidate ('patient') images by registering patient CXR. For computation, we implemented...
Tuberculosis (TB) is a severe comorbidity of HIV and chest x-ray (CXR) analysis necessary step in screening for the infective disease. Automatic digital CXR images detecting pulmonary abnormalities critical population screening, especially medical resource constrained developing regions. In this article, we describe steps that improve previously reported performance NLM's algorithms help advance state art field. We propose local-global classifier fusion method where two complementary...