A5016047550- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Colorectal Cancer Screening and Detection
- Medical Image Segmentation Techniques
- COVID-19 diagnosis using AI
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Medical Imaging and Analysis
- Advanced Neural Network Applications
- Lung Cancer Diagnosis and Treatment
- Image Retrieval and Classification Techniques
- Artificial Intelligence in Healthcare and Education
- Advanced MRI Techniques and Applications
- MRI in cancer diagnosis
- Gastric Cancer Management and Outcomes
- Colorectal Cancer Surgical Treatments
- Cardiac Imaging and Diagnostics
- Pancreatic and Hepatic Oncology Research
- Radiation Dose and Imaging
- Topic Modeling
- Radiology practices and education
- Prostate Cancer Diagnosis and Treatment
- Nutrition and Health in Aging
- Body Composition Measurement Techniques
- Liver Disease Diagnosis and Treatment
National Institutes of Health Clinical Center
2016-2025
National Institutes of Health
2015-2024
Walter Reed National Military Medical Center
2017-2024
Baltimore VA Medical Center
2024
Children's Hospital of Philadelphia
1998-2024
The London College
2024
University of Wisconsin–Madison
2024
General Electric (Spain)
2024
Bracco (Germany)
2024
University of Illinois Chicago
2024
Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical features from sufficient training data. However, obtaining as comprehensively ImageNet medical imaging domain remains a challenge. There are currently three major techniques that successfully employ classification: CNN scratch, using off-the-shelf...
The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis many lung diseases. A tremendous number imaging studies accompanied by reports are accumulated stored in modern hospitals' Picture Archiving Communication Systems (PACS). On other side, it still an open question how this type hospital-size knowledge database containing invaluable informatics (i.e., loosely labeled) can be used to facilitate data-hungry deep learning paradigms building...
Artificial intelligence (AI) continues to garner substantial interest in medical imaging. The potential applications are vast and include the entirety of imaging life cycle from image creation diagnosis outcome prediction. chief obstacles development clinical implementation AI algorithms availability sufficiently large, curated, representative training data that includes expert labeling (eg, annotations). Current supervised methods require a curation process for optimally train, validate,...
International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far most widely investigated medical processing task, but various segmentation typically been organized in isolation, such that algorithm development was driven by need to tackle single clinical problem. We hypothesized method capable performing well on multiple tasks will generalize previously unseen task and potentially outperform...
Semantic segmentation of medical images aims to associate a pixel with label in image without human initialization. The success semantic algorithms is contingent on the availability high-quality imaging data corresponding labels provided by experts. We sought create large collection annotated datasets various clinically relevant anatomies available under open source license facilitate development algorithms. Such resource would allow: 1) objective assessment general-purpose methods through...
Automated computer-aided detection (CADe) in medical imaging has been an important tool clinical practice and research. State-of-the-art methods often show high sensitivities but at the cost of false-positives (FP) per patient rates. We design a two-tiered coarse-to-fine cascade framework that first operates candidate generation system $\sim$100% FP levels. By leveraging existing CAD systems, coordinates regions or volumes interest (ROI VOI) for lesion candidates are generated this step...
Labeled medical imaging data is scarce and expensive to generate. To achieve generalizable deep learning models large amounts of are needed. Standard augmentation a method increase generalizability routinely performed. Generative adversarial networks offer novel for augmentation. We evaluate the use CycleGAN in CT segmentation tasks. Using image database we trained transform contrast images into non-contrast images. then used augment our training using these synthetic compared performance...
Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation scans differentiation findings from other entities. Here we show that series deep learning algorithms, trained diverse multinational cohort 1280 patients localize parietal pleura/lung parenchyma followed by classification pneumonia, can achieve up 90.8% accuracy, with 84% sensitivity and 93% specificity,...
Extracting, harvesting, and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. Meanwhile, vast amounts of clinical annotations have been collected stored in hospitals' picture archiving communication systems (PACS). These types annotations, also known as bookmarks PACS, are usually marked by radiologists during their daily workflow to highlight significant findings that may serve reference for later studies. We propose mine harvest...
Chest X-rays are one of the most common radiological examinations in daily clinical routines. Reporting thorax diseases using chest is often an entry-level task for radiologist trainees. Yet, reading a X-ray image remains challenging job learning-oriented machine intelligence, due to (1) shortage large-scale machine-learnable medical datasets, and (2) lack techniques that can mimic high-level reasoning human radiologists requires years knowledge accumulation professional training. In this...
Automation-assisted cervical screening via Pap smear or liquid-based cytology (LBC) is a highly effective cell imaging based cancer detection tool, where cells are partitioned into "abnormal" and "normal" categories. However, the success of most traditional classification methods relies on presence accurate segmentations. Despite sixty years research in this field, segmentation remains challenge clusters pathologies. Moreover, previous only built upon extraction hand-crafted features, such...
Despite the recent advances in automatically describing image contents, their applications have been mostly limited to caption datasets containing natural images (e.g., Flickr 30k, MSCOCO). In this paper, we present a deep learning model efficiently detect disease from an and annotate its contexts location, severity affected organs). We employ publicly available radiology dataset of chest x-rays reports, use annotations mine names train convolutional neural networks (CNNs). doing so, adopt...
Interstitial lung diseases (ILD) involve several abnormal imaging patterns observed in computed tomography (CT) images. Accurate classification of these plays a significant role precise clinical decision making the extent and nature diseases. Therefore, it is important for developing automated pulmonary computer-aided detection systems. Conventionally, this task relies on experts' manual identification regions interest (ROIs) as prerequisite to diagnose potential This protocol time consuming...
Background Abdominal and thoracic CT provide a valuable opportunity for osteoporosis screening regardless of the clinical indication imaging. Purpose To establish reference normative ranges first lumbar vertebra (L1) trabecular attenuation values across all adult ages to measure bone mineral density (BMD) at routine CT. Materials Methods Reference data were constructed from 20 374 abdominal and/or examinations performed 120 kV. Data derived adults (mean age, 60 years ± 12 [standard...
As one of the most ubiquitous diagnostic imaging tests in medical practice, chest radiography requires timely reporting potential findings and diagnosis diseases images. Automated, fast, reliable detection based on is a critical step radiology workflow. In this work, we developed evaluated various deep convolutional neural networks (CNN) for differentiating between normal abnormal frontal radiographs, order to help alert radiologists clinicians as means work list triaging prioritization. A...
Purpose Multiparametric MRI (mpMRI) improves the detection of clinically significant prostate cancer, but is limited by interobserver variation. The second version theProstate Imaging Reporting and Data System (PIRADSv2) was recently proposed as a standard for interpreting mpMRI. To assess performance agreement PIRADSv2 we performed multi-reader study with five radiologists varying experience. Materials Methods Five (n = 2 dedicated, n 3 general body) blinded to clinicopathologic results...