A5087446167- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Medical Image Segmentation Techniques
- Cardiac Valve Diseases and Treatments
- Advanced Neural Network Applications
- Medical Imaging and Analysis
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Infective Endocarditis Diagnosis and Management
- COVID-19 Clinical Research Studies
- Coronary Interventions and Diagnostics
- Multimodal Machine Learning Applications
- Machine Learning in Healthcare
- Aortic Disease and Treatment Approaches
- Anomaly Detection Techniques and Applications
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Domain Adaptation and Few-Shot Learning
- Sepsis Diagnosis and Treatment
- Advanced Radiotherapy Techniques
- Colorectal Cancer Screening and Detection
- Robotics and Sensor-Based Localization
- Radiology practices and education
- Dental Radiography and Imaging
Medical Solutions
2025
Siemens (Germany)
2014-2025
Siemens Healthcare (United States)
2016-2024
Siemens (United States)
2014-2024
Siemens Healthcare (Germany)
2020-2021
Technical University of Munich
2010-2014
Princeton University
2013
Graz University of Technology
2010
Robust and fast detection of anatomical structures is a prerequisite for both diagnostic interventional medical image analysis. Current solutions anatomy are typically based on machine learning techniques that exploit large annotated databases in order to learn the appearance captured anatomy. These subject several limitations, including use suboptimal feature engineering most importantly computationally search-schemes detection. To address these issues, we propose method follows new...
3-D image registration, which involves aligning two or more images, is a critical step in variety of medical applications from diagnosis to therapy. Image registration commonly performed by optimizing an matching metric as cost function. However this task challenging due the non-convex nature over plausible parameter space and insufficient approches for robust optimization. As result, current approaches are often customized specific problem sensitive quality artifacts. In paper, we propose...
Purpose To present a method that automatically segments and quantifies abnormal CT patterns commonly in COVID-19, namely ground-glass opacities consolidations. Materials Methods In this retrospective study, the proposed takes as input noncontrast chest lesions, lungs, lobes three dimensions, based on dataset of 9749 volumes. The outputs two combined measures severity lung lobe involvement, quantifying both extent COVID-19 abnormalities presence high opacities, deep learning reinforcement...
Prostate-specific membrane antigen (PSMA)–targeting PET imaging is becoming the reference standard for prostate cancer staging, especially in advanced disease. Yet, implications of PSMA PET–derived whole-body tumor volume overall survival are poorly elucidated to date. This might be because semiautomated quantification as a biomarker an unmet clinical challenge. Therefore, present study we propose and evaluate software that enables biomarkers such volume. <b>Methods:</b> The proposed...
Deep learning models have demonstrated remarkable success in multi-organ segmentation but typically require large-scale datasets with all organs of interest annotated. However, medical image are often low sample size and only partially labeled, i.e., a subset Therefore, it is crucial to investigate how learn unified model on the available labeled leverage their synergistic potential. In this paper, we systematically partial-label problem theoretical empirical analyses prior techniques. We...
Building accurate and robust artificial intelligence systems for medical image assessment requires the creation of large sets annotated training examples. However, constructing such datasets is very costly due to complex nature annotation tasks, which often require expert knowledge (e.g., a radiologist). To counter this limitation, we propose method learn from images at scale in self-supervised way.Our approach, based on contrastive learning online feature clustering, leverages over...
Detecting malignant pulmonary nodules at an early stage can allow medical interventions which may increase the survival rate of lung cancer patients. Using computer vision techniques to detect improve sensitivity and speed interpreting chest CT for screening. Many studies have used CNNs nodule candidates. Though such approaches been shown outperform conventional image processing based methods regarding detection accuracy, are also known be limited generalize on under-represented samples in...
Building accurate and robust artificial intelligence systems for medical image assessment requires not only the research design of advanced deep learning models but also creation large curated sets annotated training examples. Constructing such datasets, however, is often very costly -- due to complex nature annotation tasks high level expertise required interpretation images (e.g., expert radiologists). To counter this limitation, we propose a method self-supervised rich features based on...
<title>Abstract</title> Vision-Language (VL) models such as Contrastive Language-Image pretraining (CLIP) use multimodal self-supervised learning (SSL) methods to extract maximal information from large-scale datasets. This enables the trained model learn key image encodings while correlating them corresponding textual through a contrastive loss function that maximizes similarity of VL pairs. Due weak supervision provided by text information, these demonstrate strong zero-shot classification...
The aim of this study was to leverage volumetric quantification airspace disease (AD) derived from a superior modality (computed tomography [CT]) serving as ground truth, projected onto digitally reconstructed radiographs (DRRs) (1) train convolutional neural network (CNN) quantify AD on paired chest (CXRs) and CTs, (2) compare the DRR-trained CNN expert human readers in CXR evaluation patients with confirmed COVID-19.We retrospectively selected cohort 86 COVID-19 (with positive reverse...
We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax pelvis on computed tomography (CT) images for radiation treatment planning.The identifies region of interest (ROI) by detecting anatomical landmarks around specific using reinforcement learning technique. The segmentation is restricted to this ROI performed image-to-image (DI2IN) based convolutional encoder-decoder architecture combined with multi-level feature concatenation....
Though large-scale datasets are essential for training deep learning systems, it is expensive to scale up the collection of medical imaging datasets. Synthesizing objects interests, such as lung nodules, in images based on distribution annotated can be helpful improving supervised tasks, especially when limited by size and class balance. In this paper, we propose class-aware adversarial synthesis framework synthesize nodules CT images. The built with a coarse-to-fine patch in-painter...