A5102676931- Medical Image Segmentation Techniques
- Dementia and Cognitive Impairment Research
- Advanced Neuroimaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Domain Adaptation and Few-Shot Learning
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- Neurological Disease Mechanisms and Treatments
- Functional Brain Connectivity Studies
- AI in cancer detection
- Generative Adversarial Networks and Image Synthesis
- Statistical Methods and Inference
- Osteoarthritis Treatment and Mechanisms
- Morphological variations and asymmetry
- Advanced MRI Techniques and Applications
- Machine Learning in Healthcare
- Cancer-related molecular mechanisms research
- Medical Imaging and Analysis
- 3D Shape Modeling and Analysis
- Medical Imaging Techniques and Applications
- Bayesian Methods and Mixture Models
- Alzheimer's disease research and treatments
- Artificial Intelligence in Healthcare and Education
- Insurance, Mortality, Demography, Risk Management
University of Copenhagen
2013-2023
Copenhagen University Hospital
2022-2023
Rigshospitalet
2022-2023
Stanford University
2021
KVG Medical College & Hospital
2014
Quality of Life Research Center
2013
General Electric (India)
2011
The University of Texas at El Paso
2010
In this work, we report the set-up and results of Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Conferences Medical Image Computing Computer-Assisted Intervention (MICCAI) 2018. The image dataset is diverse contains primary secondary tumors varied sizes appearances various lesion-to-background levels (hyper-/hypo-dense), created collaboration seven hospitals research institutions. Seventy-five...
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...
In this work, we report the set-up and results of Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Conferences Medical Image Computing Computer-Assisted Intervention (MICCAI) 2018. The image dataset is diverse contains primary secondary tumors varied sizes appearances various lesion-to-background levels (hyper-/hypo-dense), created collaboration seven hospitals research institutions. Seventy-five...
This paper presents a brain T1-weighted structural magnetic resonance imaging (MRI) biomarker that combines several individual MRI biomarkers (cortical thickness measurements, volumetric hippocampal shape, and texture). The method was developed, trained, evaluated using two publicly available reference datasets: standardized dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) arm of Australian Imaging Biomarkers Lifestyle flagship study ageing (AIBL). In addition, by...
Abstract Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers prognostic markers disease progression death. From a cohort approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for disease; 3944 cases had least one positive test subjected further analysis. from the...
Purpose To organize a multi-institute knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic methods relevant monitoring osteoarthritis progression. Materials Methods A dataset partition consisting three-dimensional from 88 retrospective patients at two time points (baseline 1-year follow-up) with ground truth articular (femoral, tibial, patellar) cartilage meniscus segmentations was standardized. Challenge submissions majority-vote ensemble were...
Pulmonary opacification is the inflammation in lungs caused by many respiratory ailments, including novel corona virus disease 2019 (COVID-19). Chest X-rays (CXRs) with such opacifications render regions of imperceptible, making it difficult to perform automated image analysis on them. In this work, we focus segmenting from abnormal CXRs as part a pipeline aimed at risk scoring COVID-19 CXRs. We treat high opacity missing data and present modified CNN-based segmentation network that utilizes...
Alzheimer’s disease (AD) is a progressive, incurable neurodegenerative and the most common type of dementia. It cannot be prevented, cured or drastically slowed, even though AD research has increased in past 5-10 years. Instead focusing on brain volume single structures like hippocampus, this paper investigates relationship proximity between regions uses information as novel way classifying normal control (NC), mild cognitive impaired (MCI), subjects. A longitudinal cohort 528 subjects (170...
Abstract Objective To determine the inflammatory analytes that predict clinical progression and evaluate their performance against biomarkers of neurodegeneration. Methods A longitudinal study MCI‐AD patients in a Discovery cohort over 15 months, with replication Alzheimer’s Disease Neuroimaging Initiative (ADNI) MCI 36 months. Fifty‐three were measured CSF plasma RBM multiplex analyte platform. Inflammatory on Clinical Dementia Rating Scale‐Sum Boxes (CDR‐SB) Mini Mental State Exam scores...
In this paper, we propose a multi-scale, multi-kernel shape, compactly supported kernel bundle framework for stationary velocity field-based image registration (Wendland field, wKB-SVF). We exploit the possibility of directly choosing kernels to construct reproducing Hilbert space (RKHS) instead imposing it from differential operator. The proposed allows us minimize computational cost without sacrificing theoretical foundations SVF-based diffeomorphic registration. order recover deformations...
Quantitative characterization of disease progression using longitudinal data can provide long-term predictions for the pathological stages individuals. This work studies robust modeling Alzheimer's parametric methods. The proposed method linearly maps individual's age to a score (DPS) and jointly fits constrained generalized logistic functions dynamics biomarkers as DPS M-estimation. Robustness estimates is quantified bootstrapping via Monte Carlo resampling, estimated inflection points...
Disease progression modeling (DPM) using longitudinal data is a challenging task in machine learning for healthcare that can provide clinicians with better tools diagnosis and monitoring of disease. Existing DPM algorithms neglect temporal dependencies among measurements make parametric assumptions about biomarker trajectories. In addition, they do not model multiple biomarkers jointly need to align subjects' this paper, recurrent neural networks (RNNs) are utilized address these issues....
Segmenting vascular pathologies such as white matter lesions in Brain magnetic resonance images (MRIs) require acquisition of multiple sequences T1-weighted (T1-w) --on which appear hypointense-- and fluid attenuated inversion recovery (FLAIR) sequence --where hyperintense--. However, most the existing retrospective datasets do not consist FLAIR sequences. Existing missing modality imputation methods separate process imputation, segmentation. In this paper, we propose a method to link both...
Diffeomorphic deformation is a popular choice in medical image registration. A fundamental property of diffeomorphisms invertibility, implying that once the relation between two points to B found, then given per definition. Consistency measure numerical algorithm's ability mimic this and achieving consistency has proven be challenge for many state-of-the-art algorithms. We present CDD (Collocation Deformations), solution diffeomorphic registration, which solves Stationary Velocity Field...
Segmentation of medical image volumes is a time-consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it unclear how they behave in other clinical settings.To evaluate the performance open-source Multi-Planar U-Net (MPUnet), validated Knee Imaging Quantification (KIQ) framework, state-of-the-art two-dimensional (2D) architecture on three cohorts without extensive adaptation algorithms.Retrospective cohort study.A total 253 subjects (146 females, 107...
The rising burden of non-communicable diseases (NCDs) in India necessitates more studies on nutritional intake and dietary behaviour. While data exists low-income groups, rural populations the population at large, limited information that urban, working professionals – a demographic has means access to make informed choices, yet, have disproportionately high risk NCDs. aim this study was investigate nutrient Indian professionals. A cross-sectional conducted 214 (aged 30-40 years; 69 females...
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...