A5078494006- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Prostate Cancer Diagnosis and Treatment
- Medical Imaging and Analysis
- Functional Brain Connectivity Studies
- AI in cancer detection
- Image and Object Detection Techniques
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
- Advanced Radiotherapy Techniques
- Cardiac Imaging and Diagnostics
- Urinary Bladder and Prostate Research
- Robotics and Sensor-Based Localization
- 3D Shape Modeling and Analysis
- Fetal and Pediatric Neurological Disorders
- COVID-19 diagnosis using AI
- MRI in cancer diagnosis
- Autism Spectrum Disorder Research
- Domain Adaptation and Few-Shot Learning
- Brain Tumor Detection and Classification
- Hepatocellular Carcinoma Treatment and Prognosis
- Cardiovascular Function and Risk Factors
Yale University
2016-2025
University of New Haven
2019-2024
Elucid Bioimaging
2024
Creative Commons
2023
Swiss National Science Foundation
2023
University of Bern
2023
University Hospital of Bern
2023
University of Parma
2023
Jacksonville College
2023
Mayo Clinic in Florida
2023
Elevated levels of glucocorticoids in depression have been hypothesized to be associated with damage the hippocampus, a brain area involved learning and memory. The purpose this study was measure hippocampal volume patients depression.Magnetic resonance imaging used hippocampus 16 major remission case-matched nondepressed comparison subjects.Patients had statistically significant 19% smaller left than subjects, without volumes regions (amygdala, caudate, frontal lobe, temporal lobe) or whole...
OBJECTIVE: Smaller hippocampal volume has been reported only in some but not all studies of unipolar major depressive disorder. Severe stress early life also associated with smaller and persistent changes the hypothalamic-pituitary-adrenal axis. However, prior morphometric depressed patients have neither nor controlled for a history childhood trauma. In this study, volumes hippocampus control brain regions were measured women without abuse healthy nonabused comparison subjects. METHOD: Study...
Segmentation using boundary finding is enhanced both by considering the as a whole and model-based global shape information. The authors apply flexible constraints, in form of probabilistic deformable model, to problem segmenting natural 2-D objects whose diversity irregularity make them poorly represented terms fixed features or form. parametric model based on elliptic Fourier decomposition boundary. Probability distributions parameters representation bias particular overall while allowing...
OBJECTIVE: Animal studies have suggested that early stress is associated with alterations in the hippocampus, a brain area plays critical role learning and memory. The purpose of this study was to measure both hippocampal structure function women without childhood sexual abuse diagnosis posttraumatic disorder (PTSD). METHOD: Thirty-three participated study, including PTSD (N=10), (N=12), or (N=11). Hippocampal volume measured magnetic resonance imaging all subjects, during performance...
Childhood sexual abuse is very common in our society, but little known about the long-term effects of on brain function. The purpose this study was to measure neural correlates memories childhood sexually abused women with and without diagnosis posttraumatic stress disorder (PTSD).Twenty-two a history underwent injection [15O]H2O, followed by positron emission tomography imaging while they listened neutral traumatic (personalized events) scripts. Brain blood flow during exposure scripts...
Animals exposed to stress exhibit a decrease in benzodiazepine receptor binding the frontal cortex. No studies have examined central patients with posttraumatic disorder (PTSD). The purpose of this study was examine measures PTSD.From 13 Vietnam combat-related PTSD and case-matched healthy comparison subjects, quantitative measure related (distribution volume) obtained single photon emission computed tomography (SPECT) imaging [(123)I]iomazenil measurement radioligand concentration plasma....
Objective. To compare regional brain volumes measured in term and preterm infants, to correlate with measures of neurodevelopmental outcome. Methods. High-contrast, high-resolution magnetic resonance imaging scans were acquired 10 14 infants who scanned near term. The cerebrum was segmented into cortical gray matter, white cerebral ventricles, subcortical cerebellum, brainstem. ventricles further divided specific anatomic subregions, the compared across groups. Measures cognitive motor...
Deep learning models have shown their advantage in many different tasks, including neuroimage analysis. However, to effectively train a high-quality deep model, the aggregation of significant amount patient information is required. The time and cost for acquisition annotation assembling, example, large fMRI datasets make it difficult acquire numbers at single site. due need protect privacy data, hard assemble central database from multiple institutions. Federated allows population-level be...
Automated segmentation in medical image analysis is a challenging task that requires large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited annotated data, which poses major practical problem for accurate and robust segmentation. In addition, semi-supervised are not compared with the supervised counterparts, also lack explicit modeling geometric structure semantic information, both limit accuracy. this work, we present SimCVD,...
Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus instance discrimination and invariant mapping (i.e., pulling positive samples closer negative apart feature space). However, they face three common pitfalls: (1) tailness: data usually follows an implicit long-tail class distribution. Blindly all pixels training hence can lead to imbalance issues, cause...
The cortex is the outermost thin layer of gray matter in brain; geometric measurement helps understanding brain anatomy and function. In quantitative analysis from MR images, extracting structure obtaining a representation for various measurements are key steps. While manual segmentation tedious labor intensive, automatic reliable efficient remain challenging problems, due to its convoluted nature. Here, authors' present new approach coupled-surfaces propagation, using level set methods...
Accurately segmenting and quantifying structures is a key issue in biomedical image analysis. The two conventional methods of segmentation, region-based boundary finding, often suffer from variety limitations. Here the authors propose method which endeavors to integrate approaches an effort form unified approach that robust noise poor initialization. authors' uses Green's theorem derive homogeneous region-classified area integrates this with gray level gradient-based finder. This combines...
The pathophysiology of Tourette syndrome (TS) is thought to involve disturbances in cortico-striato-thalamo-cortical circuitry. morphological characteristics the cortical and associated white matter portions these circuits have not been previously examined TS subjects.High-resolution anatomical magnetic resonance images were acquired 155 131 healthy children adults. cerebrums ventricles isolated then parcellated into subregions using standard landmarks.For analyses that included both adults,...
BioImage Suite is an NIH-supported medical image analysis software suite developed at Yale. It leverages both the Visualization Toolkit (VTK) and Insight (ITK) it includes many additional algorithms for especially in areas of segmentation, registration, diffusion weighted processing fMRI analysis. has a user-friendly user interface Tcl scripting language. A final beta version freely available download.