A5082042615- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Fetal and Pediatric Neurological Disorders
- Functional Brain Connectivity Studies
- MRI in cancer diagnosis
- Tensor decomposition and applications
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Bone and Joint Diseases
- Medical Imaging and Analysis
- Traumatic Brain Injury Research
- AI in cancer detection
- Neurological disorders and treatments
- Cell Image Analysis Techniques
- Domain Adaptation and Few-Shot Learning
- NMR spectroscopy and applications
- Glioma Diagnosis and Treatment
- Digital Imaging for Blood Diseases
- Spinal Dysraphism and Malformations
- Peripheral Nerve Disorders
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Genetic Neurodegenerative Diseases
Harvard University
2016-2025
Brigham and Women's Hospital
2016-2025
Mass General Brigham
2025
Harvard–MIT Division of Health Sciences and Technology
2025
Boston University
2025
NYU Langone Health
2024
University Radiology
2024
Thomas Jefferson University
2024
University of Electronic Science and Technology of China
2024
Harvard University Press
2022
biopsy in our patients did not show evidence of Crohn's disease, but there was unequivocal disease elsewhere.Furthermore, the failure symptoms who do smoke to respond treatment suggests peptic ulceration associated with disease.Treatment omeprazole led prompt relief and complete healing ulceration, which confirmed by endoscopy.Omeprazole is effective resistant ulcera- tion,' only one report its use disease.4A proton pump inhibitor, it capable maintaining high intragastric pH for long...
We propose a new white matter atlas creation method that learns model of the common structures present in group subjects. demonstrate our method, which is based on spectral clustering tractography, discovers corresponding to expected anatomy such as corpus callosum, uncinate fasciculus, cingulum bundles, arcuate and corona radiata. The clusters are augmented with expert anatomical labels stored type we call high-dimensional atlas. then show how perform automatic segmentation tractography...
White matter bundle segmentation using diffusion MRI fiber tractography has become the method of choice to identify white pathways in vivo human brains. However, like other analyses complex data, there is considerable variability protocols and techniques. This can result different reconstructions same intended pathways, which directly affects results, quantification, interpretation. In this study, we aim evaluate quantify that arises from for segmentation. Through an open call users...
Abstract A surgical guidance and visualization system is presented, which uniquely integrates capabilities for data analysis on‐line interventional into the setting of MRI. Various pre‐operative scans (T1‐ T2‐weighted MRI, MR angiography, functional MRI (fMRI)) are fused automatically aligned with operating field system. Both pre‐surgical intra‐operative may be segmented to generate three‐dimensional surface models key anatomical structures. Models combined in a scene along reformatted...
We propose a method for the automated identification of key white matter fiber tracts neurosurgical planning, and we apply in retrospective study 18 consecutive patients with brain tumors. Our is designed to be relatively robust challenges tractography, which include peritumoral edema, displacement, mass effect caused by lesions. The proposed has two parts. First, learn data-driven parcellation or cluster atlas using groupwise registration spectral clustering multi-fiber tractography from...
Abstract Diffusion MRI (dMRI) is the only noninvasive method for mapping white matter connections in brain. We describe SlicerDMRI, a software suite that enables visualization and analysis of dMRI neuroscientific studies patient-specific anatomic assessment. SlicerDMRI has been successfully applied multiple human brain health disease, here, we especially focus on its cancer research applications. As an extension module 3D Slicer medical image computing platform, clinically relevant...
There are two popular approaches for automated white matter parcellation using diffusion MRI tractography, including fiber clustering strategies that group fibers according to their geometric trajectories and cortical-parcellation-based focus on the structural connectivity among different brain regions of interest. While multiple studies have assessed test-retest reproducibility parcellations strategies, there no existing parcellation. In this work, we perform what believe is first study...
PURPOSE We present SlicerDMRI, an open-source software suite that enables research using diffusion magnetic resonance imaging (dMRI), the only modality can map white matter connections of living human brain. SlicerDMRI analysis and visualization dMRI data is aimed at needs clinical users. built upon deeply integrated with 3D Slicer, a National Institutes Health–supported platform for medical image informatics, processing, three-dimensional visualization. Integration Slicer provides many...
Segmentation of brain tissue types from diffusion MRI (dMRI) is an important task, required for quantification microstructure and improving tractography. Current dMRI segmentation mostly based on anatomical (e.g., T1- T2-weighted) that registered to the space. However, such inter-modality registration challenging due more image distortions lower resolution in as compared with MRI. In this study, we present a deep learning method segmentation, which refer DDSeg. Our proposed learns...
The Adolescent Brain Cognitive Development (ABCD) Study® has collected data from over 10,000 children across 21 sites, providing insights into adolescent brain development. However, site-specific scanner variability made it challenging to use diffusion MRI (dMRI) this study. To address this, a dataset of harmonized and processed ABCD dMRI (from release 3) been created, comprising quality-controlled imaging 9,345 subjects, focusing exclusively on the baseline session, i.e., first time point...
ABSTRACT Tractography parcellation classifies streamlines reconstructed from diffusion MRI into anatomically defined fiber tracts for clinical and research applications. However, scans often have incomplete fields of view (FOV) where brain regions are partially imaged, leading to partial, or truncated tracts. To address this challenge, we introduce TractCloud‐FOV, a deep learning framework that robustly parcellates tractography under conditions FOV. We propose novel training strategy,...