A5073315969- Glioma Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- MRI in cancer diagnosis
- Advanced Neuroimaging Techniques and Applications
- Machine Learning in Healthcare
- Radiomics and Machine Learning in Medical Imaging
- Topic Modeling
- Medical Image Segmentation Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Prion Diseases and Protein Misfolding
- Brain Metastases and Treatment
- Medical Imaging Techniques and Applications
- Brain Tumor Detection and Classification
- Epilepsy research and treatment
- Radiation Dose and Imaging
- Acute Ischemic Stroke Management
- Functional Brain Connectivity Studies
- Cancer Immunotherapy and Biomarkers
- Diet and metabolism studies
- Meningioma and schwannoma management
- Natural Language Processing Techniques
- Cancer, Hypoxia, and Metabolism
- Biomedical Text Mining and Ontologies
- Parkinson's Disease Mechanisms and Treatments
- Cerebrovascular and Carotid Artery Diseases
Brigham and Women's Hospital
2016-2025
Harvard University
2016-2025
Dana-Farber Cancer Institute
2015-2022
Zero to Three
2021
Prescott Center for the Arts
2019
Lemuel Shattuck Hospital
2014
Harvard University Press
2012
Capital Medical University
2009-2011
Beijing Tian Tan Hospital
2011
Beijing Institute of Neurosurgery
2011
Stimulated Raman scattering microscopy provides a rapid, label-free means of detecting tumor infiltration brain tissue ex vivo and in vivo.
We demonstrate the use of coherent anti-Stokes Raman scattering (CARS) microscopy to image brain structure and pathology ex vivo. Although non-invasive clinical imaging with CT, MRI PET has transformed diagnosis neurologic disease, definitive pre-operative distinction neoplastic benign pathologies remains elusive. Definitive still requires biopsy in a significant number cases. CARS microscopy, nonlinear, vibrationally-sensitive technique, is capable high-sensitivity chemically-selective...
Abstract Purpose To automatically differentiate radiation necrosis from recurrent tumor at high spatial resolution using multiparametric MRI features. Materials and Methods data retrieved 31 patients (15 16 necrosis) who underwent chemoradiation therapy after surgical resection included post‐gadolinium T1, T2, fluid‐attenuated inversion recovery, proton density, apparent diffusion coefficient (ADC), perfusion‐weighted imaging (PWI) ‐derived relative cerebral blood volume (rCBV), flow (rCBF),...
Phosphatidylinositol 3-kinase (PI3K) signaling is highly active in glioblastomas. We assessed pharmacokinetics, pharmacodynamics, and efficacy of the pan-PI3K inhibitor buparlisib patients with recurrent glioblastoma PI3K pathway activation.This study was a multicenter, open-label, multi-arm, phase II trial pathway-activated at first or second recurrence. In cohort 1, scheduled for re-operation after progression received 7 to 13 days before surgery evaluate brain penetration modulation...
Background Approximately one‐fourth of all cancer metastases are found in the brain. MRI is primary technique for detection brain metastasis, planning radiotherapy, and monitoring treatment response. Progress tumor now requires new or growing at small subcentimeter size, when these therapies most effective. Purpose To develop a deep‐learning‐based approach finding metastasis on MRI. Study Type Retrospective. Sequence Axial postcontrast 3D T 1 ‐weighted imaging. Field Strength 1.5T 3T....
<h3>BACKGROUND AND PURPOSE:</h3> Patient survival in high-grade glioma remains poor, despite the recent developments cancer treatment. As new chemo-, targeted molecular, and immune therapies emerge show promising results clinical trials, image-based methods for early prediction of treatment response are needed. Deep learning models that incorporate radiomics features promise to extract information from brain MR imaging correlates with prognosis. We report initial production a combined deep...
Abstract Background Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling prognosis in brain tumor patients. Manual segmentation the components is time-consuming and poses significant reproducibility issues. We compare prediction overall survival (OS) recurrent high-grade glioma(HGG) patients undergoing immunotherapy, using deep learning (DL) classification networks along with radiomic signatures derived manual convolutional...
Background: Computed Tomography Angiography (CTA) is crucial for cerebrovascular disease diagnosis. Dynamic CTA a type of imaging that captures temporal information about the We aim to develop and evaluate two segmentation techniques segment vessels directly on images: (1) creating registering population-averaged vessel atlases (2) using deep learning (DL). Methods: retrieved 4D-CT head from our institutional research database, with bone soft tissue subtracted post-contrast images. An...
While the prognosis of patients with glioblastoma (GBM) remains poor despite recent therapeutic advances, variable survival times suggest wide variation in tumor biology and an opportunity for stratified intervention. We used volumetric analysis morphometrics to measure spatial relationship between subventricular zone (SVZ) proximity a cohort 39 newly diagnosed GBM patients. collected T2-weighted gadolinium-enhanced T1-weighted magnetic resonance images (MRI) at pre-operative,...
We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features linear models. prompts LLMs with expert-crafted queries to generate interpretable from health records. The resulting noisy labels are then used train a simple classifier. Generating based on LLM can empower physicians use their domain expertise craft that clinically meaningful downstream task interest, without having manually extract these raw EHR. motivated by real-world risk...
Abstract Purpose To investigate whether regional brain volumes in adolescent idiopathic scoliosis (AIS) patients differ from matched control subjects as AIS are reported to have poor performance on combined visual and proprioceptive testing impaired postural balance previous studies. Materials Methods Twenty female with typical right‐convex thoracic curve (age range,11–18 years; mean, 14.1 years) 26 controls (mean age, 14.8 underwent three‐dimensional magnetization prepared rapid acquisition...
<h3>BACKGROUND AND PURPOSE:</h3> Clival invasion, a rare but potentially significant complication of pituitary adenoma, is difficult to detect on MR imaging. Because CT widely used in adjunct guidance surgery and it has recently been suggested that preoperative may add useful diagnostic information addition imaging, we performed the first large cross-sectional imaging study define image attributes, clinical correlates, prognostic implications clival invasion for adenoma surgical guidance....
ABSTRACT BACKGROUND AND PURPOSE Language task‐based functional MRI (fMRI) is increasingly used for presurgical planning in patients with brain lesions. Different paradigms elicit activations of different components the language network. The aim this study to optimize fMRI clinical usage by comparing effectiveness three tasks lateralization and localization a large group METHODS We analyzed data from sequential retrospective cohort 51 lesions who underwent mapping. compared (Antonym...
Unstructured data in Electronic Health Records (EHRs) often contains critical information -- complementary to imaging that could inform radiologists' diagnoses. But the large volume of notes associated with patients together time constraints renders manually identifying relevant evidence practically infeasible. In this work we propose and evaluate a zero-shot strategy for using LLMs as mechanism efficiently retrieve summarize unstructured patient EHR given query. Our method entails tasking...
<b>SUMMARY:</b> Unlike the more widely reported gradient-echo echo-planar perfusion-weighted imaging (EPI-PWI) technique, spin-echo (SE) EPI relative cerebral blood volume maps select for in microvessels <8 μm diameter. This first report of SE-EPI PWI distinguishing brain metastasis from high-grade glioma demonstrated 88% sensitivity and 72% specificity 83 patients. We discuss differences microvessel architecture between that may explain surprising success this application deserve further...