A5026471196- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Digital Radiography and Breast Imaging
- Neurological disorders and treatments
- Artificial Intelligence in Healthcare and Education
- Advanced Neuroimaging Techniques and Applications
- Atomic and Subatomic Physics Research
- Parkinson's Disease Mechanisms and Treatments
- Brain Tumor Detection and Classification
- Advanced NMR Techniques and Applications
- Breast Cancer Treatment Studies
- Global Cancer Incidence and Screening
- Liver Disease Diagnosis and Treatment
- Medical Imaging and Analysis
- Breast Lesions and Carcinomas
- Ultrasound Imaging and Elastography
- Genetic Neurodegenerative Diseases
- Functional Brain Connectivity Studies
- Photoacoustic and Ultrasonic Imaging
- Global Energy and Sustainability Research
- Viral Infections and Immunology Research
- Hemoglobinopathies and Related Disorders
Memorial Sloan Kettering Cancer Center
2018-2024
Cornell University
2013-2024
New York Hospital Queens
2024
Hospital of the University of Pennsylvania
2024
NewYork–Presbyterian Hospital
2024
Kettering University
2022
Weill Cornell Medicine
2016-2021
John Radcliffe Hospital
2020
Wellcome Centre for Integrative Neuroimaging
2020
Council on Foreign Relations
2008
To assess quantitative susceptibility mapping (QSM) in the depiction of subthalamic nucleus (STN) by using 3-T magnetic resonance (MR) imaging.This study was HIPAA compliant and institutional review board approved. Ten healthy subjects (five men, five women; mean age, 24 years ± 3 [standard deviation]; age range, 21-33 years) eight patients with Parkinson disease three 57 14; 25-69 who were referred neurologists for preoperative navigation MR imaging prior to deep brain stimulator placement...
Purpose To assess the reproducibility of brain quantitative susceptibility mapping (QSM) in healthy subjects and patients with multiple sclerosis (MS) on 1.5 3T scanners from two vendors. Materials Methods Ten volunteers 10 were scanned twice a scanner one vendor. The also 1.5T same vendor second Similar imaging parameters used for all scans. QSM images reconstructed using recently developed nonlinear morphology‐enabled dipole inversion (MEDI) algorithm L1 regularization. Region‐of‐interest...
Deep neural networks have demonstrated promising performance in screening mammography with recent studies reporting at or above the level of trained radiologists on internal datasets. However, it remains unclear whether these models is robust and replicates across external In this study, we evaluate four state-of-the-art publicly available using datasets (CBIS-DDSM, INbreast, CMMD, OMI-DB). Where test data was available, published results were replicated. The best-performing model, which...
To demonstrate the phase and quantitative susceptibility mapping (QSM) patterns created by solid shell spatial distributions of magnetic in multiple sclerosis (MS) lesions.Numerical simulations experimental phantoms solid- shell-shaped sources were used to generate magnitude, phase, QSM images. Imaging 20 consecutive MS patients was also reviewed for this Institutional Review Board (IRB)-approved MRI study identify appearance lesions on images.Solid correctly reconstructed images, while...
Cancer patients often have a history of chemotherapy, putting them at increased risk liver toxicity and pancytopenia, leading to elevated fat iron respectively. T1-in-and-out-of-phase, the conventional MR technique for assessment, fails detect in presence concomitantly iron. IDEAL-IQ is more recently introduced quantification method that corrects multiple confounding factors, including This retrospective study was approved by institutional review board with waiver informed consent. We...
To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI.In this retrospective study, 38 229 examinations (composed 64 063 individual scans from 14 475 patients) were performed in female patients (age range, 12-94 years; mean age, 52 years ± 10 [standard deviation]) who presented between 2002 and 2014 single clinical site. A total 2555 selected had been segmented on two-dimensional (2D) images by radiologists, as well...
Background parenchymal enhancement (BPE) is assessed on breast MRI reports as mandated by the Breast Imaging Reporting and Data System (BI‐RADS) but prone to inter intrareader variation. Semiautomated fully automated BPE assessment tools have been developed none has surpassed radiologist designations. Purpose To develop a deep learning model for classification compare its performance with current standard‐of‐care radiology report Study Type Retrospective. Population Consecutive high‐risk...
To develop and evaluate an AI algorithm that detects breast cancer in MRI scans up to one year before radiologists typically identify it, potentially enhancing early detection high-risk women.
Abstract Objective To investigate the feasibility of using deep learning to identify tumor-containing axial slices on breast MRI images. Methods This IRB–approved retrospective study included consecutive patients with operable invasive cancer undergoing pretreatment between January 1, 2014, and December 31, 2017. Axial from first postcontrast phase were extracted. Each image was subdivided into two subimages: one ipsilateral cancer-containing contralateral healthy breast. Cases randomly...
The aim of the study is to develop and evaluate performance a deep learning (DL) model triage breast magnetic resonance imaging (MRI) findings in high-risk patients without missing any cancers.
Purpose To generate and assess an algorithm combining eye tracking speech recognition to extract brain lesion location labels automatically for deep learning (DL). Materials Methods In this retrospective study, 700 two-dimensional tumor MRI scans from the Brain Tumor Segmentation database were clinically interpreted. For each image, a single radiologist dictated standard phrase describing into microphone, simulating clinical interpretation. Eye-tracking data recorded simultaneously. Using...
Differential blood oxygenation between left (LV) and right ventricles (RV; ΔSaO
The aim of this study was to determine the range apparent diffusion coefficient (ADC) values for benign axillary lymph nodes in contrast malignant nodes, and define optimal ADC thresholds three different parameters (minimum, maximum, mean ADC) differentiating between nodes. This retrospective included consecutive patients who underwent breast MRI from January 2017-December 2020. Two-year follow-up imaging or histopathology served as reference standard node status. Area under receiver...
Quantitative susceptibility mapping (QSM) of human spinal vertebrae from a multi‐echo gradient‐echo (GRE) sequence is challenging, because comparable amounts fat and water in the make it difficult to solve nonconvex optimization problem fat‐water separation (R2*‐IDEAL) for estimating magnetic field induced by tissue susceptibility. We present an in‐phase (IP) echo initialization R2*‐IDEAL QSM vertebrae. Ten healthy subjects were recruited spine MRI. A 3D GRE was implemented acquire out‐phase...
Black patients with recently diagnosed breast cancer were less likely to undergo preoperative MRI and more have positive surgical margins when was not performed, in comparison White patients.