A5046346564- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Breast Cancer Treatment Studies
- Advanced Neuroimaging Techniques and Applications
- Esophageal Cancer Research and Treatment
- NMR spectroscopy and applications
- Advanced X-ray Imaging Techniques
- Advanced NMR Techniques and Applications
- Atomic and Subatomic Physics Research
- AI in cancer detection
- Nuclear Physics and Applications
- Brain Metastases and Treatment
- Lanthanide and Transition Metal Complexes
- Brain Tumor Detection and Classification
- Breast Lesions and Carcinomas
- Advanced Radiotherapy Techniques
- Structural Health Monitoring Techniques
- Health, Environment, Cognitive Aging
- Lung Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Bioinformatics and Genomic Networks
- Gastric Cancer Management and Outcomes
- Radiology practices and education
The University of Texas MD Anderson Cancer Center
2016-2025
Society of Interventional Radiology
2020
Texas A&M University
2005-2008
Background Brain metastases are manually identified during stereotactic radiosurgery (SRS) treatment planning, which is time consuming and potentially challenging. Purpose To develop investigate deep learning (DL) methods for detecting brain metastasis with MRI to aid in planning SRS. Materials Methods In this retrospective study, contrast material–enhanced three-dimensional T1-weighted gradient-echo scans from patients who underwent gamma knife SRS January 2011 August 2018 were analyzed....
Triple-negative breast cancer (TNBC) is persistently refractory to therapy, and methods improve targeting evaluation of responses therapy in this disease are needed. Here, we integrate quantitative MRI data with biologically based mathematical modeling accurately predict the response TNBC neoadjuvant systemic (NAST) on an individual basis. Specifically, 56 patients enrolled ARTEMIS trial (NCT02276443) underwent standard-of-care doxorubicin/cyclophosphamide (A/C) then paclitaxel for NAST,...
Abstract Triple-negative breast cancer (TNBC) is an aggressive subtype of cancer. Neoadjuvant systemic therapy (NAST) followed by surgery are currently standard care for TNBC with 50-60% patients achieving pathologic complete response (pCR). We investigated ability deep learning (DL) on dynamic contrast enhanced (DCE) MRI and diffusion weighted imaging acquired early during NAST to predict patients’ pCR status in the breast. During development phase using images 130 patients, DL model...
Purpose: To develop deep learning models for predicting the pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in patients with triple-negative breast cancer (TNBC) based on pretreatment multiparametric MRI and clinicopathological data. Methods: The prospective institutional review board-approved study [NCT02276443] included 282 stage I–III TNBC who had at baseline underwent NAST surgery during 2016–2021. Dynamic contrast-enhanced (DCE), diffusion-weighted imaging...
We developed a practical framework to construct digital twins for predicting and optimizing triple-negative breast cancer (TNBC) response neoadjuvant chemotherapy (NAC). This study employed 105 TNBC patients from the ARTEMIS trial (NCT02276443, registered on 10/21/2014) who received Adriamycin/Cytoxan (A/C)-Taxol (T). Digital were established by calibrating biology-based mathematical model patient-specific MRI data, which accurately predicted pathological complete (pCR) with an AUC of 0.82....
Early assessment of neoadjuvant systemic therapy (NAST) response for triple-negative breast cancer (TNBC) is critical patient care in order to avoid the unnecessary toxicity an ineffective treatment. We assessed functional tumor volumes (FTVs) from dynamic contrast-enhanced (DCE) MRI after 2 cycles (C2) and 4 (C4) NAST as predictors TNBC. A group 100 patients with stage I-III TNBC who underwent DCE at baseline, C2, C4 were included this study. Tumors segmented on images 1 min 2.5...
Purpose To determine if a radiomics model based on quantitative maps acquired with synthetic MRI (SyMRI) is useful for predicting neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC). Materials and Methods In this prospective study, 181 women diagnosed stage I–III TNBC were scanned SyMRI sequence at baseline midtreatment (after four cycles of NAST), producing T1, T2, proton density (PD) maps. Histopathologic analysis surgery was used to pathologic complete...
Abstract Partial parallel imaging (PPI) techniques using array coils and multichannel receivers have become an effective approach to achieving fast magnetic resonance (MRI). This article presents a Matlab toolbox called PULSAR (Parallel Utilizing Localized Surface‐coil Acquisition Reconstruction) that can simulate the data acquisition image reconstruction, analyze performance of five common PPI techniques. sensitivity functions rectangular loop quasi‐static model based on Biot‐Savart's Law...
Abstract Purpose To develop a fast T1‐weighted, fat‐suppressed three‐dimensional dual echo Dixon technique and to demonstrate its use in contrast agent enhanced MRI. Materials Methods A product gradient pulse sequence was modified acquire echoes after each RF excitation with water fat signals in‐phase (IP) opposed‐phase (OP), respectively. An on‐line reconstruction algorithm implemented automatically generate separate images. The signal noise ratio (SNR) of the new compared that phantom. In...
Background Assessment of treatment response in triple‐negative breast cancer (TNBC) may guide individualized care for improved patient outcomes. Diffusion tensor imaging (DTI) measures tissue anisotropy and could be useful characterizing changes the tumors adjacent fibroglandular (FGT) TNBC patients undergoing neoadjuvant systemic (NAST). Purpose To evaluate potential DTI parameters prediction NAST. Study Type Prospective. Population Eighty‐six women (average age: 51 ± 11 years) with...
Abstract Previously published fast spin‐echo (FSE) implementations of a Dixon method for water and fat separation all require multiple scans thus relatively long scan time. Further, the minimum echo spacing (esp), time critical FSE image quality efficiency, often needs to be increased in order bring about required phase shift between signals. This work proposes implements novel triple‐echo (fTED) technique that can address these limitations. In new technique, three raw images are acquired...
The purpose of this study was to assess the feasibility a short protocol for screening breast MRI that is noninferior standard-of-care (SOC) in image quality complies with American College Radiology accreditation requirements.In prospective trial, 23 women at high risk underwent both an initial SOC examination included axial iterative decomposition water and fat echo asymmetry least-squares estimation (IDEAL) T1-weighted volume imaging assessment (VIBRANT) dynamic contrast-enhanced sequences...
Background Dynamic contrast‐enhanced (DCE) MRI is useful for diagnosis and assessment of treatment response in breast cancer. Fast DCE offers a higher sampling rate contrast enhancement curves comparison to conventional MRI, potentially characterizing tumor perfusion kinetics more accurately measurement functional volume (FTV) as predictor response. Purpose To investigate FTV by fast neoadjuvant systemic therapy (NAST) triple‐negative cancer (TNBC). Study Type Prospective....
Abstract Purpose To compare image quality and clinical utility of a T2‐weighted (T2W) 3‐dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional for rectal magnetic resonance imaging (MRI). Methods The study included 50 patients with cancer who underwent MRI consecutively between July 7, 2020 January 20, 2021 T2W 3D FSE DLR reconstruction. Three radiologists reviewed the two sets images, scoring overall SNR, motion artifacts, on 3‐point...
Purpose To determine if amide proton transfer–weighted chemical exchange saturation transfer (APTW CEST) MRI is useful in the early assessment of treatment response persons with triple-negative breast cancer (TNBC). Materials and Methods In this prospective study, a total 51 participants (mean age, years [range, 26–79 years]) TNBC were included who underwent APTW CEST 0.9- 2.0-µT power performed at baseline, after two cycles (C2), four (C4) neoadjuvant systemic therapy (NAST). Imaging was...
Diffusion-weighted imaging (DWI) has become a useful tool in the detection, characterization, and evaluation of response to treatment many cancers, including malignant liver lesions. DWI offers higher image contrast between lesions normal tissue than other sequences. images acquired at two or more b-values can be used derive an apparent diffusion coefficient (ADC). body several technical challenges. This include ghosting artifacts, mis-registration susceptibility artifacts. New sequences...
Early prediction of neoadjuvant systemic therapy (NAST) response for triple-negative breast cancer (TNBC) patients could help oncologists select individualized treatment and avoid toxic effects associated with ineffective in unlikely to achieve pathologic complete (pCR). The objective this study is evaluate the performance radiomic features peritumoral tumoral regions from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) acquired at different time points NAST early TNBC. This...
Abstract Triple-negative breast cancer (TNBC) is often treated with neoadjuvant systemic therapy (NAST). We investigated if radiomic models based on multiparametric Magnetic Resonance Imaging (MRI) obtained early during NAST predict pathologic complete response (pCR). included 163 patients stage I-III TNBC MRI at baseline and after 2 (C2) 4 cycles of NAST. Seventy-eight (48%) had pCR, 85 (52%) non-pCR. Thirty-six multivariate combining features from dynamic contrast-enhanced...
Purpose To combine deep learning and biology-based modeling to predict the response of locally advanced, triple negative breast cancer before initiating neoadjuvant chemotherapy (NAC). Materials Methods In this retrospective study, a mathematical model tumor NAC was constructed calibrated on patient-specific basis using imaging data from patients enrolled in MD Anderson ARTEMIS trial (ClinicalTrials.gov, NCT02276443) between April 2018 May 2021. relate parameters pretreatment MRI data,...
To develop an improved region-growing algorithm for phase correction in MRI.Phase MRI can sometimes be formulated as selecting a vector each pixel of image from two candidate vectors so that the orientation output is spatially smooth. Existing algorithms may run into difficulty presence high noise, artifacts, or isolated objects. In this study, we developed to include following novel and salient features: 1) automated quality guidance determining sequence region growing, 2) joint...