A5005727853- Radiomics and Machine Learning in Medical Imaging
- Acute Ischemic Stroke Management
- RNA Research and Splicing
- 3D Printing in Biomedical Research
- Single-cell and spatial transcriptomics
- Venous Thromboembolism Diagnosis and Management
- Gene Regulatory Network Analysis
- MRI in cancer diagnosis
- Renal and related cancers
- Renal cell carcinoma treatment
- Bone Tumor Diagnosis and Treatments
- Lung Cancer Diagnosis and Treatment
- COVID-19 and healthcare impacts
- Medical Imaging and Analysis
- HIV/AIDS Research and Interventions
- Surgical Simulation and Training
- AI in cancer detection
- Mobile Health and mHealth Applications
- Augmented Reality Applications
- Occupational and environmental lung diseases
- Healthcare Policy and Management
- Cancer Cells and Metastasis
- Sarcoma Diagnosis and Treatment
- Epigenetics and DNA Methylation
- Radiology practices and education
Stanford University
2022-2024
Stanford Medicine
2020-2024
University of Pennsylvania
2018-2022
Palo Alto University
2020
University of California Davis Medical Center
2015
Shriners Hospitals for Children
2015
Abstract Purpose: With increasing incidence of renal mass, it is important to make a pretreatment differentiation between benign mass and malignant tumor. We aimed develop deep learning model that distinguishes tumors from cell carcinoma (RCC) by applying residual convolutional neural network (ResNet) on routine MR imaging. Experimental Design: Preoperative images (T2-weighted T1-postcontrast sequences) 1,162 lesions definitely diagnosed pathology or imaging in multicenter cohort were...
To develop a deep learning model to classify primary bone tumors from preoperative radiographs and compare performance with radiologists. A total of 1356 patients (2899 images) histologically confirmed pre-operative were identified five institutions' pathology databases. Manual cropping was performed by radiologists label the lesions. Binary discriminatory capacity (benign versus not-benign malignant not-malignant) three-way classification intermediate malignant) our evaluated. The...
Current guidelines for returning health care workers (HCW) to service after a positive SARS-CoV-2 RT-PCR test and ceasing of transmission precautions patients is based on two general strategies. A test-based strategy that requires negative respiratory tests obtained the resolution symptoms. Alternatively, due limited availability testing, many sites employ symptom-based recommends excluding HCW from workforce keeping contact until fixed period time has elapsed symptom recovery. The...
We previously validated Fibresolve, a machine learning classifier system that non-invasively predicts idiopathic pulmonary fibrosis (IPF) diagnosis. The incorporates an automated deep algorithm analyzes chest computed tomography (CT) imaging to assess for features associated with fibrosis. Here, we performance in assessment of patterns beyond those are characteristic usual interstitial pneumonia (UIP) pattern. was developed and using standard training, validation, test sets, clinical plus...
Background Pretreatment determination of renal cell carcinoma aggressiveness may help to guide clinical decision‐making. Purpose To evaluate the efficacy residual convolutional neural network using routine MRI in differentiating low‐grade (grade I–II) from high‐grade III–IV) stage I and II carcinoma. Study Type Retrospective. Population In all, 376 patients with 430 lesions 2008–2019 a multicenter cohort were acquired. The 353 Fuhrman‐graded carcinomas divided into training, validation, test...
Extensive cell-to-cell variation exists even among putatively identical cells, and there is great interest in understanding how the properties of transcription relate to this heterogeneity. Differential expression from two gene copies diploid cells could potentially contribute, yet our ability measure which copy individual RNAs originated remains limited, particularly context tissues. Here, we demonstrate quantitative, single molecule allele-specific RNA FISH adapted for use on tissue...
Abstract Head and neck surgeons often have difficulty in relocating sites of positive margins due to the complex 3‐dimensional (3D) anatomy head neck. We introduce a new technique where resection specimens are 3D scanned with smartphone, annotated computer‐assisted design software, immediately visualized on augmented reality (AR) glasses. The virtual specimen can be accurately superimposed onto surgical for orientation sizing applications. During an operative workshop, surgeon using AR...
Despite the routine use of electronic health record (EHR) data by radiologists to contextualize clinical history and inform image interpretation, majority deep learning architectures for medical imaging are unimodal, i.e., they only learn features from pixel-level information. Recent research revealing how race can be recovered pixel alone highlights potential serious biases in models which fail account demographics other key patient attributes. Yet lack datasets capture context, inclusive...
An electronic clinical decision support (CDS) alert can provide real-time provider to offer pre-exposure prophylaxis (PrEP) youth at risk for human immunodeficiency virus (HIV). The purpose of this study was evaluate utilization a PrEP CDS in large academic-community pediatric network and assess the association with prescribing rates.HIV test orders were altered patients 13 years older include hard-stop prompt asking if patient would benefit from PrEP. If providers answered "Yes" or "Not...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Abstract Organoids recapitulate complex 3D organ structures and represent a unique opportunity to probe the principles of self-organization. While we can alter an organoid’s morphology by manipulating culture conditions, organoid often resembles that its original organ, suggesting morphologies are governed set tissue-specific constraints. Here, establish framework identify constraints on morphological features quantifying them from microscopy images organoids exposed range perturbations. We...
Abstract Extensive cell-to-cell variation exists even among putatively identical cells, and there is great interest in understanding how the properties of transcription relate to this heterogeneity. Differential expression from two gene copies diploid cells could potentially contribute, yet our ability measure which copy individual RNAs originated remains limited, particularly context tissues. Here, we demonstrate quantitative, single molecule allele-specific RNA FISH adapted for use on...