A5066782057- Radiology practices and education
- Diversity and Career in Medicine
- Radiation Dose and Imaging
- Prostate Cancer Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Treatment and Research
- Healthcare Policy and Management
- Innovations in Medical Education
- Advances in Oncology and Radiotherapy
- Advanced X-ray and CT Imaging
- Frailty in Older Adults
- Abdominal Trauma and Injuries
- Global Health Workforce Issues
- Colorectal Cancer Treatments and Studies
- Body Composition Measurement Techniques
- COVID-19 and healthcare impacts
- Nutrition and Health in Aging
- Topic Modeling
- Pelvic and Acetabular Injuries
- AI in cancer detection
- Medical Imaging and Analysis
- Healthcare Systems and Challenges
- History of Medical Practice
- Genetic factors in colorectal cancer
Duke University
2022-2025
Duke University Hospital
2021-2025
Brigham and Women's Hospital
2018-2024
Harvard University
2019-2024
St. Michael's Hospital
2024
University of Toronto
2024
Jackson Laboratory
2024
American College of Radiology
2024
Society of Abdominal Radiology
2024
Radiological Society of North America
2024
Background Although CT-based body composition (BC) metrics may inform disease risk and outcomes, obtaining these has been too resource intensive for large-scale use. Thus, population-wide distributions of BC remain uncertain. Purpose To demonstrate the validity fully automated, deep learning analysis from abdominal CT examinations, to define demographically adjusted reference curves, illustrate advantage use curves compared with standard methods, along their biologic significance in...
“Just Accepted” papers have undergone full peer review and been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, proof before it is published its final version. Please note that during production of the copyedited article, errors may be discovered which could affect content. Purpose To develop evaluate an automated system extracting structured clinical information from unstructured radiology pathology reports using open-weights...
Childbearing and Family Leave Policies
Body composition on chest CT scans encompasses a set of important imaging biomarkers. This study developed and validated fully automated analysis pipeline for multi-vertebral level assessment muscle adipose tissue routine scans. retrospectively trained two convolutional neural networks 629 from patients (55% women; mean age, 67 years ± 10 [standard deviation]) obtained between 2014 2017 prior to lobectomy primary lung cancer at three institutions. A slice-selection network was identify an...
KRAS, BRAF, and PI3KCA are the most frequently mutated oncogenes in human colon cancer. To explore their effects on morphogenesis, we used cancer–derived cell line Caco-2. When seeded extracellular matrix, individual cells proliferate generate hollow, polarized cysts. The expression of oncogenic phosphatidylinositol 3-kinase (PI3KCA H1047R) Caco-2 has no effect, but K-Ras V12 or B-Raf V600E disrupts polarity tight junctions promotes hyperproliferation, resulting large, filled structures....
Parenting issues can affect physicians' choice of specialty or subspecialty, as well their selection individual training programs, because the distinctive challenges facing residents and fellows with children. Specific information about how perceive these is limited.
Artificial intelligence and machine learning (AI-ML) have taken center stage in medical imaging. To develop as leaders AI-ML, radiology residents may seek a formative data science experience. The authors piloted an elective Data Science Pathway (DSP) for 4th-year at the authors' institution collaboration with MGH & BWH Center Clinical (CCDS). goal of DSP was to provide introduction AI-ML through flexible schedule educational, experiential, research activities. study describes initial...
The RSNA Abdominal Traumatic Injury CT (ie, RATIC) dataset contains 4274 abdominal studies with annotations related to traumatic injuries and is available at https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection https://imaging.rsna.org/dataset/5 .
Artificial intelligence (AI) tools are rapidly being developed for radiology and other clinical areas. These have the potential to dramatically change practice; however, these be usable function as intended, they must integrated into existing systems. In a collaborative effort between Radiological Society of North America, radiologists, imaging-focused vendors, Imaging AI in Practice (IAIP) demonstrations were show how can generate, consume, present results throughout workflow simulated...
BACKGROUND. CT-based body composition (BC) measurements have historically been too resource intensive to analyze for widespread use and lacked robust comparison with traditional weight metrics predicting cardiovascular risk. OBJECTIVE. The aim of this study was determine whether BC obtained from routine CT scans by a fully automated deep learning algorithm could predict subsequent events independently weight, BMI, additional risk factors. METHODS. This retrospective included 9752 outpatients...
Early prostate cancer detection and staging from MRI is extremely challenging for both radiologists deep learning algorithms, but the potential to learn large diverse datasets remains a promising avenue increase their performance within across institutions. To enable this prototype-stage where majority of existing research remains, we introduce flexible federated framework cross-site training, validation, evaluation custom algorithms.
This study assesses how member boards of the American Board Medical Specialties (ABMS) have adhered to a 2021 ABMS policy change allowing residents minimum 6 weeks parental, caregiver, and medical leave.
Abstract With vast interest in machine learning applications, more investigators are proposing to assemble large datasets for applications. We aim delineate multiple possible roadblocks exam retrieval that may present themselves and lead significant time delays. This HIPAA-compliant, institutional review board–approved, retrospective clinical study required identification of all outpatient emergency patients undergoing abdominal pelvic computed tomography (CT) at three affiliated hospitals...
The 2023 RSNA Abdominal Trauma Detection AI Challenge led to the development of innovative machine learning models with high performance in detection traumatic abdominal injuries on CT scans.
The American College of Radiology (ACR) passed a historic paid family/medical leave (PFML) resolution at its April 2022 meeting, resolving that "diagnostic radiology, interventional radiation oncology, medical physics, and nuclear medicine practices, departments training programs strive to provide 12 weeks in 12-month period for attending physicians, physicists, members as needed." purpose this article is share policy beyond radiology so it may serve call action other specialties. Such PFML...
Abstract Purpose To subjectively and quantitatively compare the quality of 3 Tesla magnetic resonance imaging prostate acquired with a novel flexible surface coil (FSC) conventional endorectal (ERC). Methods Six radiologists independently reviewed 200 pairs axial, high-resolution T2-weighted diffusion-weighted image data sets, each containing one examination FSC ERC, respectively. Readers selected their preferred from pair assessed every single using six criteria on 4-point scales....
Non-invasive prostate cancer classification from MRI has the potential to revolutionize patient care by providing early detection of clinically significant disease, but thus far shown limited positive predictive value. To address this, we present a image-based deep learning method predict screening in patients that subsequently underwent biopsy with results ranging benign pathology highest grade tumors. Specifically, demonstrate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...