A5009955603- Radiomics and Machine Learning in Medical Imaging
- Statistical Methods in Clinical Trials
- Medical Imaging Techniques and Applications
- Cancer Genomics and Diagnostics
- MRI in cancer diagnosis
- AI in cancer detection
- Health Systems, Economic Evaluations, Quality of Life
- Prostate Cancer Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- Lung Cancer Treatments and Mutations
- Cancer-related molecular mechanisms research
- Ovarian cancer diagnosis and treatment
- Pancreatic and Hepatic Oncology Research
- Advanced Radiotherapy Techniques
- Gastric Cancer Management and Outcomes
- Colorectal Cancer Treatments and Studies
- Hepatocellular Carcinoma Treatment and Prognosis
- Meta-analysis and systematic reviews
- Artificial Intelligence in Healthcare and Education
- Cancer-related Molecular Pathways
- Renal cell carcinoma treatment
- Advanced Breast Cancer Therapies
- Lymphoma Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Colorectal Cancer Screening and Detection
Zimmer Biomet (United States)
2025
National Institutes of Health
2010-2024
National Cancer Institute
2014-2024
Nvidia (United States)
2024
Singapore General Hospital
2024
Leidos (United States)
2024
Frederick National Laboratory for Cancer Research
2024
Cancer Institute (WIA)
2017
University of Miami
2015
Purpose To investigate relationships between computer-extracted breast magnetic resonance (MR) imaging phenotypes with multigene assays of MammaPrint, Oncotype DX, and PAM50 to assess the role radiomics in evaluating risk cancer recurrence. Materials Methods Analysis was conducted on an institutional review board-approved retrospective data set 84 deidentified, multi-institutional MR examinations from National Cancer Institute Imaging Archive, along clinical, histopathologic, genomic The...
Although investigators in the imaging community have been active developing and evaluating quantitative biomarkers (QIBs), development implementation of QIBs hampered by inconsistent or incorrect use terminology methods for technical performance statistical concepts. Technical is an assessment how a test performs reference objects subjects under controlled conditions. In this article, some relevant concepts are reviewed, that can be used comparing described, issues related to discussed. More...
Using quantitative radiomics, we demonstrate that computer-extracted magnetic resonance (MR) image-based tumor phenotypes can be predictive of the molecular classification invasive breast cancers. Radiomics analysis was performed on 91 MRIs biopsy-proven cancers from National Cancer Institute's multi-institutional TCGA/TCIA. Immunohistochemistry including estrogen receptor, progesterone human epidermal growth factor receptor 2, and for 84 cases, subtype (normal-like, luminal A, B,...
BACKGROUND The objective of this study was to demonstrate that computer‐extracted image phenotypes (CEIPs) biopsy‐proven breast cancer on magnetic resonance imaging (MRI) can accurately predict pathologic stage. METHODS authors used a data set deidentified MRIs organized by the National Cancer Institute in Imaging Archive. In total, 91 cancers were analyzed from patients who had information available stage (stage I, n = 22; II, 58; III, 11) and surgically verified lymph node status (negative...
The mode of action targeted cancer agents (TCAs) differs from classic chemotherapy, which leads to concerns about the role RECIST in evaluating tumor response trials with TCAs. We investigated performance using a pooled database 50 clinical at least one TCA.We examined impact number target lesions (TLs) on within-patient variability response. prognostic effect TL (at 12 weeks or study basis maximum five TLs) survival was studied through landmark and time-dependent Cox models adjusted for...
Purpose To evaluate interradiologist agreement on assessments of computed tomography (CT) imaging features high-grade serous ovarian cancer (HGSOC), to assess their associations with time-to-disease progression (TTP) and HGSOC transcriptomic profiles (Classification Ovarian Cancer [CLOVAR]), develop an imaging-based risk score system predict TTP CLOVAR profiles. Materials Methods This study was a multireader, multi-institutional, institutional review board-approved, HIPAA-compliant...
Abstract Objectives To investigate the association between CT imaging traits and texture metrics with proteomic data in patients high-grade serous ovarian cancer (HGSOC). Methods This retrospective, hypothesis-generating study included 20 HGSOC prior to primary cytoreductive surgery. Two readers independently assessed contrast-enhanced computed tomography (CT) images extracted 33 traits, a third reader adjudicating event of disagreement. In addition, all sites suspected were manually...
In this study, we sought to investigate if computer-extracted magnetic resonance imaging (MRI) phenotypes of breast cancer could replicate human-extracted size and Breast Imaging-Reporting Data System (BI-RADS) using MRI data from The Cancer Genome Atlas (TCGA) project the National Institute.Our retrospective interpretation study involved analysis Health Insurance Portability Accountability Act-compliant Imaging Archive, an open-source database TCGA project. This was exempt institutional...
Develop an integrated intra-site and inter-site radiomics-clinical-genomic marker of high grade serous ovarian cancer (HGSOC) outcomes explore the biological basis radiomics with respect to molecular signaling pathways tumor microenvironment (TME).
NCT03253744 was a phase 1 trial to identify the maximum tolerated dose (MTD) of image-guided, focal, salvage stereotactic body radiation therapy (SBRT) for patients with locally radiorecurrent prostate cancer. Additional objectives included biochemical control and imaging response.
Purpose To evaluate the performance of an artificial intelligence (AI) model in detecting overall and clinically significant prostate cancer (csPCa)-positive lesions on paired external in-house biparametric MRI (bpMRI) scans assess differences between each dataset. Materials Methods This single-center retrospective study included patients who underwent at institution were rescanned authors' May 2015 2022. A genitourinary radiologist performed prospective readouts following Prostate Imaging...
Objectives To develop and validate a Prostate Imaging‐Reporting Data System (PI‐RADS) version 2.1 (v2.1)‐based predictive model for diagnosis of clinically significant prostate cancer (csPCa), integrating clinical multiparametric magnetic resonance imaging (mpMRI) data, compare its performance with existing models. Patients Methods We retrospectively analysed data from patients who underwent prospective mpMRI assessment using the PI‐RADS v2.1 scoring system biopsy at our institution between...