A5101785824- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Lung Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Cancer Genomics and Diagnostics
- Glioma Diagnosis and Treatment
- Digital Radiography and Breast Imaging
- Lung Cancer Treatments and Mutations
- Advanced MRI Techniques and Applications
- Genetic factors in colorectal cancer
- Radiation Dose and Imaging
- Esophageal Cancer Research and Treatment
- Axon Guidance and Neuronal Signaling
- Sinusitis and nasal conditions
- Brain Tumor Detection and Classification
- 3D Printing in Biomedical Research
- AI in cancer detection
- Radiation Therapy and Dosimetry
- Sarcoma Diagnosis and Treatment
- Pluripotent Stem Cells Research
- Ultrasound and Hyperthermia Applications
- Digital Imaging in Medicine
- Advanced X-ray Imaging Techniques
- Medical Imaging and Analysis
Janssen (United States)
2023-2024
Dana-Farber Brigham Cancer Center
2014-2018
Brigham and Women's Hospital
2014-2018
Harvard University
2008-2018
Dana-Farber Cancer Institute
2014-2018
Varian Medical Systems (United States)
2015
Harvard University Press
2011
University of British Columbia
2011
Massachusetts General Hospital
2008-2010
Abstract Purpose: Over the past few years, alkylating agent temozolomide has become standard-of-care therapy for patients with glioblastoma, most common brain tumor. Recently, large-scale cancer genome sequencing efforts have identified a hypermutation phenotype and inactivating MSH6 mismatch repair gene mutations in recurrent, post-temozolomide glioblastomas, particularly those growing more rapidly during treatment. This study aimed to clarify timing role of mediating glioblastoma...
PET-based radiomics have been used to noninvasively quantify the metabolic tumor phenotypes; however, little is known about relationship between these phenotypes and underlying somatic mutations. This study assessed association predictive power of <sup>18</sup>F-FDG PET–based radiomic features for mutations in non–small cell lung cancer patients. <b>Methods:</b> Three hundred forty-eight patients underwent diagnostic PET scans were tested genetic Thirteen percent (44/348) 28% (96/348) found...
Tumor phenotypes captured in computed tomography (CT) images can be described qualitatively and quantitatively using radiologist-defined "semantic" computer-derived "radiomic" features, respectively. While both types of features have shown to promising predictors prognosis, the association between these groups remains unclear. We investigated associations semantic radiomic CT 258 non-small cell lung adenocarcinomas. The tumor imaging were 9 qualitative that scored by radiologists, 57...
Glioblastoma multiforme (GBM), the most common primary brain tumor in adults, is invariably fatal despite current optimal multimodal therapy, with median survival (12-15 months) having barely improved since 1980s (1).The alkylating agent temozolomide (TMZ) part of standard care, extending by a few months compared radiation alone (2).The clinical benefits TMZ are associated epigenetic silencing O 6 -methylguanine-DNA-methyltransferase (MGMT) gene (3,4).Although inactivating pseudosubstrates...
Background PET-based texture features have been used to quantify tumor heterogeneity due their predictive power in treatment outcome. We investigated the sensitivity of motion by comparing static (3D) and respiratory-gated (4D) PET imaging. Methods Twenty-six patients (34 lesions) received 3D 4D [18F]FDG-PET scans before chemo-radiotherapy. The acquired data were retrospectively binned into five breathing phases create image sequence. Texture features, including Maximal correlation...
Purpose: Although change in SUV measures and PET-based textural features during treatment have shown promise tumor response prediction, it is unclear which quantitative measure the most predictive. We compared relationship between pathologic overall survival with esophageal cancer. Methods: Fifty-four cancer patients received PET/CT scans before after chemo-radiotherapy. Of these, 45 underwent surgery were classified into complete, partial, non-responders to preoperative chemoradiation....
Purpose Accurate segmentation of lung nodules is crucial in the development imaging biomarkers for predicting malignancy nodules. Manual time consuming and affected by inter-observer variability. We evaluated robustness accuracy a publically available semiautomatic algorithm that implemented 3D Slicer Chest Imaging Platform (CIP) compared it with performance manual segmentation. Methods CT images 354 manually segmented were downloaded from LIDC database. Four radiologists performed assessed...
Purpose: Although reduction of the cine electronic portal imaging device (EPID) acquisition frame rate through multiple averaging may reduce hardware memory burden and decrease image noise, it can hinder continuity soft-tissue motion leading to poor autotracking results. The impact blurring noise on tracking performance was investigated. Methods: Phantom patient images were acquired at a 12.87 Hz with an amorphous silicon imager (AS1000, Varian Medical Systems, Palo Alto, CA). maximum is...
To study the variability in volume change estimates of pulmonary nodules due to segmentation approaches used across several algorithms and evaluate these effects on ability predict nodule malignancy.We obtained 100 patient image datasets from National Lung Screening Trial (NLST) that had a detected each two consecutive low dose computed tomography (LDCT) scans, with an equal proportion malignant benign cases (50 malignant, 50 benign). Information about location for was provided by screen...
Beam's-eye-view (BEV) imaging with an electronic portal device (EPID) can be performed during lung stereotactic body radiation therapy (SBRT) to monitor the tumor location in real-time. Image quality for each patient and treatment field depends on several factors including anatomy gantry couch angles. The authors investigated angular dependence of automatic localization non-coplanar SBRT delivery.All images were acquired at a frame rate 12 Hz amorphous silicon EPID. A previously validated...
Purpose We hypothesized that combining multiple amorphous silicon flat panel layers increases photon detection efficiency in an electronic portal imaging device ( EPID ), improving image quality and tracking accuracy of low‐contrast targets during radiotherapy. Methods The prototype imager evaluated this study contained four individually programmable each with a copper converter layer, Gd 2 O S scintillator, active‐matrix AMFPI ). was placed on Varian TrueBeam linac Las Vegas phantom...
Accurate deformable registration is essential for voxel-based comparison of sequential positron emission tomography (PET) images proper adaptation treatment plan and response assessment. The may be sensitive to the method as optimal algorithm unknown. This study investigated impact choice on therapy evaluation.Sixteen patients with 20 lung tumors underwent a pre- post-treatment computed (CT) 4D FDG-PET scans before after chemoradiotherapy. All CT were coregistered using rigid ten algorithms....
A new portal imager consisting of four vertically stacked conventional electronic imaging device (EPID) layers has been constructed in pursuit improved detective quantum efficiency (DQE).We hypothesize that super-resolution (SR) can also be achieved such a system by shifting each layer laterally half pixel relative to the above.Super-resolution will improve resolution and contrast-to-noise ratio (CNR) megavoltage (MV) planar cone beam computed tomography (MV-CBCT) applications.Simulations...
Purpose: We hypothesize that an electronic portal imaging device (EPID) consisting of multiple layers, each containing a scintillator coupled to amorphous silicon flat panel imager (AMFPI), increases photon detection efficiency, improving image quality and tracking accuracy low contrast targets during radiotherapy. Methods: The prototype 4‐layer evaluated in this study contained four individually programmable layers with copper‐Gd₂O₂S AMFPI complete set readout electronics. was placed on...
Purpose: Although reduction of the cine EPID acquisition frame rate through multiple averaging may reduce hardware memory burden and decrease image noise, it can hinder continuity soft‐tissue motion leading to poor auto‐tracking results. The impact blurring noise on tracking performance was investigated. Methods: Phantom patient images were acquired at a 12.87Hz an AS1000 portal imager. Low obtained by continuous averaging. A previously validated algorithm employed for auto‐tracking....
Purpose: Early prediction of distant metastasis may provide crucial information for adaptive therapy, subsequently improving patient survival. Radiomic features that extracted from PET and CT images have been used assessing tumor phenotype predicting clinical outcomes. This study investigates the values radiomic in (DM) non‐small cell lung cancer (NSCLC). Methods: A total 108 patients with stage II–III adenocarcinoma were included this retrospective study. Twenty selected (10 10 PET)....
Purpose: Beams‐eye‐view imaging applications such as real‐time soft‐tissue motion estimation are hindered by the inherently low image contrast of electronic portal devices (EPID) currently in clinical use. We introduce and characterize a novel EPID that provides substantially increased detective quantum efficiency (DQE), contrast‐to‐noise ratio (CNR) dynamic range without degradation spatial resolution. Methods: The prototype design features stack four conventional layers combined with noise...