A5061457064- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Advanced Radiotherapy Techniques
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- AI in cancer detection
- Lung Cancer Treatments and Mutations
- Advanced X-ray and CT Imaging
- Glioma Diagnosis and Treatment
- Sarcoma Diagnosis and Treatment
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Artificial Intelligence in Healthcare and Education
- Head and Neck Cancer Studies
- Advanced Neuroimaging Techniques and Applications
- Dysphagia Assessment and Management
- Prostate Cancer Diagnosis and Treatment
- Functional Brain Connectivity Studies
- Advanced Measurement and Metrology Techniques
- Breast Cancer Treatment Studies
- Mathematical Biology Tumor Growth
- Cleft Lip and Palate Research
- Effects of Radiation Exposure
- Respiratory and Cough-Related Research
- Cancer Genomics and Diagnostics
- Bone health and osteoporosis research
Memorial Sloan Kettering Cancer Center
2017-2025
University Hospital Carl Gustav Carus
2024
Helmholtz-Zentrum Dresden-Rossendorf
2024
Cardiff University
2024
TU Dresden
2024
National Center for Tumor Diseases
2024
University of Pennsylvania
2024
German Cancer Research Center
2024
University Hospitals Plymouth NHS Trust
2023
Purdue University West Lafayette
2019
Purpose Radiomics is a growing field of image quantitation, but it lacks stable and high‐quality software systems. We extended the capabilities Computational Environment for Radiological Research (CERR) to create comprehensive, open‐source, MATLAB‐based platform with an emphasis on reproducibility, speed, clinical integration radiomics research. Method The tools in CERR were designed specifically quantitate medical images combination CERR's core functionalities radiological data import,...
Glioblastoma (GBM) is the most common malignant central nervous system tumor, and MGMT promoter hypermethylation in this tumor has been shown to be associated with better prognosis. We evaluated capacity of radiomics features add complementary information status, improve ability predict prognosis.159 patients untreated GBM were included study divided into training independent test sets. 286 extracted from magnetic resonance images acquired prior any treatments. A least absolute shrinkage...
This work introduces a user-friendly, cloud-based software framework for conducting Artificial Intelligence (AI) analyses of medical images. The allows users to deploy AI-based workflows by customizing and hardware dependencies. components our include the Python-native Computational Environment Radiological Research (pyCERR) platform radiological image processing, Cancer Genomics Cloud (CGC) accessing resources user management utilities images from data repositories installing AI models...
Delineating swallowing and chewing structures aids in radiotherapy (RT) treatment planning to limit dysphagia, trismus, speech dysfunction. We aim develop an accurate efficient method automate this process.
Reducing trismus in radiotherapy for head and neck cancer (HNC) is important. Automated deep learning (DL) segmentation automated planning was used to introduce new rarely segmented masticatory structures study if risk could be decreased.Auto-segmentation based on purpose-built DL, our in-house system, ECHO. Treatment plans ten HNC patients, treated with 2 Gy × 35 fractions, were optimized (ECHO0). Six manually OARs replaced DL auto-segmentations the re-optimized (ECHO1). In a third set of...
Objective . To investigate if histogram analysis and visually assessed heterogeneity of diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) mapping can predict molecular subtypes invasive breast cancers. Materials Methods In this retrospective study, 91 patients carcinoma who underwent preoperative magnetic resonance (MRI) DWI at our institution were included. Two radiologists delineated a 2-D region interest (ROI) on ADC maps in consensus. Tumors also independently...
The use of stereotactic body radiation therapy for ultracentral lung tumors is limited by increased toxicity. We hypothesized that using published normal tissue complication probability (NTCP) and tumor control (TCP) models could improve the therapeutic ratio between A proposed model-based approach was applied to virtually replan early-stage non-small cell cancer (NSCLC) tumors.
Abstract Purpose Delineating the swallowing and chewing structures in Head Neck (H&N) CT scans is necessary for radiotherapy treatment (RT) planning to reduce incidence of radiation-induced dysphagia, trismus, speech dysfunction. Automating this process would decrease manual input required yield reproducible segmentations, but generating accurate segmentations challenging due complex morphology limited soft tissue contrast images. Methods We trained deep learning models using 194 H&N...
Abstract The emerging field of radiomics, which consists transforming standard-of-care images to quantifiable scalar statistics, endeavors reveal the information hidden in these macroscopic images. This research has found different applications ranging from phenotyping and tumor classification outcome prediction treatment planning. Texture analysis, often reducing spatial texture matrices summary features, been shown be important many latter applications. However, as pointed out studies,...
Purpose This work presents a framework for deployment of deep learning image segmentation models medical images across different operating systems and programming languages. Methods Computational Environment Radiological Research (CERR) platform was extended deploying learning-based to leverage CERR’s existing functionality radiological data import, transformation, management, visualization. The is compatible with MATLAB as well GNU Octave Python license-free use. Pre post processing...
Purpose: The goal of this study is to develop innovative methods for identifying radiomic features that are reproducible over varying image acquisition settings. Approach: We propose a regularized partial correlation network identify reliable and features. This approach was tested on two feature sets generated using different reconstruction computed tomography (CT) scans from cohort 47 lung cancer patients. largest common component between the networks phantom data consisting five samples....
An open-source library of implementations for deep-learning based image segmentation and outcomes models is presented in this work. As oncology treatment planning becomes increasingly driven by automation, such a model crucial to (i) validate existing on datasets collected at different institutions, (ii) automate segmentation, (iii) create ensembles improving performance (iv) incorporate validated the clinical workflow. The was developed with Computational Environment Radiological Research...
Abstract Purpose Recent advances in computational resources, including software libraries and hardware, have enabled the use of high-dimensional, multi-modal datasets to build Artificial Intelligence (AI) models workflows for radiation therapy image analysis. The purpose Software Toolbox RAdioTherapy Imaging analysiS (STRATIS) is provide cloud-enabled, easy-to-share train deploy AI transparency multi-institutional collaboration. Method STRATIS leverages open source medical informatics...
Background and Objectives: Radiotherapy prescriptions currently derive from population-wide guidelines established through large clinical trials. We provide an open-source software tool for patient-specific prescription determination using personalized dose-response curves. Methods: developed ROE, a plugin to the Computational Environment Research visualize predicted tumor control normal tissue complication simultaneously, as function of dose. ROE is made compatible with MATLAB, well Octave...