A5018154366- Radiomics and Machine Learning in Medical Imaging
- Head and Neck Cancer Studies
- Artificial Intelligence in Healthcare and Education
- Lung Cancer Diagnosis and Treatment
- Advanced Radiotherapy Techniques
- AI in cancer detection
- Glioma Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Head and Neck Surgical Oncology
- Lung Cancer Treatments and Mutations
- Cancer Diagnosis and Treatment
- Brain Tumor Detection and Classification
- Colorectal and Anal Carcinomas
- Advanced X-ray and CT Imaging
- Medical Imaging and Analysis
- Salivary Gland Tumors Diagnosis and Treatment
- Machine Learning in Healthcare
- Advanced Neural Network Applications
- Brain Metastases and Treatment
- Health Systems, Economic Evaluations, Quality of Life
- Lung Cancer Research Studies
- Nutrition and Health in Aging
- Prostate Cancer Diagnosis and Treatment
- Radiation Therapy and Dosimetry
- Prostate Cancer Treatment and Research
Mass General Brigham
2022-2025
Harvard University
2008-2025
Boston Children's Hospital
2023-2025
Dana-Farber Cancer Institute
2019-2025
Brigham and Women's Hospital
2019-2025
Dana-Farber Brigham Cancer Center
2008-2024
Intel (United States)
2023-2024
Artificial Intelligence in Medicine (Canada)
2022
Yale University
2016-2021
Massachusetts General Hospital
2021
Abstract Data about the quality of cancer information that chatbots and other artificial intelligence systems provide are limited. Here, we evaluate accuracy on ChatGPT compared with National Cancer Institute’s (NCI’s) answers by using questions “Common Myths Misconceptions” web page. The NCI’s to each question were blinded, then evaluated for (accurate: yes vs no). Ratings independently question, between blinded NCI answers. Additionally, word count Flesch-Kincaid readability grade level...
Identification of nodal metastasis and tumor extranodal extension (ENE) is crucial for head neck cancer management, but currently only can be diagnosed via postoperative pathology. Pretreatment, radiographic identification ENE, in particular, has proven extremely difficult clinicians, would greatly influential guiding patient management. Here, we show that a deep learning convolutional neural network trained to identify ENE with excellent performance surpasses what human clinicians have...
Abstract Social determinants of health (SDoH) play a critical role in patient outcomes, yet their documentation is often missing or incomplete the structured data electronic records (EHRs). Large language models (LLMs) could enable high-throughput extraction SDoH from EHR to support research and clinical care. However, class imbalance limitations present challenges for this sparsely documented information. Here, we investigated optimal methods using LLMs extract six categories narrative text...
Purpose To develop and externally test a scan-to-prediction deep learning pipeline for noninvasive, MRI-based
Nanoparticle applications in medicine have seen a tremendous growth the past decade. In addition to their drug targeting application and ability improve bioavailability of drugs, nanoparticles can be designed allow detection with variety imaging methodologies. current study, we developed multimodal nanoparticle platform enable guided therapy, which was evaluated colon cancer mouse model. This "theranostic" is based on oil-in-water nanoemulsions carries iron oxide nanocrystals for MRI,...
Extranodal extension (ENE) is a well-established poor prognosticator and an indication for adjuvant treatment escalation in patients with head neck squamous cell carcinoma (HNSCC). Identification of ENE on pretreatment imaging represents diagnostic challenge that limits its clinical utility. We previously developed deep learning algorithm identifies computed tomography (CT) HNSCC. sought to validate our performance from diverse set institutions compare ability expert diagnosticians.We...
ABSTRACT The use of large language models (LLMs) such as ChatGPT for medical question-answering is becoming increasingly popular. However, there are concerns that these may generate and amplify misinformation. Because cancer patients frequently seek to educate themselves through online resources, some individuals will likely obtain treatment information. This study evaluated the performance robustness in providing breast, prostate, lung recommendations align with National Comprehensive...
Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing deploying personalized medicine targeted clinical trials. Recent advances ML have enabled the integration of wider ranges data including both medical records imaging (radiomics). However, development prognostic models is complex as no modeling strategy universally superior to others validation developed requires large diverse datasets demonstrate that (regardless method) from one dataset applicable...
Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging typically achieved through skeletal muscle index (SMI), which can be derived from cervical segmentation cross-sectional area. However, manual labor intensive, prone to interobserver variability, impractical for large-scale clinical use.To develop externally validate a fully automated image-based deep learning platform vertebral...
Background: Management of brain metastases typically includes radiotherapy (RT) with conventional fractionation and/or stereotactic radiosurgery (SRS). However, optimal indications and practice patterns for SRS remain unclear. We sought to evaluate national patients metastatic disease receiving RT. Methods: queried the National Cancer Data Base (NCDB) diagnosed non-small cell lung cancer, breast colorectal or melanoma from 2004 2014 who received upfront Patients were divided into non-SRS...
Although chemotherapy is used routinely in pediatric medulloblastoma (MB) patients, its benefit for adult MB unclear. We evaluated the survival impact of adjuvant MB. Using National Cancer Data Base, we identified patients aged 18 years and older who were diagnosed with 2004–2012 underwent surgical resection craniospinal irradiation (CSI). Patients divided into those received CSI (CRT) or alone (RT). Predictors CRT compared RT univariable multivariable logistic regression. Survival analysis...
Accurate risk-stratification can facilitate precision therapy in oropharyngeal squamous cell carcinoma (OPSCC). We explored the potential added value of baseline positron emission tomography (PET)/computed (CT) radiomic features for prognostication and risk stratification OPSCC beyond American Joint Committee on Cancer (AJCC) 8th edition staging scheme. Using institutional publicly available datasets, we included patients with known human papillomavirus (HPV) status, without distant...
Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning pediatric brain tumor segmentation model using stepwise transfer learning. Materials Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001 through December 2015) from national consortium (n = 184; median age, 7 years [range, 1-23 years]; 94 male patients) cancer center 100; 8 1-19 47 to develop neural networks for low-grade glioma approach maximize...
Postoperative radiotherapy to the craniospinal axis is standard-of-care for pediatric medulloblastoma but associated with long-term morbidity, particularly in young children. With advent of modern adjuvant chemotherapy strategies, postoperative deferral has gained acceptance children younger than 3 years, although it remains controversial older children.To analyze recent national treatment patterns and implications overall survival patients ages 8 years.Using National Cancer Data Base, years...
Pediatric tumors of the central nervous system are most common cause cancer-related death in children. The five-year survival rate for high-grade gliomas children is less than 20\%. Due to their rarity, diagnosis these entities often delayed, treatment mainly based on historic concepts, and clinical trials require multi-institutional collaborations. MICCAI Brain Tumor Segmentation (BraTS) Challenge a landmark community benchmark event with successful history 12 years resource creation...