A5027357396- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Digital Radiography and Breast Imaging
- AI in cancer detection
- COVID-19 diagnosis using AI
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare and Education
- Medical Image Segmentation Techniques
- Biomedical Text Mining and Ontologies
- Topic Modeling
- Domain Adaptation and Few-Shot Learning
- Online Learning and Analytics
- Radiopharmaceutical Chemistry and Applications
- Advanced Neural Network Applications
- Artificial Intelligence in Healthcare
- Genetics, Bioinformatics, and Biomedical Research
- Medical Imaging Techniques and Applications
- Prostate Cancer Treatment and Research
Computer Algorithms for Medicine
2022
The aim of this study was to systematically evaluate the effect thresholding algorithms used in computer vision for quantification prostate-specific membrane antigen positron emission tomography (PET) derived tumor volume (PSMA-TV) patients with advanced prostate cancer. results were validated respect prognostication overall survival advanced-stage
Abstract Objectives Over the course of their treatment, patients often switch hospitals, requiring staff at new hospital to import external imaging studies local database. In this study, authors present MOdality Mapping and Orchestration (MOMO), a Deep Learning–based approach automate mapping process by combining metadata analysis neural network ensemble. Methods A set 11,934 series with existing anatomical labels was retrieved from PACS database train an ensemble networks (DenseNet-161...
Prior to the deep learning era, shape was commonly used describe objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models used. This is seen numerous shape-related publications premier vision conferences as well growing popularity of ShapeNet (about 51,300 models) Princeton ModelNet (127,915 models). For domain, we present a large collection anatomical shapes...
Given the rapidly expanding capabilities of generative AI models for radiology, there is a need robust metrics that can accurately measure quality AI-generated radiology reports across diverse hospitals. We develop ReXamine-Global, LLM-powered, multi-site framework tests different writing styles and patient populations, exposing gaps in their generalization. First, our method whether metric undesirably sensitive to reporting style, providing scores depending on are stylistically similar...
It is an open secret that ImageNet treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit pretraining data domain downstream task should almost always be preferred instead. leverage RadNet-12M, a dataset containing more than 12 million computed tomography (CT) image slices, to explore efficacy self-supervised and natural images. Our experiments cover intra- cross-domain...
Patients regularly continue assessment or treatment in other facilities than they began them in, receiving their previous imaging studies as a CD-ROM and requiring clinical staff at the new hospital to import these into local database. However, between different facilities, standards for nomenclature, contents, even medical procedures may vary, often human intervention accurately classify received context of recipient hospital's standards. In this study, authors present MOMO (MOdality...