Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9890149 | PMC |
| http://dx.doi.org/10.3389/fonc.2023.1131639 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Equality and diversity in research: building an inclusive future.
BMC Res Notes
January 2025
Department of General Surgery, The Royal Marsden Hospital, London, UK.
Research progress and innovation are hindered by barriers, inequalities, and exclusions within academia. Embracing equality, diversity, and inclusion (EDI) is not only an ethical imperative but also essential for advancing knowledge and addressing global challenges. EDI principles ensure that researchers from all backgrounds have equitable opportunities to contribute to and benefit from research.
View Article and Find Full Text PDFEditorial Comment: Pediatric Whole-Body MRI-Current Challenges, Potential Opportunities, and Future Imperatives.
AJR Am J Roentgenol
January 2025
Boston Children's Hospital, Boston, Massachusetts.
Scientific dissemination in CSP: importance, advances, and challenges.
Cad Saude Publica
January 2025
Programa de Computação Científica, Fundação Oswaldo Cruz, Rio de Janeiro, Brasil.
New challenges ahead in scientific publishing.
An Acad Bras Cienc
January 2025
Universidade Federal do Rio de Janeiro, Museu Nacional, Laboratório de Sistemática e Tafonomia de Vertebrados Fósseis, Departamento de Geologia e Paleontologia, Quinta da Boa Vista, s/n, São Cristóvão, 20940-040 Rio de Janeiro, RJ, Brazil.
CXR-LLaVA: a multimodal large language model for interpreting chest X-ray images.
Eur Radiol
January 2025
Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
Objective: This study aimed to develop an open-source multimodal large language model (CXR-LLaVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists.
Materials And Methods: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by the LLaVA network.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!