Related references
Note: Only part of the references are listed.
Review
Radiology, Nuclear Medicine & Medical Imaging
Tom Boeken et al.
Summary: The emergence of affordable massively parallel computing devices has revolutionized AI research. The investment from web giants has also contributed to the development of high-quality software. The combination of faster computers, dedicated software libraries, and abundant data has increased flexibility in AI model design. Radiomics and AI are used in diagnostic imaging, and current evidence suggests that AI-assisted radiologists work better and faster. Interventional radiology, with its rich data and standardized format, has the potential to lead the development of AI-powered applications. This article provides an update on the status of radiomics and AI research and discusses their applications in interventional radiology.
DIAGNOSTIC AND INTERVENTIONAL IMAGING
(2023)
Review
Radiology, Nuclear Medicine & Medical Imaging
Maxime Barat et al.
Summary: In the field of adrenal imaging, artificial intelligence (AI) can be used for lesion detection, characterization, syndrome management, and patient follow-up. Although a perfect AI tool that covers all necessary steps from detection to analysis does not yet exist, multiple AI algorithms have been developed and tested with promising outcomes. However, AI in this setting is still in its early stages, and most published studies on AI in adrenal gland imaging provide preliminary results that have not yet found daily applications in clinical practice. This review presents recent developments and current results of AI in adrenal imaging and discusses the limitations and future perspectives of AI.
DIAGNOSTIC AND INTERVENTIONAL IMAGING
(2023)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Philippe Soyer et al.
CANADIAN ASSOCIATION OF RADIOLOGISTS JOURNAL-JOURNAL DE L ASSOCIATION CANADIENNE DES RADIOLOGISTES
(2023)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Steven P. Rowe et al.
DIAGNOSTIC AND INTERVENTIONAL IMAGING
(2022)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Philippe Soyer et al.
DIAGNOSTIC AND INTERVENTIONAL IMAGING
(2022)
Article
Medical Informatics
Jianfu Li et al.
Summary: This study fine-tuned pre-trained language models for named entity recognition (NER) tasks in clinical trial eligibility criteria text. The evaluation results showed that domain-specific transformer models performed better than general models, with PubMedBERT achieving the best performance. The study also explored the feasibility of data augmentation and found it to improve NER performance. These findings highlight the importance of contextual embeddings and the benefits of leveraging multiple data sources for the challenging NER task in clinical trial eligibility criteria text.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2022)
Article
Biochemical Research Methods
Renqian Luo et al.
Summary: This paper introduces a domain-specific generative Transformer language model BioGPT pre-trained on large-scale biomedical literature, which performs well on biomedical natural language processing tasks, especially achieving high accuracy in relation extraction tasks.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Health Care Sciences & Services
Diane M. Korngiebel et al.
Summary: Natural language computer applications are advancing rapidly and can now be deployed in healthcare settings that traditionally involve human-to-human interaction. However, careful consideration of the opportunities and pitfalls that come with using advanced Natural Language Processing applications in eHealth is necessary.
NPJ DIGITAL MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Maram Mahmoud A. Monshi et al.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2020)
Review
Radiology, Nuclear Medicine & Medical Imaging
Yasuyuki Kobayashi et al.
JAPANESE JOURNAL OF RADIOLOGY
(2019)
Review
Radiology, Nuclear Medicine & Medical Imaging
Ewoud Pons et al.
