Methods: 3D biomodels were printed with flexible material (elastomer) using angiotomographic DICOM acquired images and compared to 3D digital subtraction angiography (DSA) images.
Results: 3D biomodels represented the aneurysm angioarchitecture exactly, especially the neck and domus features.
Conclusion: Elastomers 3D biomodels proved to be a trustworthy representation of the angiotomographic images and could be used to help surgical planning in IA treatment.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1590/0004-282X20160113 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Benchmarking the most popular XAI used for explaining clinical predictive models: Untrustworthy but could be useful.
Health Informatics J
December 2024
The University of Queensland, Brisbane, QLD, Australia.
Objective: This study aimed to assess the practicality and trustworthiness of explainable artificial intelligence (XAI) methods used for explaining clinical predictive models.
Methods: Two popular XAIs used for explaining clinical predictive models were evaluated based on their ability to generate domain-appropriate representations, impact clinical workflow, and consistency. Explanations were benchmarked against true clinical deterioration triggers recorded in the data system and agreement was quantified.
Supporting diversity in clinical trials: the equitable breakthroughs in medicine site maturity model.
Trials
November 2024
Global Health Leadership Initiative, Yale School of Public Health, 60 College Street, New Haven, CT, 06510, USA.
Background: Among the most powerful barriers to broader inclusion of diverse participants in clinical trials are social determinants of health, trustworthiness of health care providers and research institutions, and competing pressures on potential participants. Nevertheless, current tools to assess organizational capabilities for clinical trial diversity focus primarily on trial infrastructure, rely solely on quantitative self-reported data, and lack meaningful assessment of capabilities related to community engagement.
Methods: The Equitable Breakthroughs in Medicine (EQBMED) initiative developed a holistic, collaborative, site-driven formative model and accompanying assessment to catalog sites' current capabilities and identify opportunities for growth in both conducting industry-sponsored clinical trials and enriching diversity of those trials.
Persistence images, derived from topological data analysis, emerge as a powerful tool for visualizing and mitigating biases in radiological data interpretation and AI model development. This technique transforms complex topological features into stable, interpretable representations, offering unique insights into medical imaging data structure. By providing intuitive visualizations, persistence images enable the identification of subtle structural differences and potential biases in data acquisition, interpretation, and AI model training.
View Article and Find Full Text PDFAdversarial Examples on XAI-Enabled DT for Smart Healthcare Systems.
Sensors (Basel)
October 2024
Saudi Electronic University, Prince Muhammad Ibn Salman Rd., Ar Rabi, Ryiadh 11673, Saudi Arabia.
There have recently been rapid developments in smart healthcare systems, such as precision diagnosis, smart diet management, and drug discovery. These systems require the integration of the Internet of Things (IoT) for data acquisition, Digital Twins (DT) for data representation into a digital replica and Artificial Intelligence (AI) for decision-making. DT is a digital copy or replica of physical entities (e.
View Article and Find Full Text PDFBeyond the stereotypes: Artificial Intelligence image generation and diversity in anesthesiology.
Front Artif Intell
October 2024
Institute for Medical Education, University of Bern, Bern, Switzerland.
Article Synopsis
- This study investigates how AI-generated images represent the racial and ethnic diversity in the anesthesiology workforce and explores biases in these images.* -
- An analysis of 1,200 images from two AI models revealed a significant overrepresentation of White anesthesiologists and male gender, with younger professionals being underrepresented.* -
- The results indicate that AI models don't accurately reflect the actual diversity of the anesthesiology field, emphasizing the need for improved training datasets to reduce biases in AI-generated visuals.*
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!