EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Artificial intelligence-powered personalized patient dosimetry in CT

John Damilakis iD

BJR|Artificial Intelligence · 2025

DOI: 10.1093/bjrai/ubaf007 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift BJR|Artificial Intelligence, 2025. Verfasst von John Damilakis. Beteiligte Einrichtung: Department of Medical Physics, School of Medicine, University of Crete, 71003 Iraklion, Crete, Greece. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advanced X-ray imaging techniques have increased the importance of patient dosimetry, requiring better dose assessment methods and improved dose management strategies to optimize imaging protocols, resulting in diagnostic information obtained with the lowest possible dose to the patient. This review explores the potential of artificial intelligence (AI) in CT dosimetry. Using machine learning models, trained with extensive data from personalized Monte Carlo dosimetry, AI significantly enhances the dosimetry process by providing accurate, rapid dose assessments. It automates organ segmentation from CT images, a critical and traditionally time-consuming step, enabling precise estimation of organ doses. AI’s ability to predict dose distributions with high accuracy facilitates the seamless integration of personalized dosimetry into clinical workflows, promising improved patient safety and optimized radiation dose management. Additionally, AI-driven approaches offer substantial advancements over conventional methodologies, which often face challenges such as prolonged computation times and labour-intensive manual processes. Despite these advancements, challenges hinder the widespread adoption of AI in CT dosimetry. These include potential biases in training data and the need for robust validation to ensure accuracy across diverse patient populations and imaging conditions. Addressing these challenges is essential for realizing the full potential of AI-powered dosimetry in clinical practice.

Schlagwörter

Stichwörter der Autor:innen

X-ray imagingartificial intelligenceconvolutional neural networksdeep learningdeep neural networksdosimetrymachine learningradiation

Autor:innen und Institutionen

  • Department of Medical Physics, School of Medicine, University of Crete, 71003 Iraklion, Crete, Greece.

ORCID-Profile: John Damilakis

Zitieren

APA

Damilakis, J. (2025). Artificial intelligence-powered personalized patient dosimetry in CT. BJR|Artificial Intelligence. https://doi.org/10.1093/bjrai/ubaf007

Vancouver

Damilakis J. Artificial intelligence-powered personalized patient dosimetry in CT. BJR|Artificial Intelligence. 2025. doi:10.1093/bjrai/ubaf007

BibTeX
@article{Damilakis2025,
  author = {Damilakis, John},
  title = {Artificial intelligence-powered personalized patient dosimetry in CT},
  journal = {BJR|Artificial Intelligence},
  year = {2025},
  doi = {10.1093/bjrai/ubaf007}
}
Kostenlos starten →