Scholarlink

Background <p>The integration of ionizing radiation in medical practice has evolved significantly over the past century, with diagnostic radiology and nuclear medicine playing pivotal roles in modern healthcare. Despite its substantial benefits, radiation exposure poses inherent risks, necessitating adherence to the principle of “as low as reasonably achievable” (ALARA). Recent advancements in artificial intelligence (AI) have introduced transformative methodologies aimed at optimizing radiation use and improving patient safety.</p> Purpose <p>This review explores the application of AI techniques in radiology and nuclear medicine, specifically focusing on their role in reducing radiation exposure while maintaining diagnostic efficacy.</p> Methods <p>The article synthesizes findings from recent studies on AI-driven innovations, including machine learning algorithms, convolutional neural networks (CNNs), and deep learning models. It evaluates their contributions to imaging processes such as image reconstruction, enhancement, automated lesion detection, and quantitative analysis.</p> Results <p>AI technologies have demonstrated significant potential in improving image quality, reducing noise, enhancing resolution, and enabling precise dose optimization. These advancements have led to improved diagnostic accuracy, better treatment planning, and reduced radiation exposure for patients undergoing imaging procedures.</p> Conclusions <p>AI represents a promising frontier in clinical practices by enhancing safety and efficacy in diagnostic imaging. Its ability to optimize radiation doses while maintaining high-quality imaging underscores its transformative impact on patient care. Future developments in AI-driven predictive modeling and real-time decision support systems are expected to further revolutionize the field.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The role of artificial intelligence in optimizing radiation dose in diagnostic imaging

  • 期刊论文

  • 发表日期：

    2026年1月8日

查看全文
  • Hanieh Alimiri Dehbaghi,
  • Karim Khoshgard

摘要

Background

The integration of ionizing radiation in medical practice has evolved significantly over the past century, with diagnostic radiology and nuclear medicine playing pivotal roles in modern healthcare. Despite its substantial benefits, radiation exposure poses inherent risks, necessitating adherence to the principle of “as low as reasonably achievable” (ALARA). Recent advancements in artificial intelligence (AI) have introduced transformative methodologies aimed at optimizing radiation use and improving patient safety.

Purpose

This review explores the application of AI techniques in radiology and nuclear medicine, specifically focusing on their role in reducing radiation exposure while maintaining diagnostic efficacy.

Methods

The article synthesizes findings from recent studies on AI-driven innovations, including machine learning algorithms, convolutional neural networks (CNNs), and deep learning models. It evaluates their contributions to imaging processes such as image reconstruction, enhancement, automated lesion detection, and quantitative analysis.

Results

AI technologies have demonstrated significant potential in improving image quality, reducing noise, enhancing resolution, and enabling precise dose optimization. These advancements have led to improved diagnostic accuracy, better treatment planning, and reduced radiation exposure for patients undergoing imaging procedures.

Conclusions

AI represents a promising frontier in clinical practices by enhancing safety and efficacy in diagnostic imaging. Its ability to optimize radiation doses while maintaining high-quality imaging underscores its transformative impact on patient care. Future developments in AI-driven predictive modeling and real-time decision support systems are expected to further revolutionize the field.