Scholarlink

Peripheral Arterial Occlusive Disease (PAOD) management is essential in combating atherosclerosis-induced blockages, requiring advanced vascular imaging for accurate diagnosis and treatment. Artificial intelligence-enhanced super-resolution (SR) techniques are increasingly recognized for improving vascular imaging and decision support, enhancing PAOD treatment accuracy and efficacy. PAOD, caused by atherosclerosis, reduces blood flow to the lower extremities. Computed tomography angiography (CTA) images are used for evaluating PAOD, offering detailed visualization of vascular structures. This study used CTA images, the most common modality for daily PAOD evaluation, to demonstrate the role of SR techniques in decision support systems, particularly in healthcare. The research addresses challenges in segmenting CTA images of lower extremity arteries, highlighting SR techniques’ potential in refining artery segmentation, 3-D modeling, and visualization. Comparing SR models like SRCNN, EDSR, RCAN, SRGAN, and ESRGAN, the study identifies SRGAN as the optimal choice. These are models based on deep learning and generative models. Metrics like peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) validate model efficacy. This sophisticated technology aids healthcare professionals in making smarter decisions, analyzing complex information, and providing valuable recommendations.

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

Decision Support in Peripheral Arterial Occlusive Disease Management with AI-Enhanced Super-Resolution Techniques for Advanced Vascular Imaging

  • 章节

  • 发表日期：

    2026年

查看全文
  • Alexandra La Cruz,
  • Juan Pedro Felipe,
  • Erika Severeyn,
  • Andrés Garćıa-León

摘要

Peripheral Arterial Occlusive Disease (PAOD) management is essential in combating atherosclerosis-induced blockages, requiring advanced vascular imaging for accurate diagnosis and treatment. Artificial intelligence-enhanced super-resolution (SR) techniques are increasingly recognized for improving vascular imaging and decision support, enhancing PAOD treatment accuracy and efficacy. PAOD, caused by atherosclerosis, reduces blood flow to the lower extremities. Computed tomography angiography (CTA) images are used for evaluating PAOD, offering detailed visualization of vascular structures. This study used CTA images, the most common modality for daily PAOD evaluation, to demonstrate the role of SR techniques in decision support systems, particularly in healthcare. The research addresses challenges in segmenting CTA images of lower extremity arteries, highlighting SR techniques’ potential in refining artery segmentation, 3-D modeling, and visualization. Comparing SR models like SRCNN, EDSR, RCAN, SRGAN, and ESRGAN, the study identifies SRGAN as the optimal choice. These are models based on deep learning and generative models. Metrics like peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) validate model efficacy. This sophisticated technology aids healthcare professionals in making smarter decisions, analyzing complex information, and providing valuable recommendations.