Scholarlink

<p>Accurately predicting long-term outcomes after stroke remains a key challenge in personalized medicine. Here, we present a neuroimaging platform that forecasts individualized cognitive outcomes in patients with ischemic stroke using deep learning-based lesion segmentation and location-/network-based features. This novel, fully automated system is capable of processing raw DICOM MRI data from heterogeneous scanners and generating text-based, personalized outcome information. To demonstrate this pipeline, we trained cognitive outcome-prediction models using a large lesion cohort (<i>N</i> = 604) and applied them to an independent stroke cohort (<i>N</i> = 153). Multiple cognitive outcome predictions achieved reasonable accuracy, with 96% concordance with manual methods. A report generated by a large language model provides interpretable, patient-specific prognoses within ~3 min. This demonstrates the potential for imaging-informed prognostication to inform stroke care and guide rehabilitation strategies.</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

A clinical neuroimaging platform for rapid, automated lesion detection and personalized post-stroke outcome prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月27日

查看全文
  • Michal Brzus,
  • Joseph Griffis,
  • Cavan J. Riley,
  • Joel Bruss,
  • Carrie Shea,
  • Hans J. Johnson,
  • Aaron D. Boes

摘要

Accurately predicting long-term outcomes after stroke remains a key challenge in personalized medicine. Here, we present a neuroimaging platform that forecasts individualized cognitive outcomes in patients with ischemic stroke using deep learning-based lesion segmentation and location-/network-based features. This novel, fully automated system is capable of processing raw DICOM MRI data from heterogeneous scanners and generating text-based, personalized outcome information. To demonstrate this pipeline, we trained cognitive outcome-prediction models using a large lesion cohort (N = 604) and applied them to an independent stroke cohort (N = 153). Multiple cognitive outcome predictions achieved reasonable accuracy, with 96% concordance with manual methods. A report generated by a large language model provides interpretable, patient-specific prognoses within ~3 min. This demonstrates the potential for imaging-informed prognostication to inform stroke care and guide rehabilitation strategies.