Scholarlink

<p>Advances in magnetic resonance imaging (MRI) have revolutionized disease detection and treatment planning. However, the growing volume and complexity of MRI data—along with heterogeneity in imaging protocols, scanner technology, and labeling practices—creates a need for standardized tools to automatically identify and characterize key imaging attributes. Such tools are essential for large-scale, multi-institutional studies that rely on harmonized data to train robust machine learning models. In this study, we developed convolutional neural networks (CNNs) to automatically classify three core attributes of abdominal MRI: pulse sequence type, imaging orientation, and contrast enhancement status. Three distinct CNNs with similar backbone architectures were trained to classify single image slices into one of 12 pulse sequences, 4 orientations, or 2 contrast classes. The models achieved high classification accuracies of 99.51%, 99.87%, and 99.99% for pulse sequence, orientation, and contrast, respectively. We applied Grad-CAM to visualize image regions influencing pulse sequence predictions and highlight relevant anatomical features. To enhance performance, we implemented a majority voting approach to aggregate slice-level predictions, achieving 100% accuracy at the volume level for all tasks. External validation using the Duke Liver Dataset demonstrated strong generalizability; after adjusting for class label mismatch, volume-level accuracies exceeded 96.9% across all classification tasks.</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

Automated characterization of abdominal MRI exams using deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月25日

查看全文
  • Joonghyun Kim,
  • Allison Chae,
  • Jeffrey Duda,
  • Arijitt Borthakur,
  • Daniel J. Rader,
  • James C. Gee,
  • Charles E. Kahn Jr.,
  • Daniel J. Rader,
  • Marylyn D. Ritchie,
  • JoEllen Weaver,
  • Nawar Naseer,
  • Afiya Poindexter,
  • Khadijah Hu-Sain,
  • Yi-An Ko,
  • Meghan Livingstone,
  • Fred Vadivieso,
  • Stephanie DerOhannessian,
  • Teo Tran,
  • Julia Stephanowski,
  • Monica Zielinski,
  • Ned Haubein,
  • Joseph Dunn,
  • Anurag Verma,
  • Colleen M. Kripke,
  • Marjorie Risman,
  • Renae Judy,
  • Shefali S. Verma,
  • Yuki Bradford,
  • Scott Dudek,
  • Theodore Drivas,
  • Walter R. Witschey,
  • Hersh Sagreiya

摘要

Advances in magnetic resonance imaging (MRI) have revolutionized disease detection and treatment planning. However, the growing volume and complexity of MRI data—along with heterogeneity in imaging protocols, scanner technology, and labeling practices—creates a need for standardized tools to automatically identify and characterize key imaging attributes. Such tools are essential for large-scale, multi-institutional studies that rely on harmonized data to train robust machine learning models. In this study, we developed convolutional neural networks (CNNs) to automatically classify three core attributes of abdominal MRI: pulse sequence type, imaging orientation, and contrast enhancement status. Three distinct CNNs with similar backbone architectures were trained to classify single image slices into one of 12 pulse sequences, 4 orientations, or 2 contrast classes. The models achieved high classification accuracies of 99.51%, 99.87%, and 99.99% for pulse sequence, orientation, and contrast, respectively. We applied Grad-CAM to visualize image regions influencing pulse sequence predictions and highlight relevant anatomical features. To enhance performance, we implemented a majority voting approach to aggregate slice-level predictions, achieving 100% accuracy at the volume level for all tasks. External validation using the Duke Liver Dataset demonstrated strong generalizability; after adjusting for class label mismatch, volume-level accuracies exceeded 96.9% across all classification tasks.