Synthetic Perfusion Maps: Imaging Perfusion Deficits in DSC-MRI with\n Deep Learning

2018/06/11 by Andreas Hess, Raphael Meier, Hess, Andreas +15
Medicine · #Acute Ischemic Stroke Management #Advanced MRI Techniques and Applications #Advanced Neuroimaging Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #MRI in cancer diagnosis #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.1806.03848

openalex publication_date 2018/06/11 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28

Abstract

In this work, we present a novel convolutional neural net- work based method\nfor perfusion map generation in dynamic suscepti- bility contrast-enhanced\nperfusion imaging. The proposed architecture is trained end-to-end and solely\nrelies on raw perfusion data for inference. We used a dataset of 151 acute\nischemic stroke cases for evaluation. Our method generates perfusion maps that\nare comparable to the target maps used for clinical routine, while being\nmodel-free, fast, and less noisy.\n

Related

• Quantitative perfusion maps using a novelty spatiotemporal convolutional neural network
• Neural Network-derived perfusion maps: a Model-free approach to computed tomography perfusion in patients with acute ischemic stroke
• Physiology-Informed Generative Multi-Task Network for Contrast-Free CT Perfusion
• CT-To-MR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation
• Deep generative computed perfusion-deficit mapping of ischaemic stroke