Deep learning-based interpretation of basal/acetazolamide brain perfusion SPECT leveraging unstructured reading reports.
Hyun Gee RyooHongyoon ChoiDong Soo LeePublished in: European journal of nuclear medicine and molecular imaging (2020)
We developed a deep learning model to support the interpretation of brain perfusion SPECT by converting unstructured text reports into structured labels. This model can be used as a support system not only to identify perfusion abnormalities but also to provide quantitative scores of abnormalities, particularly for patients who require revascularization.
Keyphrases
- deep learning
- contrast enhanced
- white matter
- resting state
- artificial intelligence
- convolutional neural network
- pet ct
- machine learning
- adverse drug
- high resolution
- magnetic resonance
- computed tomography
- emergency department
- mass spectrometry
- acute coronary syndrome
- atrial fibrillation
- electronic health record
- subarachnoid hemorrhage