Leveraging open dataset and transfer learning for accurate recognition of chronic pulmonary embolism from CT angiogram maximum intensity projection images.
Tuomas VainioTeemu MäkeläAnssi ArkkoSauli SavolainenMarko KangasniemiPublished in: European radiology experimental (2023)
• Automatic recognition of CPE from computed tomography pulmonary angiography was developed. • Deep learning was applied on two-dimensional maximum intensity projection images. • A large public dataset was used for training the deep learning model. • The proposed model showed an excellent predictive accuracy.
Keyphrases
- deep learning
- pulmonary embolism
- computed tomography
- image quality
- convolutional neural network
- artificial intelligence
- positron emission tomography
- dual energy
- machine learning
- inferior vena cava
- optical coherence tomography
- high intensity
- magnetic resonance imaging
- healthcare
- pulmonary hypertension
- contrast enhanced
- minimally invasive
- mental health
- high resolution
- emergency department
- drug induced
- mass spectrometry
- adverse drug