Predicting hematoma expansion in acute spontaneous intracerebral hemorrhage: integrating clinical factors with a multitask deep learning model for non-contrast head CT.
Hyochul LeeJunhyeok LeeJoon JangInpyeong HwangKyu Sung ChoiJung Hyun ParkJin Wook ChungSeung Hong ChoiPublished in: Neuroradiology (2024)
The integration of clinical findings with non-contrast CT imaging features analyzed through deep learning showed the potential for improving the prediction of HE in acute spontaneous intracerebral hemorrhage patients.
Keyphrases
- deep learning
- contrast enhanced
- liver failure
- end stage renal disease
- brain injury
- computed tomography
- magnetic resonance
- image quality
- respiratory failure
- ejection fraction
- dual energy
- newly diagnosed
- chronic kidney disease
- machine learning
- high resolution
- magnetic resonance imaging
- aortic dissection
- artificial intelligence
- drug induced
- convolutional neural network
- prognostic factors
- hepatitis b virus
- positron emission tomography
- intensive care unit
- climate change
- patient reported outcomes
- risk assessment
- patient reported
- human health
- photodynamic therapy
- fluorescence imaging