Toward automated segmentation for acute ischemic stroke using non-contrast computed tomography.
Shih-Yen LinPi-Ling ChiangPeng-Wen ChenLi-Hsin ChengMeng-Hsiang ChenPei-Chun ChangWei-Che LinYong-Sheng ChenPublished in: International journal of computer assisted radiology and surgery (2022)
This study demonstrated the potentials of R2U-RNet model for automated NCCT AIS lesion segmentation. The proposed model can serve as a tool for accelerating AIS diagnoses and improving the treatment quality of AIS patients.
Keyphrases
- deep learning
- acute ischemic stroke
- computed tomography
- end stage renal disease
- convolutional neural network
- machine learning
- high throughput
- ejection fraction
- newly diagnosed
- magnetic resonance
- prognostic factors
- magnetic resonance imaging
- positron emission tomography
- peritoneal dialysis
- contrast enhanced
- patient reported outcomes
- single cell
- image quality