Prediction of All-Cause Mortality Based on Stress/Rest Myocardial Perfusion Imaging (MPI) Using Deep Learning: A Comparison between Image and Frequency Spectra as Input.
Da-Chuan ChengTe-Chun HsiehYu-Ju HsuYung-Chi LaiKuo-Yang YenCharles C N WangChia-Hung KaoPublished in: Journal of personalized medicine (2022)
This is the first trial to use pure rest/stress MPI polar maps and limited clinical data to predict patients' 5-year survival based on CNN models and deep learning. The study shows the feasibility of using frequency spectra rather than images, which might increase the performance of CNNs.
Keyphrases
- deep learning
- convolutional neural network
- artificial intelligence
- end stage renal disease
- machine learning
- ejection fraction
- newly diagnosed
- chronic kidney disease
- high resolution
- clinical trial
- study protocol
- density functional theory
- big data
- randomized controlled trial
- heat stress
- photodynamic therapy
- patient reported outcomes
- free survival