Development of attenuation correction methods using deep learning in brain-perfusion single-photon emission computed tomography.
Taisuke MurataHajime YokotaRyuhei YamatoTakuro HorikoshiMasato TsunedaRyuna KurosawaTakuma HashimotoJoji OtaKoichi SawadaTakashi IimoriYoshitada MasudaYasukuni MoriHiroki SuyariTakashi UnoPublished in: Medical physics (2021)
New deep learning-based AC methods for AutoencoderAC and U-NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U-NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo-CT images. To verify our models' generalizability, external validation is required.
Keyphrases
- deep learning
- computed tomography
- convolutional neural network
- artificial intelligence
- contrast enhanced
- positron emission tomography
- machine learning
- dual energy
- image quality
- high resolution
- magnetic resonance imaging
- transcription factor
- systematic review
- resting state
- white matter
- magnetic resonance
- blood brain barrier
- functional connectivity
- mass spectrometry
- cerebral ischemia