Effectiveness of deep learning reconstruction on standard to ultra-low-dose high-definition chest CT images.
Nayu HamabuchiYoshiharu OhnoHirona KimataYuya ItoKenji FujiiNaruomi AkinoDaisuke TakenakaTakeshi YoshikawaYuka OshimaTakahiro MatsuyamaHiroyuki NagataTakahiro UedaHirotaka IkedaYoshiyuki OzawaHiroshi ToyamaPublished in: Japanese journal of radiology (2023)
DLR is potentially more effective for image quality improvement and lung texture evaluation than hybrid-type IR on all radiation dose CTs obtained at HDCT and reconstructed with each section thickness with both matrixes for patients with a variety of pulmonary diseases.
Keyphrases
- deep learning
- low dose
- quality improvement
- contrast enhanced
- convolutional neural network
- artificial intelligence
- randomized controlled trial
- pulmonary hypertension
- computed tomography
- optical coherence tomography
- high dose
- machine learning
- image quality
- systematic review
- patient safety
- high resolution
- dual energy
- magnetic resonance imaging
- magnetic resonance
- positron emission tomography
- mass spectrometry