Detectability of Small Low-Attenuation Lesions With Deep Learning CT Image Reconstruction: A 24-Reader Phantom Study
Giuseppe V. Toia, D Zamora, Michael Singleton, Arthur Liu, Edward Tan, Shuai Leng, William P. Shuman, Kalpana M. Kanal, Achille Mileto
Abstract
DLIR has substantial potential to preserve contrast-dependent spatial resolution for the detection of hypoattenuating lesions at decreased radiation levels in a phantom model, addressing a major shortcoming of current IR techniques.
Topics & Concepts
Imaging phantomMedicineNuclear medicineIterative reconstructionImage qualityContrast (vision)Image resolutionArtificial intelligenceRadiologyComputer scienceImage (mathematics)Radiation Dose and ImagingAdvanced X-ray and CT ImagingAdvanced Radiotherapy Techniques