Deep learning-based reconstruction in ultra-high-resolution computed tomography: Can image noise caused by high definition detector and the miniaturization of matrix element size be improved?
Autor: | Eiji Nishimaru, Tsukasa Yoshida, Yoshihiro Nakaya, Takanori Hara, Masahiro Endo, Atsushi Urikura |
---|---|
Rok vydání: | 2020 |
Předmět: |
Image quality
Noise reduction Biophysics General Physics and Astronomy Radiation Dosage Imaging phantom 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Optics Deep Learning Image noise Image Processing Computer-Assisted Radiology Nuclear Medicine and imaging Physics Miniaturization Radon transform business.industry Phantoms Imaging Detector Resolution (electron density) General Medicine 030220 oncology & carcinogenesis Radiographic Image Interpretation Computer-Assisted business Tomography X-Ray Computed Noise (radio) Algorithms |
Zdroj: | Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB). 81 |
ISSN: | 1724-191X |
Popis: | Purpose This study aimed to assess the noise characteristics of ultra-high-resolution computed tomography (UHRCT) with deep learning-based reconstruction (DLR). Methods Two different diameters of water phantom were scanned with three different resolution acquisition modes. Images were reconstructed by filtered back projection (FBP), hybrid iterative reconstruction (hybrid-IR), and DLR. Image noise analysis was performed with noise magnitude, peak frequency (fp) of the noise power spectrum (NPS), and the square root of the area under the curve (√AUCNPS) for the NPS curve. Results The noise magnitude was up to 3.30 times higher for the FBP acquired in SHR mode than that for the NR mode. The fp values of the FBP were 0.20–0.21, 0.34–0.36, and 0.34–0.37 cycles/mm for normal resolution (NR), high resolution (HR), and super high resolution (SHR) mode, respectively. The fp of hybrid-IR was 0.16–0.19, 0.21–0.26, and 0.23–0.26 cycles/mm for NR, HR, and SHR mode, respectively. The fp of DLR was 0.21–0.32 and 0.22–0.33 cycles/mm for HR and SHR mode, respectively. √AUCNPS showed that the highest value in FBP images of the SHR mode was up to 1.89 times that of the NR mode. DLR in the HR and SHR modes showed high noise reduction while suppressing fp shift with respect to FBP. Conclusions The new DLR algorithm could be a solution to the noise increase due to the high-definition detector elements and the small reconstruction matrix element size. |
Databáze: | OpenAIRE |
Externí odkaz: |