Yoshifumi Noda1, Yukako Iritani2, Nobuyuki Kawai2, Toshiharu Miyoshi3, Takuma Ishihara4, Fuminori Hyodo5, Masayuki Matsuo2. 1. Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan. noda1031@gifu-u.ac.jp. 2. Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan. 3. Department of Radiology Services, Gifu University Hospital, 1-1 Yanagido, Gifu, 501-1194, Japan. 4. Innovative and Clinical Research Promotion Center, Gifu University Hospital, 1-1 Yanagido, Gifu, 501-1194, Japan. 5. Department of Radiology, Frontier Science for Imaging, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan.
Abstract
PURPOSE: To evaluate image quality, image noise, and conspicuity of pancreatic ductal adenocarcinoma (PDAC) in pancreatic low-dose computed tomography (LDCT) reconstructed using deep learning image reconstruction (DLIR) and compare with those of images reconstructed using hybrid iterative reconstruction (IR). METHODS: Our institutional review board approved this prospective study. Written informed consent was obtained from all patients. Twenty-eight consecutive patients with PDAC undergoing chemotherapy (14 men and 14 women; mean age, 68.4 years) underwent pancreatic LDCT for therapy evaluation. The LDCT images were reconstructed using 40% adaptive statistical iterative reconstruction-Veo (hybrid-IR) and DLIR at medium and high levels (DLIR-M and DLIR-H). The image noise, diagnostic acceptability, and conspicuity of PDAC were qualitatively assessed using a 5-point scale. CT numbers of the abdominal aorta, portal vein, pancreas, PDAC, background noise, signal-to-noise ratio (SNR) of the anatomical structures, and tumor-to-pancreas contrast-to-noise ratio (CNR) were calculated. Qualitative and quantitative parameters were compared between the hybrid-IR, DLIR-M, and DLIR-H images. RESULTS: CT dose-index volumes and dose-length product in pancreatic LDCT were 2.3 ± 1.0 mGy and 74.9 ± 37.0 mGy•cm, respectively. The image noise, diagnostic acceptability, and conspicuity of PDAC were significantly better in DLIR-H than those in hybrid-IR and DLIR-M (all P < 0.001). The background noise was significantly lower in the DLIR-H images (P < 0.001) and resulted in improved SNRs (P < 0.001) and CNR (P < 0.001) compared with those in the hybrid-IR and DLIR-M images. CONCLUSION: DLIR significantly reduced image noise and improved image quality in pancreatic LDCT images compared with hybrid-IR.
PURPOSE: To evaluate image quality, image noise, and conspicuity of pancreatic ductal adenocarcinoma (PDAC) in pancreatic low-dose computed tomography (LDCT) reconstructed using deep learning image reconstruction (DLIR) and compare with those of images reconstructed using hybrid iterative reconstruction (IR). METHODS: Our institutional review board approved this prospective study. Written informed consent was obtained from all patients. Twenty-eight consecutive patients with PDAC undergoing chemotherapy (14 men and 14 women; mean age, 68.4 years) underwent pancreatic LDCT for therapy evaluation. The LDCT images were reconstructed using 40% adaptive statistical iterative reconstruction-Veo (hybrid-IR) and DLIR at medium and high levels (DLIR-M and DLIR-H). The image noise, diagnostic acceptability, and conspicuity of PDAC were qualitatively assessed using a 5-point scale. CT numbers of the abdominal aorta, portal vein, pancreas, PDAC, background noise, signal-to-noise ratio (SNR) of the anatomical structures, and tumor-to-pancreas contrast-to-noise ratio (CNR) were calculated. Qualitative and quantitative parameters were compared between the hybrid-IR, DLIR-M, and DLIR-H images. RESULTS: CT dose-index volumes and dose-length product in pancreatic LDCT were 2.3 ± 1.0 mGy and 74.9 ± 37.0 mGy•cm, respectively. The image noise, diagnostic acceptability, and conspicuity of PDAC were significantly better in DLIR-H than those in hybrid-IR and DLIR-M (all P < 0.001). The background noise was significantly lower in the DLIR-H images (P < 0.001) and resulted in improved SNRs (P < 0.001) and CNR (P < 0.001) compared with those in the hybrid-IR and DLIR-M images. CONCLUSION: DLIR significantly reduced image noise and improved image quality in pancreatic LDCT images compared with hybrid-IR.
Entities:
Keywords:
Deep learning; Image processing; Multidetector computed tomography; Pancreas
Authors: Elanchezhian Somasundaram; Jonathan R Dillman; Eric J Crotty; Andrew T Trout; Alexander J Towbin; Christopher G Anton; Angeline Logan; Catherine A Wieland; Samantha Felekey; Brian D Coley; Samuel L Brady Journal: Radiol Artif Intell Date: 2020-09-30
Authors: Hendrik Joost Wisselink; Gert Jan Pelgrim; Mieneke Rook; Ivan Dudurych; Maarten van den Berge; Geertruida H de Bock; Rozemarijn Vliegenthart Journal: Eur Radiol Exp Date: 2021-09-10