Yoshinori Kanii1, Yasutaka Ichikawa2, Ryohei Nakayama3, Motonori Nagata1, Masaki Ishida1, Kakuya Kitagawa1, Shuichi Murashima4, Hajime Sakuma1. 1. Department of Radiology, Mie University Hospital, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan. 2. Department of Radiology, Mie University Hospital, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan. yasutaka@clin.medic.mie-u.ac.jp. 3. Department of Electronic and Computer Engineering, Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga, 525-8577, Japan. 4. Department of Radiology, Matsusaka Chuo General Hospital, 102 Kobou, Kawai, Matsusaka, Mie, 515-8566, Japan.
Abstract
PURPOSE: To develop a dictionary learning (DL)-based processing technique for improving the image quality of sub-millisievert chest computed tomography (CT). MATERIALS AND METHODS: Standard-dose and sub-millisievert chest CT were acquired in 12 patients. Dictionaries including standard- and low-dose image patches were generated from the CT datasets. For each patient, DL-based processing was performed for low-dose CT using the dictionaries generated from the remaining 11 patients. This procedure was repeated for all 12 patients. Image quality of normal thoracic structures on the processed sub-millisievert CT images was assessed with a 5-point scale (5 = excellent, 1 = very poor). Lung lesion conspicuity was also assessed on a 5-point scale. RESULTS: Image noise on sub-millisievert CT was significantly decreased with DL-based image processing (48.5 ± 13.7 HU vs 20.4 ± 7.9 HU, p = 0.0005). Image quality of lung structures was significantly improved with DL-based method (middle level of lung, 2.25 ± 0.75 vs 2.92 ± 0.79, p = 0.0078). Lung lesion conspicuity was also significantly improved with DL-based technique (solid nodules, 3.4 ± 0.6 vs 2.7 ± 0.6, p = 0.0273). CONCLUSION: Image quality and lesion conspicuity on sub-millisievert chest CT images may be improved by DL-based post-processing.
PURPOSE: To develop a dictionary learning (DL)-based processing technique for improving the image quality of sub-millisievert chest computed tomography (CT). MATERIALS AND METHODS: Standard-dose and sub-millisievert chest CT were acquired in 12 patients. Dictionaries including standard- and low-dose image patches were generated from the CT datasets. For each patient, DL-based processing was performed for low-dose CT using the dictionaries generated from the remaining 11 patients. This procedure was repeated for all 12 patients. Image quality of normal thoracic structures on the processed sub-millisievert CT images was assessed with a 5-point scale (5 = excellent, 1 = very poor). Lung lesion conspicuity was also assessed on a 5-point scale. RESULTS: Image noise on sub-millisievert CT was significantly decreased with DL-based image processing (48.5 ± 13.7 HU vs 20.4 ± 7.9 HU, p = 0.0005). Image quality of lung structures was significantly improved with DL-based method (middle level of lung, 2.25 ± 0.75 vs 2.92 ± 0.79, p = 0.0078). Lung lesion conspicuity was also significantly improved with DL-based technique (solid nodules, 3.4 ± 0.6 vs 2.7 ± 0.6, p = 0.0273). CONCLUSION: Image quality and lesion conspicuity on sub-millisievert chest CT images may be improved by DL-based post-processing.
Authors: Jonathon Leipsic; Troy M Labounty; Brett Heilbron; James K Min; G B John Mancini; Fay Y Lin; Carolyn Taylor; Allison Dunning; James P Earls Journal: AJR Am J Roentgenol Date: 2010-09 Impact factor: 3.959
Authors: Priyanka Prakash; Mannudeep K Kalra; Jeanne B Ackman; Subba R Digumarthy; Jiang Hsieh; Synho Do; Jo-Anne O Shepard; Matthew D Gilman Journal: Radiology Date: 2010-07 Impact factor: 11.105
Authors: Yoshiko Sagara; Amy K Hara; William Pavlicek; Alvin C Silva; Robert G Paden; Qing Wu Journal: AJR Am J Roentgenol Date: 2010-09 Impact factor: 3.959
Authors: Priyanka Prakash; Mannudeep K Kalra; Avinash K Kambadakone; Homer Pien; Jiang Hsieh; Michael A Blake; Dushyant V Sahani Journal: Invest Radiol Date: 2010-04 Impact factor: 6.016
Authors: Mannudeep K Kalra; Michael M Maher; Thomas L Toth; Leena M Hamberg; Michael A Blake; Jo-Anne Shepard; Sanjay Saini Journal: Radiology Date: 2004-01-22 Impact factor: 11.105