Lung cancer screening (LCS) in ultra-low-dose CT (U-LDCT) by means of massive-training artificial neural network (MTANN) image-quality improvement

Research Project

Project/Area Number	26461793
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Research Field	Radiation science
Research Institution	Hiroshima University
Principal Investigator	Fukumoto Wataru 広島大学, 病院(医), 医科診療医 (00726870)
Co-Investigator(Kenkyū-buntansha)	粟井和夫広島大学, 医歯薬保健学研究院(医), 教授 (30294573) 檜垣徹広島大学, 医歯薬保健学研究院(医), 特任准教授 (80611334)
Research Collaborator	SUZUKI Kenji イリノイ工科大学
Project Period (FY)	2014-04-01 – 2017-03-31
Project Status	Completed (Fiscal Year 2016)
Budget Amount *help	¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000) Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords	機械学習 / 被曝低減 / 放射線被曝低減
Outline of Final Research Achievements	We developed a radiation dose reduction technology based on massive-training artificial neural network (MTANN) that learned to convert mDCT images to higher-dose-like CT images; thus term vHDCT technology. Our purpose in this study was to investigate and compare nodule detectability in mDCT with our vHDCT technology and that in low-dose CT (LDCT) in lung cancer screening (LCS). Detectability of solid nodules in vHDCT obtained with our MTANN technology at an mD level (0.2 mSv) would be comparable to that of LDCT (2.0 mSv); thus 90% dose reduction was achieved.