Development of four-dimensional deep convolutional neural network-based nodular liver lesion detection software in Gd-EOB-DTPA-enhanced MRI.

Research Project

Project/Area Number	17K17653
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Multi-year Fund
Research Field	Medical systems Medical Physics and Radiological Technology
Research Institution	The University of Tokyo
Principal Investigator	Takenaga Tomomi 東京大学, 医学部附属病院, 特任研究員 (80779786)
Project Period (FY)	2017-04-01 – 2020-03-31
Project Status	Completed (Fiscal Year 2019)
Budget Amount *help	¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000) Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywords	自動検出 / FC-ResNet / Gd-EOB-DTPA / 深層畳み込みニューラルネットワーク / segmentation / 4D-DCNN / CADe / MRI / EOB-MRI
Outline of Final Research Achievements	The purpose of this study is to develop software for nodular liver lesion (metastatic liver lesion and hepatocellular carcinoma) detection in Gd-EOB-DTPA-enhanced MRI. The results of this study are as follows: (1) database constructed by 1.5 and 3.0 T MRI scanners from multivendor, (2) development of software for nodular liver lesion detection in Gd-EOB-DTPA-enhanced MRI, (3) automated liver segmentation to improve the accuracy of software for nodular liver lesion detection
Academic Significance and Societal Importance of the Research Achievements	肝転移，肝細胞癌において早期発見，適切な治療が生命予後の改善に重要である。現在、肝転移，肝細胞癌の検査の主流はEOB-MR画像となってきているが，EOB-MR画像を用いた肝結節性病変を自動検出する手法は申請者の知る限り開発されていない．本システムにより，EOB-MRI検査における結節性病変の診断能力が向上し，①より適切な治療法の選択や多発腫瘍の確実かつ完全な切除，②HCCや肝転移の適切な治療による担癌患者の生命予後の改善，③放射線科医による画像診断の精度向上および負担軽減など，さまざまな立場の人々に利益のある結果が得られると期待される．