Feasibility study of lung nodule screening using pulmonary MRI and development of computer-assisted detection software

• Project/Area Number: 20K08045
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 52040:Radiological sciences-related
• Research Institution: The University of Tokyo
• Principal Investigator: Yoshikawa Takeharu 東京大学, 医学部附属病院, 特任准教授 (30293476)
• Co-Investigator(Kenkyū-buntansha): 越野 沙織 順天堂大学, 医学部, 非常勤助手 (50801552)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Project Status: Completed (Fiscal Year 2022)
• Budget Amount: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000); Fiscal Year 2022: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000); Fiscal Year 2021: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000); Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
• Keywords: 肺MRI / 肺がん / スクリーニング / 検診 / CAD / AI / 胸水 / 肺 / MRI

Outline of Research at the Start

低線量CTによる肺がん検診が広く行われるようになってきているが，CTの最大の問題点は放射線被ばくである．最近，撮像技術の発達により実用的な肺MRIの撮像が可能となってきた．本研究の目的は，肺MRIによる肺結節スクリーニングの実現可能性について検証すること，また，肺MRIによる肺結節スクリーニングに向けたCADeソフトウェア（病変の検出を支援するAIソフトウェア）を開発することである．検診受診者を対象として肺MRIの撮像を行い，肺MRIの読影結果と肺CTの読影結果を比較検討する．肺MRIでの肺結節の正解データを作成した上でCADeソフトウェアを開発し，臨床使用を試みる．

Outline of Final Research Achievements

Pulmonary MRI with ultrashort echo time (UTE) is expected to be an alternative to low-dose CT for lung screening. The feasibility of breath-hold (BH) and respiratory triggered (RT) scans with UTE was investigated. Both results of qualitative and quantitative assessment suggested that a solid nodule was more clearly depicted than a ground-glass nodule. BH scan in pulmonary MRI should be more suitable for lung screening than RT scan.
We prepared a lung and bronchus region dataset and a lung nodule dataset to develop computer-assisted detection (CADe) software for lung nodule screening. We have developed an automatic extraction method of both lung areas and bronchi regions simultaneously using deep learning, and accurate extraction were achieved. Now, we are developing (CADe) software for lung nodule screening.
Chest MRI was highly sensitive in detecting pleural fluid, which was considered mainly physiological. It was relevant to other clinical factors.

Academic Significance and Societal Importance of the Research Achievements

本研究により，肺MRIによる肺結節スクリーニングは実現可能であることが示された．呼吸停止下撮像が第一選択であり，時間に余裕があれば呼吸同期撮像を追加するのが望ましい．現状では，すりガラス状結節は充実性結節より検出が難しく，検出能の向上のために撮像技術の進歩などによる改善が望まれる．
本研究で開発した手法により，肺MRIでの肺野および気管支領域の自動抽出が可能となった．肺結節スクリーニングのためのコンピュータ支援検出ソフトウェアの開発を進めた．初期のソフトウェアでは期待していたほどの肺結節検出能が得られなかったが，学習症例数を追加することで性能改善が期待される．

Research Products

• [Presentation] Automated segmentation of lung area and bronchi regions in ultra-short TE MR images using deep learning (2023)
  • Author(s): Takahashi M, Nomura Y, Takenaga T, Hanaoka S, Yoshikawa T, Abe S
  • Organizer: 第79回放射線技術学会総会学術大会
• [Presentation] The prevalence and clinical significance of pleural fluid detected by chest MRI: a cross-sectional study in a medical checkup setting (2021)
  • Author(s): Fukuda K, Matsuzaki H, Saito A, Nagase T, Yoshikawa T
  • Organizer: The 25th Congress of the Asian Pacific Society of Respirology
  • Int'l Joint Research
• [Presentation] Feasibility study of nodule conspicuity for lung screening using ultrashort echo time MRI (2020)
  • Author(s): Koshino S, Yoshikawa T, Nomura Y, Miki S, Hanaoka S, Watadani T, Hayashi N, Abe O
  • Organizer: 2020 ISMRM & SMRT VIRTUAL CONFERENCE & EXHIBITION
  • Int'l Joint Research