Establishment of CT diagnosis of small adenocarcinoma of the lung based on quantitative image analysis

• Project/Area Number: 17K10352
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Radiation science
• Research Institution: Niigata University
• Principal Investigator: Ishikawa Hiroyuki 新潟大学, 医歯学総合病院, 講師 (90377151)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000); Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
• Keywords: 肺腺癌 / 薄層CT / テクスチャ解析 / 放射線 / CT / 肺癌 / 画像 / 解析・評価

Outline of Final Research Achievements

Adenocarcinoma in situ and minimally invasive adenocarcinoma were accurately differentiated from invasive adenocarcinoma of the lung using quantitative CT image analysis, which appeared as ground-glass opacity at high-resolution CT.
Reproducibility of quantitative analysis was maintained regardless of experience of CT image interpretation. Quantitative image analysis and automatic feature extraction using artificial intelligence can stratify the postoperative prognosis and may have equal or greater prognostic accuracy than conventional features evaluated by experienced thoracic radiologists.

Academic Significance and Societal Importance of the Research Achievements

肺腺癌の治療法の選択や予後の予測において、上皮内腺癌～微少浸潤性腺癌と浸潤性腺癌の鑑別は重要である。この鑑別は薄層CTにより非侵襲的に行われることが期待されているが、視覚的評価のみでは限界があった。今回、定量的画像解析を用いることで良好な鑑別能が示され、新たな可能性を示すことができた。また、定量的画像解析による予後予測能も視覚的評価より優れている可能性が示された。

Research Products

• [Journal Article] HRCT texture analysis for pure or part-solid ground-glass nodules: distinguishability of adenocarcinoma in situ or minimally invasive adenocarcinoma from invasive adenocarcinoma. (2018)
  • Author(s): Takuya Yagi, Motohiko Yamazaki, Riuko Ohashi, Rei Ogawa, Hiroyuki Ishikawa, Norihiko Yoshimura, Masanori Tsuchida, Yoichi Ajioka, Hidefumi Aoyama
  • Journal Title: Japanese Journal of Radiology Volume: 36 Issue: 2 Pages: 113-121
  • DOI: 10.1007/s11604-017-0711-2
  • NAID: 210000173132
  • Peer Reviewed
• [Presentation] A comparison of the prognostic accuracy between convolutional neural network and conventional evaluation in clinical stage I lung adenocarcinoma (2020)
  • Author(s): 山崎元彦、八木琢也、石川浩志、吉村宣彦
  • Organizer: 第79回日本医学放射線学会総会
• [Presentation] すりガラス肺腺癌に対するHRCTテクスチャ解析：AIS-MIAと浸潤癌の鑑別能の検討 (2018)
  • Author(s): 山崎元彦、八木琢也、石川浩志、青山英史
  • Organizer: 第77回日本医学放射線学会総会
• [Presentation] CTテクスチャ解析を用いたAIS-MIAと浸潤癌の鑑別能に関する検討：医師と医学生による評価 (2018)
  • Author(s): 山崎元彦、八木琢也、石川浩志、青山英史、佐藤征二郎、小池輝元、土田正則、大橋瑠子
  • Organizer: 第42回新潟肺癌研究会総会
• [Presentation] 肺腺癌の組織分類鑑別能の検討: 医学生のテクスチャ解析と放射線科医の視覚評価との対比 (2018)
  • Author(s): 山崎元彦、八木琢也、石川浩志、吉村宣彦、青山英史
  • Organizer: 第25回日本CT検診学会学術集会
• [Presentation] HRCTの定量解析を用いた肺腺癌組織分類の鑑別 (2017)
  • Author(s): 八木琢也、山崎元彦、小川玲、石川浩志、吉村宣彦、青山英史、佐藤誠二郎、小池輝元、土田正則、大橋瑠子
  • Organizer: 第41回新潟肺癌研究会総会
• [Presentation] テクスチャ解析を用いた肺腺癌の再発予測に関する検討 (2017)
  • Author(s): 山崎元彦、八木琢也、石川浩志、青山英史
  • Organizer: 第137回日本医学放射線学会北日本地方会
• [Presentation] CT-Based Radiomics Signature: A Potential Postoperative Prognostic Marker for Patients with Lung Adenocarcinoma. (2017)
  • Author(s): Motohiko Yamazaki, Takuya Yagi, Hiroyuki Ishikawa,, Hidefumi Aoyama
  • Organizer: RSNA 2017 - 103rd Scientific Assembly and Annual Meeting
  • Int'l Joint Research