Development of innovative radiotherapy support system with predictable prognosis in head and neck cancer

• Project/Area Number: 17K15808
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Medical Physics and Radiological Technology
• Research Institution: Teikyo University
• Principal Investigator: Kamezawa Hidemi 帝京大学, 福岡医療技術学部, 講師 (50759503)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000); Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
• Keywords: 頭頸部癌 / 予後予測 / 生存率 / 悪性度 / radiomics / 耳下腺癌 / 悪性度予測 / レディオミクス / Radiomics / 深層学習 / 医学物理学 / 放射線治療支援

Outline of Final Research Achievements

The purpose of this study was to develop an innovative radiotherapy support system with predictable prognosis in head and neck cancer. We could predict the 2-year survival of squamous cell head and neck cancer and malignancy glade of parotid gland cancer by using some machine learning approaches. Therefore, we could develop an innovative radiotherapy support system for squamous cell head and neck cancer and parotid gland cancer.
The proposed approach could support the decision making of the radiotherapy approach for the low 2-year survival squamous cell head and neck cancer and high glade parotid gland cancer.

Academic Significance and Societal Importance of the Research Achievements

本研究で開発した放射線治療支援システムは、治療前にあらかじめ扁平上皮頭頸部癌の２年生存率や高悪性度の耳下腺癌を予測できるため、それらの癌に最適な治療方針を検討する上で有用である。また、医用画像のみの入力で予測が可能であるため、非侵襲的であることは医学的意義も大きい。
さらには、頭頸部癌のみならず、他部位のさまざまな癌においても応用出来る可能性を持っており、波及効果も高いと考える。

Research Products

• [Journal Article] MR-radiomic biopsy for estimation of malignancy grade in parotid gland cancer (2020)
  • Author(s): Kamezawa Hidemi、Arimura Hidetaka、Yasumatsu Ryuji、Ninomiya Kenta
  • Journal Title: Proc. SPIE 11318, Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications, 1131818 Volume: 11318 Pages: 41-41
  • DOI: 10.1117/12.2549462
  • Peer Reviewed
• [Journal Article] Radiomics-based malignancy prediction of parotid gland tumor (2019)
  • Author(s): H. Kamezawa, H. Arimura, R. Yasumatsu, K. Ninomiya, S. Haseai
  • Journal Title: Proc. SPIE 11050 Volume: - Pages: 26-26
  • DOI: 10.1117/12.2521362
  • Peer Reviewed
• [Journal Article] Survival prediction of squamous cell head and neck cancer patients based on radiomic features selected from lung cancer patients using artificial neural network (2018)
  • Author(s): H. Kamezawa, H. Arimura, M. Soufi
  • Journal Title: Proc. SPIE 10579 Volume: - Pages: 43-43
  • DOI: 10.1117/12.2293415
  • Peer Reviewed
• [Presentation] MR-radiomic biopsy for estimation of malignancy grade in parotid gland cancer (2020)
  • Author(s): Hidemi Kamezawa, Hidetaka Arimura, Ryuji Yasumatsu, Kenta Ninomiya
  • Organizer: SPIE Medical Imaging 2020
  • Int'l Joint Research
• [Presentation] Radiomics-based malignancy estimation of parotid gland tumor using preoperative magnetic resonance images (2019)
  • Author(s): Hidemi Kamezawa, Hidetaka Arimura, Ryuji Yasumatsu, Soufi Mazen, Kenta Ninomiya, Shu Haseai
  • Organizer: 第117回日本医学物理学会学術大会
• [Presentation] Deep learning-based malignancy grade prediction models of parotid gland cancer using preoperative MR images (2019)
  • Author(s): Hidemi Kamezawa, Hidetaka Arimura, Ryuji Yasumatsu, Kenta Ninomiya, Shu Haseai
  • Organizer: American Association of Physicists in Medicine 61th annual meeting
  • Int'l Joint Research
• [Presentation] Radiomics-based Malignancy Prediction of Parotid Gland Tumor (2019)
  • Author(s): H. Kamezawa, H. Arimura, R. Yasumatsu, K. Ninomiya, S. Haseai
  • Organizer: IFMIA2019
  • Int'l Joint Research
• [Presentation] Radiomics-based prediction of malignant potential in patients with parotid gland cancer (2018)
  • Author(s): Hidemi Kamezawa, Hidetaka Arimura, Ryuji Yasumatsu, Mazen Souf, Shu Haseai and Kenta Ninomiya
  • Organizer: RSNA 2018
  • Int'l Joint Research
• [Presentation] Survival prediction of squamous cell head and neck cancer patients based on radiomic features selected from lung cancer patients using artificial neural network (2018)
  • Author(s): H. Kamezawa, H. Arimura, M. Soufi
  • Organizer: SPIE 10579, Medical Imaging 2018
  • Int'l Joint Research