• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Prediction of prognosis after radiochemotherapy for head and neck cancer using recurrent neural networks and MR images

Research Project

Project/Area Number 21K15814
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionSt. Marianna University School of Medicine

Principal Investigator

Tomita Hayato  聖マリアンナ医科大学, 医学部, 講師 (90647801)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2022: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2021: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Keywords深層学習 / 人工知能 / 予後予測 / 喉頭癌 / 下咽頭癌 / 拡散強調画像 / 放射線治療 / 再起型ニューラルネットワーク / ADC / 頭頸部癌 / 畳み込み型ニューラルネットワーク / 拡散強調像 / 再帰型ニューラルネットワーク / MR / 放射線化学療法
Outline of Research at the Start

進行期頭頸部癌に対する化学放射線療法は,25-30%に再発を認める.後療法への早期の切り替えは,予後の改善や医療コストの低下につながる.これまでの頭頸部癌の治療効果予測因子は治療前の画一的な評価であり,患者個々に合わせた評価がなされず,十分な役割を果たしていない.近年,医療画像に対して深層学習を用いた治療効果予測,予後予測が行われるようになったが, 治療中の腫瘍の「経時的変化」を捉えた評価・判定の研究は進んでいない.本研究では,進行期頭頸部癌の治療前画像と治療中画像を用いて,腫瘍の経時的変化を反映させた深層学習を行うことにより,治療効果予測および予後予測の新たな評価方法を確立する.

Outline of Final Research Achievements

This preliminary study aimed to develop a DL model using DWI and ADC map to predict local recurrence and 2-year PFS in laryngeal and hypopharyngeal cancer patients treated by curative therapy related to radiotherapy. All patients underwent MR before and 4 weeks after the start of radiotherapy. The DL models that extracted imaging features on pretreatment and intra-treatment DWI and ADC map were trained to predict the local recurrence within a 2-year follow-up. The best AUC and accuracy for predicting the local recurrence in the DL model using intra-treatment DWI (DWIintra) were 0.767 and 81.0 %, respectively. Log-rank test showed that DWIintra was significantly associated with PFS (P = 0.013). DWIintra was an independent prognostic factor for PFS in multivariate analysis (P = 0.016).

Academic Significance and Societal Importance of the Research Achievements

畳み込み型ニューラルネットワークと治療中の拡散強調像を用いた場合、治療後の再発はAUCで0.767,正診率は81.0%であった。高リスク群と低リスク群に分類し、 Log-rankテストを行うと、同手法を用いた治療中の拡散強調像から2年の予後予測であった(P = 0.013)。また、Cox regression解析では深層学習による手法が 2年の予後予測の唯一の因子であることが分かった(P = 0.016)。このことは、これまで医用画像と深層学習を用いた研究では証明されていなかった内容である。また、本研究は他の腫瘍でも同様の方法を使用することができるため、研究の意義は大きいと思われる。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (6 results)

All 2023 2022

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 1 results) Presentation (1 results) (of which Invited: 1 results)

  • [Journal Article] Radiomics model of diffusion-weighted whole-body imaging with background signal suppression (DWIBS) for predicting axillary lymph node status in breast cancer2023

    • Author(s)
      Haraguchi Takafumi、Kobayashi Yasuyuki、Hirahara Daisuke、Kobayashi Tatsuaki、Takaya Eichi、Nagai Mariko Takishita、Tomita Hayato、Okamoto Jun、Kanemaki Yoshihide、Tsugawa Koichiro
    • Journal Title

      Journal of X-Ray Science and Technology

      Volume: 1 Issue: 3 Pages: 1-14

    • DOI

      10.3233/xst-230009

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Deep learning approach of diffusion-weighted imaging as an outcome predictor in laryngeal and hypopharyngeal cancer patients with radiotherapy-related curative treatment: a preliminary study2022

    • Author(s)
      Tomita Hayato、Kobayashi Tatsuaki、Takaya Eichi、Mishiro Sono、Hirahara Daisuke、Fujikawa Atsuko、Kurihara Yoshiko、Mimura Hidefumi、Kobayashi Yasuyuki
    • Journal Title

      European Radiology

      Volume: 32 Issue: 8 Pages: 5353-5361

    • DOI

      10.1007/s00330-022-08630-9

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Radiomics analysis for differentiating of cervical lymphadenopathy between cancer of unknown primary and malignant lymphoma on unenhanced computed tomography2022

    • Author(s)
      Hayato Tomita, Tsuneo Yamashiro, Gyo Iida, Maho Tsubakimoto, Hidefumi Mimura, Sadayuki Murayama
    • Journal Title

      Nagoya Journal of Medical Science

      Volume: 84 Issue: 2 Pages: 269-285

    • DOI

      10.18999/nagjms.84.2.269

    • ISSN
      0027-7622
    • URL

      https://nagoya.repo.nii.ac.jp/records/2002878

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Therapeutic efficacy of selective intraarterial chemoradiotherapy with docetaxel and nedaplatin for human papilloma virus-negative oropharyngeal cancer2022

    • Author(s)
      Heianna Joichi、Makino Wataru、Hirakawa Hitoshi、Agena Shinya、Tomita Hayato、Ariga Takuro、Ishikawa Kazuki、Takehara Shota、Kusada Takeaki、Maemoto Hitoshi、Maeda Hiroyuki、Murayama Sadayuki
    • Journal Title

      Auris Nasus Larynx

      Volume: 49 Issue: 3 Pages: 468-476

    • DOI

      10.1016/j.anl.2021.10.014

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Therapeutic efficacy of selective intra-arterial chemoradiotherapy with docetaxel and nedaplatin for fixed bulky nodal disease in head and neck cancer of unknown primary2022

    • Author(s)
      Heianna Joichi、Makino Wataru、Hirakawa Hitoshi、Agena Shinya、Tomita Hayato、Ariga Takuro、Ishikawa Kazuki、Takehara Shota、Maemoto Hitoshi、Murayama Sadayuki
    • Journal Title

      European Archives of Oto-Rhino-Laryngology

      Volume: 279 Issue: 6 Pages: 3105-3113

    • DOI

      10.1007/s00405-021-07121-9

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Presentation] 各領域研究の進歩1 頭頸部2023

    • Author(s)
      冨田 隼人
    • Organizer
      SAMI 2023
    • Related Report
      2023 Annual Research Report
    • Invited

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi