Investigation of multimodality diagnosis assistant system for breast cancer

• Project/Area Number: 17K09061
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Medical Physics and Radiological Technology
• Research Institution: Shiga University (2019); Gifu University (2017-2018)
• Principal Investigator: Muramatsu Chisako 滋賀大学, データサイエンス学部, 准教授 (80509422)
• Project Period (FY): 2017-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000); Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2017: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: breast cancer / computer aided diagnosis / image retrieval / multimodality imaging / mammography / breast ultrasound / 乳癌 / マンモグラフィ / 乳腺超音波 / 類似画像検索 / 画像診断支援 / 深層学習 / 乳腺腫瘤 / コンピュータ支援診断 / ディープラーニング / 全厨房超音波スキャナ / モデリング / 類似画像 / 鑑別診断 / 乳がん / 超音波 / 全乳房スキャン

Outline of Final Research Achievements

The purpose of this study was to develop a computerized system for assisting multimodality image diagnosis by collating image findings and abnormality locations on multimodality exams and retrieving reference images using multimodality information. For matching the locations of abnormalities, automatic detection of breast masses on automatic breast ultrasound volume scanner (ABVS) was investigated. Using deep leaning technique, relatively high detection rate was obtained, although improvement is needed for finding corresponding locations on a 3D model. For assisting differential diagnosis, reference image retrieval system was developed for mammograms and breast ultrasound images. High precision was obtained using multimodality information compared with those using single modality information, indicating the potential usefulness of the proposed study.

Academic Significance and Societal Importance of the Research Achievements

乳がんによる死亡率低下には早期発見が最も重要である．乳がんの診断には，マンモグラフィや超音波検査など複数の画像モダリティが使用される．また，乳房を自動的にスキャンする超音波自動ボリュームスキャナ（ABVS）の有用性も認識されている．しかし読影データの増加により医師の負担も増加している．本研究ではマルチモダリティ診断が効率的かつ正確に行われるように，画像診断支援システムの開発を試みた．本研究成果で得られたABVSにおける病変の自動検出システムは今後マンモグラフィとの照合システムの開発に役立てられる．また，マルチモダリティ情報を用いた参照画像検索システムは，鑑別診断に有用であることが示唆された．

Research Products

• [Journal Article] Improving breast mass classification by shared data with domain transformation using a generative adversarial network (2020)
  • Author(s): Muramatsu Chisako、Nishio Mizuho、Goto Takuma、Oiwa Mikinao、Morita Takako、Yakami Masahiro、Kubo Takeshi、Togashi Kaori、Fujita Hiroshi
  • Journal Title: Computers in Biology and Medicine Volume: 119 Pages: 103698-103698
  • DOI: 10.1016/j.compbiomed.2020.103698
  • Peer Reviewed
• [Journal Article] Breast mass image retrieval based on multimodality similarity estimation (2020)
  • Author(s): Muramatsu C, Oiwa M, Kawasaki T, Fujita H
  • Journal Title: Proceedings of SPIE, IWBI2020 Volume: 11513 Pages: 1151326-1151326
  • DOI: 10.1117/12.2564048
  • Peer Reviewed
• [Journal Article] Image retrieval of breast masses on ultrasound images (2019)
  • Author(s): Muramatsu C, Higuchi S, Morita T, Oiwa M, Kawasaki T, Fujita H
  • Journal Title: Proc SPIE Medical Imaging Volume: 10955 Pages: 43-43
  • DOI: 10.1117/12.2513663
  • Peer Reviewed
• [Journal Article] Retrieval of reference images of breast masses on mammograms by similarity space modeling (2018)
  • Author(s): Muramatsu C, Higuchi S, Morita T, Oiwa M, Kawasaki T, Fujita H
  • Journal Title: Proc SPIE, International Workshop on Breast Imaging Volume: 10718 Pages: 81-81
  • DOI: 10.1117/12.2318717
  • Peer Reviewed
• [Journal Article] Overview of subjective similarity of images for content-based medical image retrieval (2018)
  • Author(s): Muramatsu C
  • Journal Title: Radiological Physics and Technology Volume: 11 Issue: 2 Pages: 109-124
  • DOI: 10.1007/s12194-018-0461-6
• [Journal Article] Similarity estimation for reference image retrieval in mammograms using convolutional neural network (2018)
  • Author(s): Chisako Muramatsu, Shunichi Higuchi, Takako Morita, Mikinao Oiwa, Hiroshi Fujita
  • Journal Title: Proceedings of SPIE Medical Imaging Volume: 10575 Pages: 101-101
  • DOI: 10.1117/12.2293979
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] 乳房超音波画像診断支援のための画像解析技術の現状と将来 (2017)
  • Author(s): 村松千左子，藤田広志
  • Journal Title: 超音波TECHNO Volume: 29 Pages: 4-9
• [Presentation] Multimodality breast mass classification using CNN-based similarity estimation (2020)
  • Author(s): Muramatsu C, Oiwa M, Kawasaki T, Morita T, Fujita H
  • Organizer: International Workshop on Advance Image Technology
  • Int'l Joint Research
• [Presentation] Image retrieval of breast masses on ultrasound images (2019)
  • Author(s): Muramatsu C, Higuchi S, Morita T, Oiwa M, Kawasaki T, Fujita H
  • Organizer: SPIE Medical Imaging
  • Int'l Joint Research
• [Presentation] 深層学習を利用したマンモグラムと乳腺超音波画像の腫瘤陰影の類似画像検索の検討 (2019)
  • Author(s): 樋口峻一，村松千左子，大岩幹直，森田孝子，藤田広志
  • Organizer: 医用画像情報学会
• [Presentation] Retrieval of reference images of breast masses on mammograms by similarity space modeling (2018)
  • Author(s): Muramatsu C, Higuchi S, Morita T, Oiwa M, Kawasaki T, Fujita H
  • Organizer: International Workshop on Breast Imaging
  • Int'l Joint Research
• [Presentation] Improving computer aided classification of breast lesions on mammograms using simulated masses by generative adversarial networks (2018)
  • Author(s): Muramatsu C, Morita T, Oiwa M, Fujita H
  • Organizer: Radiological Society of North America
  • Int'l Joint Research
• [Presentation] Similarity estimation for reference image retrieval in mammograms using convolutional neural network (2018)
  • Author(s): Chisako Muramatsu, Shunichi Higuchi, Takako Morita, Mikinao Oiwa, Hiroshi Fujita
  • Organizer: SPIE Medical Imaging
  • Int'l Joint Research
• [Presentation] Mass detection on automated breast ultrasound volume scans using convolutional neural network (2018)
  • Author(s): Chisako Muramatsu, Yuya Hiramatsu, Hironobu Kobayashi, Hiroshi Fujita
  • Organizer: International Workshop on Advanced Image Technology
  • Int'l Joint Research
• [Presentation] 深層学習を利用した全乳房超音波画像における腫瘤検出手法の検討 (2017)
  • Author(s): 平松祐哉，村松千左子，小林宏暢，原武史，藤田広志
  • Organizer: 日本医用画像工学会
• [Presentation] Deep Learningによる腫瘤の類似画像決定法の検討 (2017)
  • Author(s): 樋口峻市，村松千左子，原武史，藤田広志
  • Organizer: 日本医用画像工学会
• [Presentation] 深層学習を利用した全乳房超音波画像における腫瘤検出手法の検討 (2017)
  • Author(s): 平松祐哉，村松千左子，小林宏暢，原武史，藤田広志
  • Organizer: 日本生体医工学会東海支部大会