Automated diagnosis for colonoscopy using deep learning

• Project/Area Number: 17K15971
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Gastroenterology
• Research Institution: Showa University
• Principal Investigator: MISAWA MASASHI 昭和大学, 医学部, 講師 (90459206)
• Research Collaborator: Mori Kensaku ; Itoh Hayato ; Oda Masahiro
• Project Period (FY): 2017-04-01 – 2019-03-31
• Project Status: Completed (Fiscal Year 2018)
• Budget Amount: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000); Fiscal Year 2017: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
• Keywords: 人工知能 / 内視鏡 / 大腸癌 / 大腸内視鏡 / ディープラーニング / 深層学習 / 拡大内視鏡 / コンピュータ診断支援 / 超拡大内視鏡

Outline of Final Research Achievements

The aim of this research was to develop computer-aided detection(CADe) and computer-aided diagnosis(CADx) system for colonoscopy and evaluate its diagnostic performance.1.We developed CADx system based on ultra-magnifying endoscopy for differentiating colonic neoplasms and non-neoplasms. Support vector machine which is a traditional machine learning method, was applied for the CADx and achieved 97.4% accuracy. 2.The CADe system that works on conventional endoscopy, was developed using 3-dimensional convolution neural network. We prepared fully annotated 1.8 million frame of colonoscopy videos for machine learning.The CADe system achieved 90% sensitivity for colorectal lesion based on video based analysis.(Misawa M, et al. Gastroenterology 2018)

Academic Significance and Societal Importance of the Research Achievements

大腸内視鏡におけるリアルタイム病変検出・診断は、近年重要視され高精度化が要求されている。これは病変の見落としを防ぐことで、大腸癌罹患を予防し、加えて治療不要な非腫瘍性ポリープを確実に診断することで、かかる治療・病理検査を省略できるためである。本研究では大腸内視鏡における、病変の発見、病変の診断を人工知能で支援し、どのようなレベルの医師であっっても均てん化した医療が提供できる可能性を示した。これにより、本邦がん罹患数１位のがん種である大腸がんを抑制することが期待される。

Research Products

• [Journal Article] Artificial Intelligence-Assisted Polyp Detection for Colonoscopy: Initial Experience. (2019)
  • Author(s): Misawa M, Kudo SE, Mori Y, Cho T, Kataoka S, Yamauchi A, Ogawa Y, Maeda Y, Takeda K, Ichimasa K, Nakamura H, Yagawa Y, Toyoshima N, Ogata N, Kudo T, Hisayuki T, Hayashi T, Wakamura K, Baba T, Ishida F, Itoh H, Roth H, Oda M, Mori K.
  • Journal Title: Gastroenterology Volume: epub ahead of print Issue: 8 Pages: 2027-2029
  • DOI: 10.1053/j.gastro.2018.04.003
  • Peer Reviewed / Open Access
• [Journal Article] Fully automated diagnostic system with artificial intelligence using endocytoscopy to identify the presence of histologic inflammation associated with ulcerative colitis (with video). (2019)
  • Author(s): Maeda Y, Kudo SE, Mori Y, Misawa M, Ogata N, Sasanuma S, Wakamura K, Oda M, Mori K, Ohtsuka K.
  • Journal Title: Gastrointest Endosc Volume: 89 Issue: 2 Pages: 408-415
  • DOI: 10.1016/j.gie.2018.09.024
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Simultaneous detection and characterization of diminutive polyps with the use of artificial intelligence during colonoscopy. (2019)
  • Author(s): Mori Y, Kudo SE, Misawa M, Mori K.
  • Journal Title: VideoGIE Volume: 4 Issue: 1 Pages: 7-10
  • DOI: 10.1016/j.vgie.2018.10.006
  • Peer Reviewed / Open Access
• [Journal Article] Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study (2018)
  • Author(s): Mori Y, Kudo SE, Misawa M, Saito Y, Ikematsu H, Hotta K, Ohtsuka K, Urushibara F, Kataoka S, Ogawa Y, Maeda Y, Takeda K, Nakamura H, Ichimasa K, Kudo T, Hayashi T, Wakamura K, Ishida F, Inoue H, Itoh H, Oda M, Mori K
  • Journal Title: Ann Intern Med Volume: 169 Issue: 6 Pages: 357-366
  • DOI: 10.7326/m18-0249
  • Peer Reviewed / Open Access
• [Journal Article] Artificial intelligence may help in predicting the need for additional surgery after endoscopic resection of T1 colorectal cancer (2018)
  • Author(s): Katsuro Ichimasa, Shin-ei Kudo, Yuichi Mori, Masashi Misawa, Shingo Matsudaira, Yuta Kouyama, Toshiyuki Baba, Eiji Hidaka, Kunihiko Wakamura, Takemasa Hayashi, Toyoki Kudo, Tomoyuki Ishigaki, Yusuke Yagawa, Hiroki Nakamura, Kenichi Takeda, Amyn Haji, Shigeharu Hamatani, Kensaku Mori, Fumio Ishida, Hideyuki Miyachi
  • Journal Title: Endoscopy Volume: 50 Issue: 03 Pages: 230-240
  • DOI: 10.1055/s-0043-122385
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Accuracy of diagnosing invasive colorectal cancer using computer-aided endocytoscopy (2017)
  • Author(s): Kenichi Takeda, Shin-ei Kudo, Yuichi Mori, Masashi Misawa, Toyoki Kudo, Kunihiko Wakamura, Atsushi Katagiri, Toshiyuki Baba, Eiji Hidaka, Fumio Ishida, Haruhiro Inoue, Masahiro Oda, Kensaku Mori
  • Journal Title: Endoscopy Volume: 49 Issue: 08 Pages: 799-802
  • DOI: 10.1055/s-0043-105486
  • Peer Reviewed
• [Journal Article] Computer-aided diagnosis for colonoscopy (2017)
  • Author(s): Yuichi Mori, Shin-ei Kudo, Tyler M Berzin, Masashi Misawa, Kenichi Takeda
  • Journal Title: Endoscopy Volume: 49 Issue: 08 Pages: 813-819
  • DOI: 10.1055/s-0043-109430
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Use of endocytoscopy for identification of sessile serrated adenoma/polyps and hyperplastic polyps by quantitative image analysis of the luminal areas (2017)
  • Author(s): Yushi Ogawa, Shin-ei Kudo, Yuichi Mori, Nobunao Ikehara, Yasuharu Maeda, Kunihiko Wakamura, Masashi Misawa, Toyoki Kudo, Takemasa Hayashi, Hideyuki Miyachi, Atsushi Katagiri, Fumio Ishida, Haruhiro Inoue
  • Journal Title: Endoscopy international open Volume: 5 Issue: 08 Pages: E769-E774
  • DOI: 10.1055/s-0043-113562
  • Peer Reviewed / Open Access
• [Presentation] 人工知能に基づく大腸内視鏡のポリープ自動検出ソフトウェア (2018)
  • Author(s): 三澤将史
  • Organizer: 第95回日本消化器内視鏡学会総会
• [Presentation] Computer-aided detection for colonoscopy using deep learning. (2018)
  • Author(s): Masashi Misawa
  • Organizer: UEGW2018
  • Int'l Joint Research
• [Presentation] 人工知能に基づく大腸内視鏡のリアルタイム病変検出支援システム (2018)
  • Author(s): 三澤将史
  • Organizer: JDDW2018
• [Presentation] Automated polyp detection for colonoscopy using deep learning technology: preliminary results. (2017)
  • Author(s): Masashi Misawa, Shin-ei Kudo, Yuichi Mori, Kenichi Takeda, Ichimasa Katsuro, Yasuharu Maeda, Yushi Ogawa, Shinichi Kataoka, Hiroki Nakamura, Naoya Toyoshima, Toyoki Kudo, Takemasa Hayashi, Kunihiko Wakamura, Fumio Ishida, Holger Roth, Hiromasa Oda, Kensaku Mori
  • Organizer: United European Gastroenterology Week 2017
  • Int'l Joint Research
• [Presentation] 大腸内視鏡診断支援ソフトウェアの開発 (2017)
  • Author(s): 三澤将史
  • Organizer: 第9回 ヒューマンケアデバイス・システム技術分科会
  • Invited
• [Presentation] Computer-aided diagnosis for diminutive colorectal polyps by using endocytoscopy combined with NBI (2017)
  • Author(s): Masashi Misawa, Shin-ei Kudo, Yuichi Mori, Kenichi Takeda, Yasuharu Maeda, Shinichi Kataoka, Hiroki Nakamura, Toyoki Kudo, Kunihiko Wakamura, Takemasa Hayashi, Hideyuki Miyachi, Atsushi Katagiri, Toshiyuki Baba, Fumio Ishida, Haruhiro Inoue, Masahiro Oda, Kensaku Mori
  • Organizer: Digestive Disease Week 2017
  • Int'l Joint Research
• [Presentation] 大腸超拡大内視鏡の診断における工夫-AIによる自動診断- (2017)
  • Author(s): 三澤将史、工藤進英、森健策
  • Organizer: 第103回日本消化器病学会総会