Automatic detection of colorectal cancer from images using active learning

• Project/Area Number: 25330337
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Life / Health / Medical informatics
• Research Institution: Hiroshima University
• Principal Investigator: Raytchev Bisser 広島大学, 工学(系)研究科(研究院), 助教 (00531922)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Project Status: Completed (Fiscal Year 2015)
• Budget Amount: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000); Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2013: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: 大腸癌 / 癌の自動診断システム / ＮＢＩ画像 / Active Learning / Ensemble methods / NBI画像 / Active learning

Outline of Final Research Achievements

An automatic diagnosis method for colorectal cancer from Narrow Band Imaging (NBI) has been developed, based on local context features and randomized decision forests. The local context features are based on a texton map from which texture and local context-based information is extracted from the surrounding area centered on each pixel. The features are very high-dimensional (infinite in principle) and therefore very discriminative, which combined with their huge number and the ability of random forests to handle efficiently such data without over-fitting enables us to achieve very good accuracy from a very small number of training images. Additionally, by providing local pixel-level classification the resulting method is much more general and does not depend on the concrete configuration of patterns available in the training images. The method operates locally and therefore is much better suited for video data also, which makes it applicable to more realistic diagnostic scenarios.

Research Products

• [Journal Article] Automatic Detection of Good/Bad Colonies of iPS Cells Using Local Features (2015)
  • Author(s): A. Masuda, B. Raytchev, T. Kurita, T. Imamura, M. Suzuki, T. Tamaki and K. Kaneda
  • Journal Title: Lecture Notes in Computer Science (LNCS) Volume: 9352 Pages: 153-160
  • DOI: 10.1007/978-3-319-24888-2_19
  • ISBN: 9783319248875, 9783319248882
  • Peer Reviewed / Acknowledgement Compliant
• [Presentation] 局所特徴量を用いたiPS細胞の分化・未分化検出 (2015)
  • Author(s): 増田 淳基, Bisser Raytchev, 栗田 多喜夫, 今村 享, 鈴木 理, 玉木 徹, 金田 和文
  • Organizer: 第18回画像の認識・理解シンポジウム(MIRU2015)
  • Place of Presentation: ホテル阪急エキスポパーク, 大阪
  • Year and Date: 2015-07-28
• [Presentation] Image Sequence Recognition with Active Learning Using Uncertainty Sampling (2013)
  • Author(s): M. Minakawa, B. Raytchev, T. Tamaki, K. Kaneda
  • Organizer: IEEE International Joint Conference on Neural Networks (IJCNN2013)
  • Place of Presentation: Dallas, USA
• [Presentation] 画像列を用いた物体認識へのActive Learningの適用 (2013)
  • Author(s): 皆川雅俊, Bisser Raytchev, 玉木徹, 金田和文
  • Organizer: 第19回画像センシングシンポジウム SSII2013
  • Place of Presentation: 横浜