| Project/Area Number |
16K00261
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Fukui University of Technology (2018)
Center for Novel Science Initatives, National Institutes of Natural Sciences (2016-2017) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | Mathematical morphology / セグメンテーション / 形態情報解析 / mathematical morphology / 画像 / 情報工学 / 生体生命情報学 |
|---|
| Outline of Final Research Achievements |
In this study, to establish a technical basis for quantitative life science research, a highly accurate, versatile, and robust automatic cell region segmentation method has been developed. Five research subjects were considered: (1) an initial method to divide the cell contour region; (2) a method to remove noise and artifacts; (3) a method to combine discontinuous contours; (4) a method to remove the structure close to contour; and (5) implementation of a morphological analysis of cells based on the developed methods. The comparison of cell segmentation result and cell recognition result obtained using the proposed method and visual observation, respectively, revealed that the proposed method realized 98% accuracy.
|
| Academic Significance and Societal Importance of the Research Achievements |
生物医学画像における解析領域のセグメンテーション(背景からその領域を切り出すこと)は，対象の特徴を定量化するために必須の処理である．また，生命科学研究分野においては，多種・大量の画像データを取り扱う必要があることから，その処理の自動化が求められている．しかし，生物医学画像の取り扱いの困難さから，いまだ，精度の高いセグメンテーション手法は確立していなかった．そこで，生物医学画像の性質を十分に考慮し，その対応に特化した，rotational morphological processingに基づく独自の画像処理手法を構築し，高い精度をもつ自動セグメンテーション手法を開発した．
|
