球面調和関数を用いた肝臓統計形状モデル構築と支援診断への応用


研究内容(右のマーククリックで内容を展開)

背景・目的

高精細医用画像から構築された人体臓器統計形状モデルは各臓器の個体差バリエーションを記述したモデルであり,診断や治療支援への応用が期待できる.各臓器の3次元形状表現の有効な手法として球面調和関数を用いた臓器形状ベクトル表現が挙げられるが, 臓器間における球面調和関数の次元数は異なるため, 各臓器間の統計形状モデル構築に対する次元数特定やその差異に対する統計形状モデル性能評価が確立されていない. 故に球面調和関数による臓器統計形状モデルの支援診断へ応用は未着手である.本研究では,球面調和関数を用いた信頼性の高い統計形状モデル構築, 性能評価を行った.

In medical image analysis, the three-dimensional (3- D) shape representation and modeling of anatomic structures using only a few parameters is an important issue, and can be applied to computer assisted diagnosis, surgical simulations, visualization, and many other medical applications. In this paper, we propose an efficient shape representation method using spher- ical harmonic functions (SPHARM) for 3D anatomical structure such as the liver. We show that the 3D shape of the liver can be reconstructed by a few coefficients of the SPHARM. We also propose to use SPHAM based shape representation for statistical shape modeling. Since the dimension of SPHARM based shape representation vector is much lower than the conventional shape representation using coordinates of surface points, our proposed method can be used for small number of training samples and enhance the computation cost.


球面調和関数

  • 更新中


球面調和関数による臓器形状の表現

  • 更新中


発表論文

  1. Yen-Wei Chen, Shinya Kohara, Jie Luo, Tomoko Tateyama, Xian-hua Han, Akira Furukawa, Shuzo Kanasaki,“Statistical Liver Atlas for Computer-aided Diagnosis of Chronic Liver Disease: Progress Overview FY2010, ”Proc of The 2nd International Symposium on Computational Anatomy, pp.87-90, Fukuoka, Japan, March, 2012.

  2. Shuzo Kanasaki, Tomoko Tateyama, Akira Furukawa, Yen-wei Chen,et al(他6 名), ”Diagnosis of liver cirrhosis with the use of multi-detector row computed tomography (MDCT) morphological approach and quantitative approach using statistical geometric hepatic model”, Proc of the 6th International Conference on Computer Sciences and Convergence Information Technology ICCIT2011), Jeju, Korea, Dec 2011(In press).

  3. Daisuke Kitabayashi, Guifang Duan, Tomoko Tateyama, Ryosuke Kimura, and Yen-Wei Chen, “Facial Morphology Analysis for a Genetic Association Study A scheme of 3D face shape alignment,” Proc. of 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT2011), Jeju Island, Korea, pp.870-873 (2011.11.29-12.1).

  4. Shinya Kohara, Tomoko Tateyama, Akira Furukawa, Shuzo Kanasaki, Yen-Wei Chen(他3名),"Preliminary Study on Statistical Shape Model Applied to Diagnosis of Liver Cirrhosis", Proc of 18th IEEE International Conference on Image rocessing (ICIP2011), pp2978-2981, Brussels Belguim, Sep.2011.

  5. Yen-Wei Chen, Tomoko Tateyama, Shinya Kohara, Akira Furukawa, Shuzo Kanasaki,“Statistical Liver Atlas for Computer-aided Diagnosis of Chronic Liver Disease: Progress Overview FY2010, ”Proc of The 2nd International Symposium on Computational Anatomy, Nagoya, Japan, March, 2011.

  6. Yen-Wei Chen, Tomoko Tateyama, Akira Furukawa(他3名),“Statistical Atlases of Human Anatomy and Computer Assisted Diagnostic System,” Proc of SEDM2010, pp700-705, Chengdu, China 2010,5.

  7. Shinya Kohara, Tomoko Tateyama, Amir H Foruzan, Akira Furukawa, Shuzo Kanasaki, Makoto Wakamiya and Yen-Wei Chen, “Application of Statistical Shape Model toDiagnosis of Liver Disease,” Proc of SEDM2010, pp680-683, Chengdu, China, 2010,5.

関連プロジェクト

  • 3次元空間上における任意の三次元幾何学物体に対し, その大きさや形状, 形態 変化のバリエーションを記述したモデル.

  • 統計形状モデルは基本的に, 主成分分析法(Principal Component Analysis:PCA), 独立成分分析法(Independent Component Analysis), Sparse Coding などの機械学習を介して作成される.