ニューラルネット学習による医療内視鏡画像からの形状復元精度向上

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2016/04/01

タイトル(英語): Improving Accuracy for Shape Recovery from Medical Endoscope Image Using Neural Network Learning

著者名: 津田　誠也（中部大学大学院工学研究科），岩堀　祐之（中部大学大学院工学研究科），花井　勇樹（中部大学大学院工学研究科），春日井　邦夫（愛知医科大学消化器内科）

著者名(英語): Seiya Tsuda (Department of Computer Science, Chubu University), Yuji Iwahori (Department of Computer Science, Chubu University), Yuki Hanai (Department of Computer Science, Chubu University), Kunio Kasugai (Department of Gastroenterology, Aichi Medical University)

キーワード: 内視鏡画像，VBWモデル，RBF-NN，復元精度向上，反射係数，回帰分析　　Endoscope Image，VBW Model，RBF-NN，Improving Accuracy，Reflectance Parameter，Regression Analysis

要約(英語): The VBW (Vogel-Breuß-Weickert) model is proposed as a method to recover 3-D shape under point light source illumination and perspective projection. However, the VBW model recovers relative, not absolute, shape. Here, shape modification is introduced to recover the exact shape. Modification is applied to the output of the VBW model. First, a local brightest point is used to estimate the reflectance parameter from two images obtained with movement of the endoscope camera in depth. After the reflectance parameter is estimated, a sphere image is generated and used for Radial Basis Function Neural Network (RBF-NN) learning. The NN implements the shape modification. NN input is the gradient parameters produced by the VBW model for the generated sphere. NN output is the true gradient parameters for the true values of the generated sphere. Depth can then be recovered using the modified gradient parameters. Performance of the proposed approach is confirmed via computer simulation and real experiment. Although it is also possible modify the shape by using regression analysis instead of neural network, it was confirmed that NN performs better accuracy than regression analysis.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.4 （2016） 特集：最新の化合物半導体デバイスとその応用技術

本誌掲載ページ: 556-563 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/136/4/136_556/_article/-char/ja/