PROBLEM TO BE SOLVED: To provide a medical image processing apparatus capable of arranging landmarks by using relevance between the landmarks.SOLUTION: A medical image processing apparatus comprises: a storage section which stores average shape data having a first marker point and a constraint condition and medical image data an extraction decision section which decides a likelihood distribution in a region including a second marker point extracted from the medical image data a positioning section which performs positioning of the average shape data on the medical image data an outlier removal section which removes an outlier from the second marker point on the basis of the first and second marker points and a threshold a connected likelihood calculation section which calculates connected likelihoods obtained by connecting a plurality of likelihoods corresponding to the position of the first marker point for every deformation of the average shape on the basis of the position of the first marker point moved with the deformation of the average shape in accordance with the constraint condition and the likelihood distribution and an anatomical marker point decision section which decides an anatomical marker point in the medical image data on the basis of the deformation corresponding to the maximum connected likelihood among the connected likelihoods, the second marker point from which the outlier is removed, and the first marker point.COPYRIGHT: (C)2015,JPO&INPIT【課題】ランドマーク間の関連性を用いてランドマークを配置可能な医用画像処理装置の提供。【解決手段】本実施形態の医用画像処理装置は、第1標識点と拘束条件とを有する平均形状データと医用画像データとを記憶する記憶部と、医用画像データから抽出された第2標識点を含む領域内の尤度分布を決定する抽出決定部と、平均形状データを医用画像データに位置合わせする位置合わせ部と、第1、第2標識点と閾値に基づいて第2標識点から外れ値を除去する外れ値除去部と、拘束条件に従った平均形状の変形により移動された第1標識点の位置と尤度分布に基づいて、位置に対応する複数の尤度を結合した結合尤度を平均形状の変形毎に計算する結合尤度計算部と、結合尤度のうち最大の結合尤度に対応する変形と、外れ値を除去した第2標識点と第1標識点とに基づいて、医用画像データにおける解剖学的標識点を決定する解剖学的標識点決定部とを有する。【選択図】図11
