統計的形状特徴を考慮可能な新しいブースティングアルゴリズムの提案と臓器抽出への応用  [in Japanese] Proposal of a Novel Boosting Algorithm Regularized by a Statistical Shape Feature and Its Application to Organ Segmentation  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

アンサンブル学習などの機械学習に基づく臓器セグメンテーションでは,構築された分類器による判定が,画素ごとや局所領域ごとに独立していることが多く,抽出図形の形状が不自然になることがしばしばある.本論文では,臓器形状の統計的特徴を考慮しながらセグメンテーション処理を構築可能な,新しいアンサンブル学習アルゴリズムを提案する.具体的には,人体臓器の統計モデルを用いて抽出図形の形状を評価する新しい損失項を提案し,従来の誤り損失項と組み合わせた損失全体を最小化する学習アルゴリズムを示す.本論文ではまず,人工画像を用いて提案手法の原理検証を行い,その後,80症例の3次元CT像を用いた脾臓のセグメンテーション結果を示し,提案手法の性能を評価する.その結果,提案手法によって,従来の誤りのみを損失とする場合に比べて,不自然な形状の抽出結果が少なくなり,性能が統計的に有意に向上することを示す.

Conventional machine learning-based segmentation (e.g., ensemble learning) suffers from the problem of unnatural shapes of the extracted figures because decision-making by the constructed classifier is carried out voxel by voxel or local region by local region independently. In this paper, we propose an ensemble learning algorithm that constructs a segmentation process based on the statistical shape feature of an organ. We describe a novel loss function for evaluating the shape of an extracted figure using a statistical shape model of the organ and an algorithm to minimize the loss function which combines conventional error loss with proposed loss. The results of experiments using an artificial image are presented to confirm the basic performance of the algorithm. In addition, the results of experiments involving spleen segmentation using 80 clinical CT volumes are presented to validate the clinical usefulness of the algorithm. Based on these results, it is concluded that the proposed algorithm reduces unnatural shapes of the extracted organs and provides significantly superior segmentation performance as compared to conventional ensemble learning-based segmentation.

Journal

  • Medical Imaging Technology

    Medical Imaging Technology 31(2), 121-131, 2013

    The Japanese Society of Medical Imaging Technology

Codes

  • NII Article ID (NAID)
    130003374500
  • Text Lang
    JPN
  • ISSN
    0288-450X
  • Data Source
    J-STAGE 
Page Top