Automated identification of the heart wall throughout the entire cardiac cycle using optimal cardiac phase for extracted features

Hiroki Takahashi, Hideyuki Hasegawa, Hiroshi Kanai

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

In most methods for evaluation of cardiac function based on echocardiography, the heart wall is currently identified manually by an operator. However, this task is very time-consuming and suffers from inter- and intraobserver variability. The present paper proposes a method that uses multiple features of ultrasonic echo signals for automated identification of the heart wall region throughout an entire cardiac cycle. In addition, the optimal cardiac phase to select a frame of interest, i.e., the frame for the initiation of tracking, was determined. The heart wall region at the frame of interest in this cardiac phase was identified by the expectation-maximization (EM) algorithm, and heart wall regions in the following frames were identified by tracking each point classified in the initial frame as the heart wall region using the phased tracking method. The results for two subjects indicate the feasibility of the proposed method in the longitudinal axis view of the heart.

Original languageEnglish
Article number07HF16
JournalJapanese journal of applied physics
Volume50
Issue number7 PART 2
DOIs
Publication statusPublished - 2011 Jul 1

ASJC Scopus subject areas

  • Engineering(all)
  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'Automated identification of the heart wall throughout the entire cardiac cycle using optimal cardiac phase for extracted features'. Together they form a unique fingerprint.

Cite this