Why the study?
The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function.
Absolute Event Rate: 80.4% vs 48.8%
A guideline-based machine learning approach significantly improves the speed and accuracy of automatic standard plane extraction in 3-D echocardiography.
May streamline 3-D echocardiography workflows; extends marginal space learning by integrating guidelines into machine learning.
The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function. A guideline-based learning method for efficient and accurate standard plane extraction is proposed. A cardiac ultrasound guideline determines appropriate operation steps for clinical examinations. The idea of guideline-based learning is incorporating machine learning approaches into each stage of the guideline. First, Hough forest with hierarchical search is applied for 3-D feature point detection. Second, initial planes are determined using anatomical regularities according to the guideline. Finally, a regression forest integrated with constraints of plane regularities is applied for refining each plane. The proposed method was evaluated on a 3-D cardiac ultrasound dataset and a synthetic dataset. Compared with other plane extraction methods, it demonstrated an improved accuracy with a significantly faster running time of 0.8 svolume. Furthermore, it showed the proposed method was robust for a range abnormalities and image qualities, which would be seen in clinical practice.
No takes yet. Share an insight, caveat, or question.
Zhu et al. (2018) studied Echocardiography (n=15). Guideline-based machine learning method vs. Marginal space learning (MSL) was evaluated on Success rate of standard plane extraction (angle error < 10 deg and distance error < 5 mm). The proposed guideline-based machine learning method achieved an 80.4% success rate for standard plane extraction with a running time of 0.8 seconds per volume, outperforming marginal space learning.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: