Semi-automatic algorithm for construction of the left ventricular area variation curve over a complete cardiac cycle

Table 2 Quantitative comparison between the proposed approach and alternative methods from the literature.

	image quality	number of images	RMSd	CCC	PE (%)	ES (%)
Proposed method	high	20	2.14 ± 0.367	0.985 ± 0.011	2.49 ± 2.46	9.62 ± 7.9
	average	23	2.53 ± 0.398	0.901 ± 0.024	7.56 ± 2.51	16.20 ± 8.23
	low	17	2.99 ± 0.695	0.734 ± 0.101	15.10 ± 7.98	18.59 ± 7.02
Klingler Jr et al. [2]	acceptable^a	121^b		0.93
Choy and Jin [3]	high	10	1.7 ± 0.7
	average	8	3.5 ± 1.0
Lacerda et al. [8]	high	7			10.65 ± 2.47	18.51 ± 5.06
	average	5			18.06 ± 7.49	24.62 ± 7.89
Amorim et al. [10]	high	8		0.917		10.79 ± 2.95

^a canine models;
^b composite images, each obtained by averaging over ten cardiac cycles.
The mean (± standard deviation) results from each evaluation metric are shown for different image segmentation methods and different degrees of image quality.