Water Cycle Bat Algorithm and Dictionary-Based Deformable Model for Lung Tumor Segmentation

Table 1

Performance comparison of the proposed method with the existing techniques.

Cluster size	Evaluation metrics	CNN [3]	[14]	Dictionary-based method [21]	Proposed method
4	Average segmentation accuracy	0.8875	0.8909	0.8934	0.9257
	Average Dice coefficient	0.7667	0.7754	0.7963	0.8213
	Average Jaccard coefficient	0.7855	0.7911	0.7997	0.8244
5	Average segmentation accuracy	0.8424	0.8591	0.8791	0.9257
	Average Dice coefficient	0.7645	0.7899	0.8085	0.8282
	Average Jaccard coefficient	0.7579	0.7844	0.7991	0.8270