Ensemble Learning Framework with GLCM Texture Extraction for Early Detection of Lung Cancer on CT Images

Table 8

Paper name	Lung cancer detection using image segmentation by means of various evolutionary algorithms [34]	Lung cancer detection using image processing and classification techniques
Objective	To find a fast image segmentation algorithm for medical images to reduce the time it takes doctors to evaluate computer tomography (CT) scan images.	(i) Classification of lung cancer using extracted Haralick features; (ii)Comparing the accuracy of various image segmentation algorithms
Features used	No features used.	Haralick features like contrast, energy, entropy, homogeneity, etc.
Segmentation also used	k-median, -means, particle swarm optimization, guaranteed convergence particle swarm optimization. Inertia-weighted particle swarm optimization, guaranteed convergence particle swarm optimization.	k-means, fuzzy c-means
Results	The highest accuracy is achieved in guaranteed convergence particle swarm optimization, i.e., 95.81%, and the average accuracy is above 90%.	The highest accuracy is achieved in fuzzy c-means, i.e., 98.78%, and the average accuracy is above 95%.