Greylag goose optimization and multilayer perceptron for enhancing lung cancer classification

Abstract

Lung cancer is an important global health problem, and it is defined by abnormal growth of the cells in the tissues of the lung, mostly leading to significant morbidity and mortality. Its timely identification and correct staging are very important for proper therapy and prognosis. Different computational methods have been used to enhance the precision of lung cancer classification, among which optimization algorithms such as Greylag Goose Optimization (GGO) are employed. These algorithms have the purpose of improving the performance of machine learning models that are presented with a large amount of complex data, selecting the most important features. As per lung cancer classification, data preparation is one of the most important steps, which contains the operations of scaling, normalization, and handling gap factor to ensure reasonable and reliable input data. In this domain, the use of GGO includes refining feature selection, which mainly focuses on enhancing the classification accuracy compared to other binary format optimization algorithms, like bSC, bMVO, bPSO, bWOA, bGWO, and bFOA. The efficiency of the bGGO algorithm in choosing the optimal features for improved classification accuracy is an indicator of the possible application of this method in the field of lung cancer diagnosis. The GGO achieved the highest accuracy with MLP model performance at 98.4%. The feature selection and classification results were assessed using statistical analysis, which utilized the Wilcoxon signed-rank test and ANOVA. The results were also accompanied by a set of graphical illustrations that ensured the adequacy and efficiency of the adopted hybrid method (GGO + MLP).

Keywords: Classification; Feature selection; GGO; Lung cancer; MLP; Optimization.

Fig. 1

Comparison between healthy lung and cancer lung.

Algorithm 1: GGO algorithm.

Algorithm 2: bGGO algorithm.

Fig. 2

The proposed lung cancer classification framework.

Fig. 3

Scatter plot for each feature in the dataset.

Fig. 4

A correlation matrix between features in the dataset.

Fig. 5

The Average Error of the Results Acquired using bGGO, the Proposed Feature Selection Technique.

Fig. 6

Analysis plots of the obtained outcomes based on bGGO, the proposed feature selection technique.

Fig. 7

Assessing the accuracy of the GGO + MLP approach and optimization algorithms using the MLP model, considering the objective function.

Fig. 8

Histograms of the accuracy results achieved by GGO + MLP approach as well as alternative combinations of optimization techniques with MLP models.

Fig. 9

Analysis plots of the obtained results using the proposed GGO + MLP approach.

Fig. 10

KDE plot of accuracy of reference models results.

Fig. 11

Box plot with swarm overlay: accuracy by reference models.

Fig. 12

Pairplot with Regression Lines for Reference Models Results.

Fig. 13

Regression Plot: Accuracy vs. F-Score for Reference Models Results.

Fig. 14

KDE plot of accuracy of optimization results.

Fig. 15

Box plot with swarm overlay: accuracy by optimization models.

Fig. 16

Performance of the Reference models using Accuracy, Sensitivity (TRP), Specificity(TNP) by Model, Pvalue (PPV), Pvalue (NPV), FScore by Optimization Models.