A comparative study of nature-inspired metaheuristic algorithms using a three-phase hybrid approach for gene selection and classification in high-dimensional cancer datasets

BIMSSA: enhancing cancer prediction with salp swarm optimization and ensemble machine learning approaches

Background

Cancer rates are rising rapidly, causing global mortality. According to the World Health Organization (WHO), 9.9 million people died from cancer in 2020. Machine learning (ML) helps identify cancer early, reducing deaths. An ML-based cancer diagnostic model can use the patient's genetic information, such as microarray data. Microarray data are high dimensional, which can degrade the performance of the ML-based models. For this, feature selection becomes essential.

Methods

Swarm Optimization Algorithm (SSA), Improved Maximum Relevance and Minimum Redundancy (IMRMR), and Boruta form the basis of this work's ML-based model BIMSSA. The BIMSSA model implements a pipelined feature selection method to effectively handle high-dimensional microarray data. Initially, Boruta and IMRMR were applied to extract relevant gene expression aspects. Then, SSA was implemented to optimize feature size. To optimize feature space, five separate machine learning classifiers, Support Vector Machine (SVM), Random Forest (RF), Extreme Learning Machine (ELM), AdaBoost, and XGBoost, were applied as the base learners. Then, majority voting was used to build an ensemble of the top three algorithms. The ensemble ML-based model BIMSSA was evaluated using microarray data from four different cancer types: Adult acute lymphoblastic leukemia and Acute myelogenous leukemia (ALL-AML), Lymphoma, Mixed-lineage leukemia (MLL), and Small round blue cell tumors (SRBCT).

Results

In terms of accuracy, the proposed BIMSSA (Boruta + IMRMR + SSA) achieved 96.7% for ALL-AML, 96.2% for Lymphoma, 95.1% for MLL, and 97.1% for the SRBCT cancer datasets, according to the empirical evaluations.

Conclusion

The results show that the proposed approach can accurately predict different forms of cancer, which is useful for both physicians and researchers.

Ensemble Classification Model With CFS-IGWO-Based Feature Selection for Cancer Detection Using Microarray Data

Cancer is the top cause of death worldwide, and machine learning (ML) has made an indelible mark on the field of early cancer detection, thereby lowering the death toll. ML-based model for cancer diagnosis is done using two forms of data: gene expression data and microarray data. The data on gene expression levels includes many dimensions. When dealing with data with a high dimension, the efficiency of an ML-based model is decreased. Microarray data is distinguished by its high dimensionality with a greater number of features and a smaller sample size. In this work, two ensemble techniques are proposed using majority voting technique and weighted average technique. Correlation feature selection (CFS) is used for feature selection, and improved grey wolf optimizer (IGWO) is used for feature optimization. Support vector machines (SVMs), multilayer perceptron (MLP) classification, logistic regression (LR), decision tree (DT), adaptive boosting (AdaBoost) classifier, extreme learning machines (ELMs), and K-nearest neighbor (KNN) are used as classifiers. The results of each distinct base learner were then combined using weighted average and majority voting ensemble methods. Accuracy (ACC), specificity (SPE), sensitivity (SEN), precision (PRE), Matthews correlation coefficient (MCC), and F1-score (F1-S) are used to assess the performance. Our result shows that majority voting achieves better performance than the weighted average ensemble technique.

Hybrid whale algorithm with evolutionary strategies and filtering for high-dimensional optimization: Application to microarray cancer data

The standard whale algorithm is prone to suboptimal results and inefficiencies in high-dimensional search spaces. Therefore, examining the whale optimization algorithm components is critical. The computer-generated initial populations often exhibit an uneven distribution in the solution space, leading to low diversity. We propose a fusion of this algorithm with a discrete recombinant evolutionary strategy to enhance initialization diversity. We conduct simulation experiments and compare the proposed algorithm with the original WOA on thirteen benchmark test functions. Simulation experiments on unimodal or multimodal benchmarks verified the better performance of the proposed RESHWOA, such as accuracy, minimum mean, and low standard deviation rate. Furthermore, we performed two data reduction techniques, Bhattacharya distance and signal-to-noise ratio. Support Vector Machine (SVM) excels in dealing with high-dimensional datasets and numerical features. When users optimize the parameters, they can significantly improve the SVM's performance, even though it already works well with its default settings. We applied RESHWOA and WOA methods on six microarray cancer datasets to optimize the SVM parameters. The exhaustive examination and detailed results demonstrate that the new structure has addressed WOA's main shortcomings. We conclude that the proposed RESHWOA performed significantly better than the WOA.

Red piranha optimization (RPO): a natural inspired meta-heuristic algorithm for solving complex optimization problems

An optimization algorithm is a step-by-step procedure which aims to achieve an optimum value (maximum or minimum) of an objective function. Several natural inspired meta-heuristic algorithms have been inspired to solve complex optimization problems by utilizing the potential advantages of swarm intelligence. In this paper, a new nature-inspired optimization algorithm which mimics the social hunting behavior of Red Piranha is developed, which is called Red Piranha Optimization (RPO). Although the piranha fish is famous for its extreme ferocity and thirst for blood, it sets the best examples of cooperation and organized teamwork, especially in the case of hunting or saving their eggs. The proposed RPO is established through three sequential phases, namely; (i) searching for a prey, (ii) encircling the prey, and (iii) attacking the prey. A mathematical model is provided for each phase of the proposed algorithm. RPO has salient properties such as; (i) it is very simple and easy to implement, (ii) it has a perfect ability to bypass local optima, and (iii) it can be employed for solving complex optimization problems covering different disciplines. To ensure the efficiency of the proposed RPO, it has been applied in feature selection, which is one of the important steps in solving the classification problem. Hence, recent bio-inspired optimization algorithms as well as the proposed RPO have been employed for selecting the most important features for diagnosing Covid-19. Experimental results have proven the effectiveness of the proposed RPO as it outperforms the recent bio-inspired optimization techniques according to accuracy, execution time, micro average precision, micro average recall, macro average precision, macro average recall, and f-measure calculations.

InSiNet: a deep convolutional approach to skin cancer detection and segmentation

Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin cancer. In addition to traditional methods, method such as deep learning is frequently used to diagnose and classify the disease. Expert experience plays a major role in diagnosing skin cancer. Therefore, for more reliable results in the diagnosis of skin lesions, deep learning algorithms can help in the correct diagnosis. In this study, we propose InSiNet, a deep learning-based convolutional neural network to detect benign and malignant lesions. The performance of the method is tested on International Skin Imaging Collaboration HAM10000 images (ISIC 2018), ISIC 2019, and ISIC 2020, under the same conditions. The computation time and accuracy comparison analysis was performed between the proposed algorithm and other machine learning techniques (GoogleNet, DenseNet-201, ResNet152V2, EfficientNetB0, RBF-support vector machine, logistic regression, and random forest). The results show that the developed InSiNet architecture outperforms the other methods achieving an accuracy of 94.59%, 91.89%, and 90.54% in ISIC 2018, 2019, and 2020 datasets, respectively. Since the deep learning algorithms eliminate the human factor during diagnosis, they can give reliable results in addition to traditional methods.