The challenges associated with conventional methods of COVID-19 detection have prompted the exploration of alternative approaches, including the analysis of lung X-ray images. This paper introduces a novel algorithm designed to identify abnormalities in X-ray images indicative of COVID-19 by combining the maximally stable extremal regions (MSER) method with metaheuristic algorithms. The MSER method is efficient and effective under various adverse conditions, utilizing symmetry as a key property to detect regions despite changes in scaling or lighting. However, calibrating the MSER method is challenging. Our approach transforms this calibration into an optimization task, employing metaheuristic algorithms such as Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), Firefly (FF), and Genetic Algorithms (GA) to find the optimal parameters for MSER. By automating the calibration process through metaheuristic optimization, we overcome the primary disadvantage of the MSER method. This innovative combination enables precise detection of abnormal regions characteristic of COVID-19 without the need for extensive datasets of labeled training images, unlike deep learning methods. Our methodology was rigorously tested across multiple databases, and the detection quality was evaluated using various indices. The experimental results demonstrate the robust capability of our algorithm to support healthcare professionals in accurately detecting COVID-19, highlighting its significant potential and effectiveness as a practical and efficient alternative for medical diagnostics and precise image analysis.

In this paper, we propose the implementation of a Fuzzy Inference System (FIS) for the systematic evaluation of exploration and exploitation capabilities in population-based Metaheuristic Optimization Algorithms (MOAs). Our approach involves an efficient feature extraction scheme applied through different stages of an algorithm’s search process, from which Dimension-Wise Diversity (DD), Average Distance to Global Best (DB), and Fitness Diversity (FD) are extracted and utilized as inputs for the proposed Mamdani-style FIS. These metrics feature zero additional objective function evaluations and are processed in real time by our proposed Mamdani-style inference system using symmetric triangular membership functions. Since the proposed FIS-based evaluation scheme relies on static membership boundaries and elementary min-max aggregation operators, constant time complexity is ensured, which contrasts with the expensive matrix operations that are frequently required in probabilistic models. To validate this framework, a comprehensive experimental design was performed. Such experiments involve testing with MOAs proposing unique and distinctive search strategies, including well-known examples such as Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Grey Wolf Optimizer (GWO), Differential Evolution (DE) and others. Our experiments also consider 14 benchmark functions (chosen by considering scalability and landscape variety) and three operational configurations (which consider varying numbers of decision variables, population size and iterations). Our results not only expose critical differences in exploration/exploitation capabilities among the compared strategies but also allow the visualization of underlying process characteristics, such as convergence speed and repeatability. Our results imply that the most successful MOAs are those which prioritize exploration by no more than 25% percent of the search process, while also manifesting a successful exchange from full exploration to full exploitation by the end of such process, with PSO and DE being among the most consistent examples.

This work presents an intelligent image-processing framework for automatically detecting and clas-sifying benign and malignant regions in breast tissue by integrating Contrast Limited Adaptive His-togram Equalization (CLAHE), Maximally Stable Extremal Regions (MSER), and metaheuristic opti-mization algorithms. Identifying tumor-related regions in breast images is challenging because their visual characteristics can vary considerably with tissue density, illumination conditions, surface tex-ture, intensity distribution, lesion severity, and image acquisition conditions. These variations can make conventional image segmentation and manually configured MSER approaches sensitive to pa-rameter selection and less robust when detecting heterogeneous cancerous regions. To address these limitations, this study highlights the critical role of metaheuristic optimization as a key driver for fully automating and optimizing the combined CLAHE-MSER pipeline for binary breast cancer classifica-tion. Methods: First, CLAHE is applied to the input medical images to improve local contrast and enhance visual differences between healthy and cancerous tissue. The enhanced images are subse-quently processed using the MSER technique to identify stable intensity regions potentially associated with lesions or tumor masses. Rather than relying on manual configuration, the MSER parameter space and enhancement thresholds are formulated as a multidimensional optimization problem, and metaheuristic optimization algorithms are employed to automatically explore the parameter space and determine optimal configurations for region detection. Candidate solutions are iteratively evalu-ated using an objective function designed to improve the quality, stability, spatial coherence, and ac-curacy of the detected tumor regions prior to binary classification. The proposed metaheuristic-driven CLAHE-MSER framework therefore lets the detection process adapt automatically to the visual char-acteristics of individual medical images while eliminating dependence on manually selected parame-ters. Results: We performed experimental evaluations on medical images containing healthy, benign, and malignant regions. We quantitatively evaluated the performance of the proposed CLAHE-MSER framework, optimized by metaheuristic algorithms, using several image-quality, region-detection, and binary classification metrics. The experimental results indicate that incorporating CLAHE improves local contrast and facilitates the identification of subtle differences between healthy and affected tis-sue. Furthermore, metaheuristic optimization significantly improves MSER parameter selection, re-sulting in more consistent and spatially coherent detection of tumor regions than conventional MSER configurations and non-optimized approaches. The optimized configurations better preserve relevant cancer-related structures, maximizing overall binary classification accuracy while drastically reduc-ing the detection of healthy tissue and irrelevant regions. Conclusion: Integrating CLAHE- MSER, and metaheuristic optimization provides a robust, fully automated, and adaptive framework for binary breast cancer classification based on medical image analysis. CLAHE enhances the visual infor-mation needed to distinguish affected tissue, while MSER extracts stable image regions associated with potential tumor lesions. Metaheuristic optimization serves as the central component to automate and refine the detection process by dynamically identifying suitable parameter configurations for different image conditions. The proposed methodology represents a promising computational ap-proach for automated breast cancer screening, computer-aided diagnosis (CAD), lesion classification, and intelligent medical decision support systems.

Timely and accurate detection of COVID-19 is essential for rapid intervention and preventing the spread of the disease, especially among vulnerable populations. This study introduces a new two-stage methodology for the detection of COVID-19 in chest X-ray images, combining an optimized preprocessing stage with a deep learning classification stage. The main contribution of this approach lies in the integration of the Maximally Stable Extremal Regions (MSER) algorithm with the Grey Wolf Optimizer (GWO) metaheuristic to enhance image preprocessing. MSER adaptively identifies candidate regions potentially associated with COVID-19, while GWO fine-tunes its parameters to maximize the relevance and stability of these regions under diverse imaging conditions. This optimized preprocessing significantly improves the visibility of key features, making them more distinguishable to the neural network. In the second stage, a deep convolutional neural network is trained to classify the enhanced images. Experimental results demonstrate that the proposed approach significantly improves classification performance, increasing accuracy from 90% to 98%, and accelerating convergence during training. Comprehensive evaluations across multiple metrics confirm the robustness and effectiveness of the method, highlighting its potential as a reliable tool for automated COVID-19 diagnosis from X-ray imagery.