Ant Colony Optimization-Based Deep Ensemble Learning Model for Improved Gastrointestinal Disease Detection

Abstract

Gastrointestinal (GI) disorders represent a significant challenge in healthcare, underscoring the necessity for more precise and effective diagnostic techniques. Conventional approaches, which often rely on single models, have demonstrated shortcomings in both accuracy and efficacy, often failing to detect the intricate and varied patterns linked to these diseases. To overcome these challenges, this study introduces a novel ensemble learning framework tailored for GI detection. The framework utilizes a three-layer architectural approach that integrates Convolutional Neural Networks (CNNs), the Ant Colony Optimization Algorithm (ACO), and Weighted Aggregation Ensemble Techniques (WAET). The methodology unfolds in three key stages: First, multiple CNNs are fine-tuned using transfer learning, while ACO optimizes the hyperparameters of each CNN to enhance model adaptability and performance. Second, the predictions from the top three optimized models are combined using WAET to strengthen the system's robustness in GI detection. Lastly, ACO is employed to optimize the weight assignment for each model during the ensembling process. We use a dataset of 6000 endoscopy images, enhanced by cropping and augmentation techniques to boost diversity and improve classification performance. Additional experiments on CP-Child-A and CP-Child-B show that the proposed ensemble model achieves superior performance, with an accuracy of 99.88% on the primary dataset and 98.75% and 100% on CP-Child-A and B, respectively. It outperforms traditional hybrid methods and state-of-the-art approaches. The effectiveness of the model is further validated through interpretability techniques like Grad-CAM and SHAP, providing insights into the decision-making process. This approach enhances diagnostic accuracy and provides a robust, interpretable solution for automated detection of GI diseases, improving clinical decision-making.