Integrating Ant Colony Optimization with Deep Learning for Improved Lung Cancer Diagnosis and Prognosis

AIM: The goal of this study is to increase the accuracy and reliability in diagnosing lung cancer with a new approach that employs Ant Colony Optimization in an ensemble with deep learning models: DenseNet, ResNet 50, VGG 19, and Long Short-Term Memory networks. BACKGROUND: In this study, Ant Colony Optimization has been united with advanced deep learning models like DenseNet, ResNet 50, VGG 19, Long Short-Term Memory networks, for improved detection of lung cancer from CT images and medical records. ACO optimization in feature selection was performed, greatly enhancing the performance of models, which when tested showed high accuracy rates in AI-driven health care solutions. OBJECTIVE: DenseNet, combined with ACO and LSTM, achieved an accuracy of 97.9%. The study demonstrates the effectiveness of ACO in improving diagnostic precision, setting a foundation for future AI-driven healthcare solutions to improve lung cancer diagnosis and patient outcomes. METHODS: This research integrates Ant Colony Optimization (ACO) with advanced deep learning models DenseNet, ResNet 50, and VGG 19 and Long Short-Term Memory (LSTM) networks to improve lung disease diagnosis from CT scans and medical records. RESULTS: This research enhances lung cancer diagnosis by integrating Ant Colony Optimization (ACO) with advanced deep learning models like DenseNet, ResNet 50, VGG 19, and LSTM networks. ACO optimizes feature selection, improving model accuracy. DenseNet with ACO and LSTM achieved the highest accuracy of 97.9%. ResNet 50 reached 96.2%, while VGG 19 had 92.3%. The study demonstrates the effectiveness of combining swarm intelligence with deep learning for improved medical diagnosis. CONCLUSION: The ACO approach effectively optimizes feature selection, significantly improving model performance. With DenseNet achieving an accuracy of 97.9%, this study highlights promising advancements in AI-driven healthcare solutions for more precise and reliable lung cancer diagnosis and prognosis.