Gazelle Optimization Algorithm-Improved SqueezeNet-based Deep Learning Model for Computer Aided Cervical Cancer Diagnosis

Cervical cancer is the fourth most common cancer among women worldwide, and early detection plays a crucial role in improving survival rates. The Pap smear test is an efficient screening method that looks at cervical cells to find dysplasia and structural changes in cell shape. This research presents a novel deep-learning method for Computer Aided Cervical Cancer Detection (CACCD), which merges the pre-trained SqueezeNet model with the Gazelle Optimization Algorithm (GOA) to boost detection and classification accuracy. The SqueezeNet model was chosen because it has a compact architecture and can effectively identify essential features and complex patterns from Pap smear test images. The GOA algorithm adjusted model hyperparameters to achieve better performance and accuracy. The performance of this approach was assessed and validated using the Herlev dataset, which serves as a standard benchmark in the domain, and the results showed superior performance compared to other models, including MobileNetV3 and ResNet. The cervical cancer detection method displays strong results according to key performance metrics like accuracy, precision, recall, F1-score, and Matthews Correlation Coefficient (MCC). This study highlights the potential of integrating SqueezeNet with advanced optimization techniques to improve the accuracy and reliability of automated cervical cancer detection.