Recent Advances in Semantic Segmentation and Classification for Ovarian Cancer Detection Using EfficientNetB0 with FPN and Causal Dilated Convolutional Neural Networks: A Systematic Review

Abstract

Ovarian cancer remains one of the most fatal gynecological malignancies due to late-stage diagnosis and the lack of reliable early detection methods. Medical imaging techniques such as ultrasound, computed tomography (CT), and magnetic resonance imaging (MRI) play a vital role in tumor identification; however, manual interpretation is time-consuming and subject to variability. Deep learning approaches, particularly convolutional neural networks (CNNs), have emerged as effective tools for automating detection and enhancing diagnostic accuracy. This review highlights advancements in semantic segmentation and classification techniques using architectures such as EfficientNetB0, Feature Pyramid Networks (FPN), and causal dilated convolutional neural networks. EfficientNetB0 enables efficient and accurate feature extraction, while FPN enhances multi-scale feature representation for better detection of complex tumor structures. Semantic segmentation models, including U-Net variants, are widely used to delineate tumor regions, whereas classification models distinguish between benign and malignant cases. These approaches have demonstrated high accuracy and improved segmentation performance. Despite these advancements, challenges such as limited datasets, model generalization, interpretability, and clinical applicability persist. Future research should focus on multi-modal data integration, explainable AI techniques, and lightweight architectures to support real-time clinical deployment and improved patient outcomes.