Artificial Intelligence Techniques for Semantic Segmentation and Classification for Ovarian Cancer Detection Using EfficientNetB0 with FPN and Causal Dilated Convolutional Neural Networks: Trends and Challenges

Abstract

Ovarian cancer remains one of the most life-threatening gynecological malignancies, largely due to late-stage diagnosis and limitations in conventional diagnostic methods. Medical imaging techniques such as ultrasound, computed tomography (CT), and magnetic resonance imaging (MRI) are widely used for tumor detection; however, manual interpretation is time-consuming and subject to variability. Artificial intelligence (AI), particularly deep learning, has emerged as a powerful approach to enhance diagnostic accuracy and efficiency. Convolutional neural networks (CNNs) enable automated feature extraction from complex medical images, allowing detection of subtle patterns and achieving performance comparable to expert radiologists. Semantic segmentation methods such as U-Net, DeepLab, and Feature Pyramid Networks (FPN) play a key role in accurately delineating tumor regions, while EfficientNetB0 improves feature extraction through its computationally efficient scaling strategy. When combined with FPN, it supports multi-scale learning for better detection accuracy. Additionally, causal dilated convolutional neural networks enhance contextual understanding by capturing long-range spatial dependencies. This review highlights advancements in segmentation and classification techniques, emphasizing hybrid architectures that integrate these models. Despite promising results, challenges such as limited data, model generalization, and interpretability remain, encouraging further research in explainable and clinically applicable AI systems.