Accurate and early detection of ovarian cancer is crucial for effective treatment and improved patient outcomes. This paper investigates the use of deep learning models for classifying histopathological images of ovarian cancer. We employed five advanced convolutional neural networks—DenseNet121, InceptionV3, VGG19, AlexNet, and ResNet50—to perform the classification task. The dataset comprised 10,000 augmented histopathological images, balanced between cancerous and non-cancerous classes. DenseNet121 and InceptionV3 demonstrated superior performance, with DenseNet121 achieving a validation accuracy of 97.47% and InceptionV3 reaching 98.20%. Both models exhibited high precision, recall, and F1-scores, making them reliable for diagnostic purposes. While VGG19, AlexNet, and ResNet50 showed comparatively lower accuracy, they provided valuable insights into the variability and complexity of the data, particularly in handling challenging cases. The study highlights the potential of deep learning models in enhancing the accuracy and efficiency of ovarian cancer diagnosis. Future work will focus on integrating additional image modalities and employing ensemble learning techniques to further improve model performance. These advancements promise to support pathologists with more precise diagnostic tools, ultimately contributing to better clinical outcomes for patients.