This study proposes a hybrid framework for early and accurate classification and segmentation of prostate cancer using deep learning. The framework consists of two stages: classification and segmentation. In the classification stage, eight pretrained convolutional neural networks (CNNs) are fine-tuned using the Aquila optimizer to classify patients with prostate cancer from normal ones. If a patient is diagnosed with prostate cancer, the segmentation stage is triggered, where the U-Net model is used to segment the cancerous area from the overall image. The framework is trained on three datasets: "PANDA: Resized Train Data (512 × 512)", "ISUP Grade-wise Prostate Cancer", and "Transverse Plane Prostate Dataset". The proposed framework achieves high classification accuracy, with 88.91% using MobileNet for the "ISUP Grade-wise Prostate Cancer" dataset and 100% using MobileNet and ResNet152 for the "Transverse Plane Prostate Dataset" dataset. The U-Net model achieves an average segmentation accuracy of 98.46% and an AUC of 0.9778 using the "PANDA: Resized Train Data (512 × 512)" dataset. The results indicate that the proposed framework performs well in both classification and segmentation tasks. The study also compares the proposed framework with related studies and highlights the effectiveness of the hybrid approach. The framework is trained on three different datasets to ensure generalization. The study concludes that the proposed framework is a promising approach for early and accurate diagnosis of prostate cancer. However, the study has some limitations, including the use of only one dataset for segmentation and the selection of only eight transfer learning models. Future work includes applying different CNN architectures and other metaheuristic optimizers, as well as extending the framework to other types of tumors.This study proposes a hybrid framework for early and accurate classification and segmentation of prostate cancer using deep learning. The framework consists of two stages: classification and segmentation. In the classification stage, eight pretrained convolutional neural networks (CNNs) are fine-tuned using the Aquila optimizer to classify patients with prostate cancer from normal ones. If a patient is diagnosed with prostate cancer, the segmentation stage is triggered, where the U-Net model is used to segment the cancerous area from the overall image. The framework is trained on three datasets: "PANDA: Resized Train Data (512 × 512)", "ISUP Grade-wise Prostate Cancer", and "Transverse Plane Prostate Dataset". The proposed framework achieves high classification accuracy, with 88.91% using MobileNet for the "ISUP Grade-wise Prostate Cancer" dataset and 100% using MobileNet and ResNet152 for the "Transverse Plane Prostate Dataset" dataset. The U-Net model achieves an average segmentation accuracy of 98.46% and an AUC of 0.9778 using the "PANDA: Resized Train Data (512 × 512)" dataset. The results indicate that the proposed framework performs well in both classification and segmentation tasks. The study also compares the proposed framework with related studies and highlights the effectiveness of the hybrid approach. The framework is trained on three different datasets to ensure generalization. The study concludes that the proposed framework is a promising approach for early and accurate diagnosis of prostate cancer. However, the study has some limitations, including the use of only one dataset for segmentation and the selection of only eight transfer learning models. Future work includes applying different CNN architectures and other metaheuristic optimizers, as well as extending the framework to other types of tumors.