Improved Pancreatic Cancer Diagnosis: Deep Learning Integration with U-Net for Segmented Histopathology Image Analysis

Pancreatic cancer remains one of the most lethal malignancies due to its asymptomatic early stages and rapid progression, leading to delayed diagnosis and limited treatment options. Accurate and early detection is critical for improving patient outcomes. This study introduces a robust deep learning approach integrating U-Net for image segmentation and four state-of-the-art Convolutional Neural Network (CNN) models—ResNet50, VGG16, MobileNetV2, and DenseNet121—for the classification of pancreatic cancer histopathology images. To address the challenges of data scarcity, various data augmentation techniques, including scaling, flipping, and random rotations, are employed to improve model generalizability. U-Net effectively isolates regions of interest, enabling precise segmentation, while transfer learning with CNNs ensures accurate classification of cancerous and non-cancerous tissues. Comparative analysis of the models reveals DenseNet121 as the most accurate model, achieving superior performance across all evaluation metrics, including accuracy, precision, recall, and F1-score. MobileNetV2, however, emerges as a viable candidate for real-time applications due to its lower computational overhead and efficient architecture. The proposed method demonstrates significant potential to enhance diagnostic accuracy, reduce time for diagnosis, and support clinical decision-making, paving the way for improved early detection of pancreatic cancer.