Data augmentation in cancer image classification problem with quantum GAN
Muhammad Bagus Andra, Asri Rizki Yuliani, Jimmy Abdel Kadar +2 more
Abstract In this paper, we propose a novel approach leveraging Quantum Generative Adversarial Networks (QGANs) for data augmentation in cancer image classification tasks. Cancer diagnosis from medical images plays a crucial role in early detection and treatment planning. However, imbalance nature of medical image data pose significant challenges for training accurate classification models. Our proposed methodology utilizes QGANs to generate synthetic medical images that closely mimic the characteristics of real cancer images classes, effectively addressing the data imbalance issue. Our QGAN architecture, which combines quantum circuits for the generator with a classical neural networks for the discriminator, was trained to synthesize medical images for augmentation. The performance of the convolutional neural networks (CNN) classifier was evaluated using accuracy and the area under the receiver operating characteristics curve (AUC-ROC) as metrics. Results show that augmented datasets significantly improve the classif ication performance. For instance, the AUC-ROC for the Basal Cell Carcinoma (BCC) class increased by 0.031, and the Dermatofibroma (DF) class saw a reduction in validation loss by 0.06. Moreover, segmentation-based QGAN training demonstrated considerable advantages in computational efficiency. The training time was reduced to just one hour, and inference times were less than a second per image.
Quantum Machine Intelligence•Sep 15, 2025•3 citations