Abstract:
This research focuses on the improvement of classification of abnormal and normal CT scan images in the context of colorectal cancer by using generated CT scan images. Li...Show MoreMetadata
Abstract:
This research focuses on the improvement of classification of abnormal and normal CT scan images in the context of colorectal cancer by using generated CT scan images. Limited data availability poses a challenge as classification models, particularly deep learning models, require substantial amounts of data to achieve optimal performance. To address this issue, we employ a Generative Adversarial Networks (GANs) based model to generate additional data using the existing dataset. Subsequently, we retrain the classification model to assess any improvements resulting from the augmented data. Our findings indicate that StyleGAN2-ADA effectively generates synthetic CT scan images of colorectal cancer patients. Leveraging the generated images, we observe an enhancement in the classification performance. These results suggest the potential of data augmentation using GAN-based models to improve the accuracy and efficacy of classification models in the field of medical imaging analysis.
Published in: 2023 IEEE 8th International Conference On Software Engineering and Computer Systems (ICSECS)
Date of Conference: 25-27 August 2023
Date Added to IEEE Xplore: 26 September 2023
ISBN Information: