sis 18: e72

Research Article

GAN Data Augmentation for Improved Automated Atherosclerosis Screening from Coronary CT Angiography

Download206 downloads
  • @ARTICLE{10.4108/eai.17-5-2022.173981,
        author={Amel Laidi and Mohammed Ammar and Mostafa El Habib Daho and Said Mahmoudi},
        title={GAN Data Augmentation for Improved Automated Atherosclerosis Screening from Coronary CT Angiography},
        journal={EAI Endorsed Transactions on Scalable Information Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SIS},
        year={2022},
        month={5},
        keywords={Atherosclerosis, CCTA, Transfer learning, Generative Adversarial Networks, GAN, Data augmentation},
        doi={10.4108/eai.17-5-2022.173981}
    }
    
  • Amel Laidi
    Mohammed Ammar
    Mostafa El Habib Daho
    Said Mahmoudi
    Year: 2022
    GAN Data Augmentation for Improved Automated Atherosclerosis Screening from Coronary CT Angiography
    SIS
    EAI
    DOI: 10.4108/eai.17-5-2022.173981
Amel Laidi1,*, Mohammed Ammar2, Mostafa El Habib Daho3, Said Mahmoudi4
  • 1: LIMOSE Laboratory M’Hamed Bougara University Boumerdes, Algeria
  • 2: LIST Laboratory, University M’Hamed Bougara, Boumerdes, Algeria
  • 3: Biomedical Engineering Laboratory, University of Tlemcen, Tlemcen, Algeria
  • 4: Computer Science Department, Faculty of Engineering ,University of Mons. , Belgium
*Contact email: a.laidi@univ-boumerdes.dz

Abstract

INTRODUCTION: Atherosclerosis is a chronic medical condition that can result in coronary artery disease, strokes, or even heart attacks. early detection can result in timely interventions and save lives.

OBJECTIVES: In this work, a fully automatic transfer learning-based model was proposed for Atherosclerosis detection in coronary CT angiography (CCTA). The model’s performance was improved by generating training data using a Generative Adversarial Network.

METHODS: A first experiment was established on the original dataset with a Resnet network, reaching 95.2% accuracy, 60.8% sensitivity, 99.25% specificity and 90.48% PPV. A Generative Adversarial Network (GAN) was then used to generate a new set of images to balance the dataset, creating more positive images. Experiments were made adding from 100 to 1000 images to the dataset.

RESULTS: adding 1000 images resulted in a small drop in accuracy to 93.2%, but an improvement in overall performance with 89.0% sensitivity, 97.37% specificity and 97.13% PPV.

CONCLUSION: This paper was one of the early research projects investigating the efficiency of data augmentation using GANs for atherosclerosis, with results comparable to the state of the art.