TY - JOUR AU - Laidi, Amel AU - Ammar, Mohammed AU - Daho, Mostafa El Habib AU - Mahmoudi, Said PY - 2022/05/17 Y2 - 2024/03/29 TI - GAN Data Augmentation for Improved Automated Atherosclerosis Screening from Coronary CT Angiography JF - EAI Endorsed Transactions on Scalable Information Systems JA - EAI Endorsed Scal Inf Syst VL - 10 IS - 1 SE - Research articles DO - 10.4108/eai.17-5-2022.173981 UR - https://publications.eai.eu/index.php/sis/article/view/1027 SP - e4 AB - <p>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.<br>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.<br>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.<br>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.<br>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.</p> ER -