Segmentation on Chest CT Imaging in COVID-19 Based on the Improvement Attention U-Net Model
Nguyen Tran-Ngoc, Hien D. Nguyen, Nhan T. Huynh, Nha P. Tran, Linh V. Nguyen
Abstract
This paper proposes a new deep learning model to detect COVID-19 lesions in chest CT images. This method is based on the Attention U-net which uses the layer of Atrous Spatial Pyramid Pooling (ASPP) to capture the feature on various scales. It also contains an attention gate. The attention gate provides the ability to suppress irrelevant regions and focus on the useful feature in an input image. The experimental results show that this method can achieve 99.61% accuracy and 80.43% precision. They are more effectively than the baseline method on Chest CT images.
Topics & Concepts
PoolingArtificial intelligenceFeature (linguistics)Coronavirus disease 2019 (COVID-19)Pyramid (geometry)SegmentationComputer scienceFocus (optics)Pattern recognition (psychology)Computer visionMedicineMathematicsPathologyPhilosophyDiseasePhysicsGeometryOpticsInfectious disease (medical specialty)LinguisticsCOVID-19 diagnosis using AIRadiomics and Machine Learning in Medical ImagingAI in cancer detection