A Novel Automated System for Pathological Lung Segmentation Using Modified Local Binary Patterns and Hierarchical Transformers

This study proposes a novel deep learning-based automatic segmentation system for accurately delineating pulmonary regions in 3D computed tomography (CT) scans. First, a modified local binary pattern, called cylinder binary pattern (CBP), is introduced, which utilizes concentric cylinders at different radii, to effectively capture intricate textural details at multiple levels. Then, a 3D encoder-decoder deep learning-based network, called VX-Net, is proposed specifically to accurately segment pulmonary regions within 3D CT scans. This network incorporates the hierarchical transformers into its encoder architecture to significantly improve feature extraction process. These transformers replicate Transformer model by integrating 3D convolutions with both larger and smaller kernels. While this network is used for segmenting pulmonary regions, it can also be adapted for various other segmentation tasks. The proposed system is evaluated on 3D CT scans of 26 patients with three different severity levels of COVID-19, using four distinct metrics. These include Dice similarity coefficient (DSC), overlap coefficient, Hausdorff distance (HD), and absolute volume difference (AVD). The proposed system shows remarkable performance, achieving scores of 97.63<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">±0.98</inf>%, 95.38<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">±1.86</inf>%, 1.99<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">±1.9</inf>, and 3.01<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">±1.15</inf>, respectively. When compared to various state-of-the-art segmentation methods, the proposed segmentation system showcases its ability to accurately segment both normal and pathological pulmonary regions.