Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network

• Published in: Korean journal of radiology 2021, 22(3), , pp.476-488
• Main Authors: Yoo, Seung Jin, Yoon, Soon Ho, Lee, Jong Hyuk, Kim, Ki Hwan, Choi, Hyoung In, Park, Sang Joon, Goo, Jin Mo
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Automation; Databases, Factual; Datasets; Deep Learning; Female; Humans; Lung - abnormalities; Lung - diagnostic imaging; Lung - physiology; Lung cancer; Lung diseases; Lung Diseases, Interstitial - diagnosis; Lung Diseases, Interstitial - diagnostic imaging; Male; Masks; Medical imaging; Medical screening; Middle Aged; Neural networks; Performance evaluation; Pulmonary arteries; Thoracic Imaging; Tomography; Tomography, X-Ray Computed; 방사선과학
• ISSN: 1229-6929; 2005-8330
• DOI: 10.3348/kjr.2020.0318

We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.