Fully Automated Lung Lobe Segmentation in Volumetric Chest CT with 3D U-Net: Validation with Intra- and Extra-Datasets

Abstract

Lung lobe segmentation in chest CT has been used for the analysis of lung functions and surgical planning. However, accurate lobe segmentation is difficult as 80% of patients have incomplete and/or fake fissures. Furthermore, lung diseases such as chronic obstructive pulmonary disease (COPD) can increase the difficulty of differentiating the lobar fissures. Lobar fissures have similar intensities to those of the vessels and airway wall, which could lead to segmentation error in automated segmentation. In this study, a fully automated lung lobe segmentation method with 3D U-Net was developed and validated with internal and external datasets. The volumetric chest CT scans of 196 normal and mild-to-moderate COPD patients from three centers were obtained. Each scan was segmented using a conventional image processing method and manually corrected by an expert thoracic radiologist to create gold standards. The lobe regions in the CT images were then segmented using a 3D U-Net architecture with a deep convolutional neural network (CNN) using separate training, validation, and test datasets. In addition, 40 independent external CT images were used to evaluate the model. The segmentation results for both the conventional and deep learning methods were compared quantitatively to the gold standards using four accuracy metrics including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). In internal validation, the segmentation method achieved high accuracy for the DSC, JSC, MSD, and HSD (0.97 ± 0.02, 0.94 ± 0.03, 0.69 ± 0.36, and 17.12 ± 11.07, respectively). In external validation, high accuracy was also obtained for the DSC, JSC, MSD, and HSD (0.96 ± 0.02, 0.92 ± 0.04, 1.31 ± 0.56, and 27.89 ± 7.50, respectively). This method took 6.49 ± 1.19 s and 8.61 ± 1.08 s for lobe segmentation of the left and right lungs, respectively. Although various automatic lung lobe segmentation methods have been developed, it is difficult to develop a robust segmentation method. However, the deep learning-based 3D U-Net method showed reasonable segmentation accuracy and computational time. In addition, this method could be adapted and applied to severe lung diseases in a clinical workflow.

Deep learning-based segmentation of the lung in MR-images acquired by a stack-of-spirals trajectory at ultra-short echo-times

“…for the tracking of potential pulmonary perfusion biomarkers in chronic obstructive pulmonary disease patients [ 22 ] and for fully automated lung lobe segmentation in volumetric chest computed tomography images [ 24 ]. Both studies report a good overall performance of the networks (overall DSC 0.934 [ 22 ] and 0.948 [ 24 ]) but did not evaluate the performance with respect to possible dorsal or ventral inaccuracies leaving this comparison for further studies. In [ 37 ], 3D lung images were processed by a CNN trained with a template-based data augmentation strategy resulting in an overall very good DSC of 0.94 ± 0.02.…”

Mouse lung automated segmentation tool for quantifying lung tumors after micro-computed tomography

“…Much of the work has been done in clinical areas, including both semi-automated [ 25 ] and fully-automated [ 26 , 27 ] approaches. More recently, researchers have worked to bring deep learning and neural networks to the world of CT lung analysis, some focusing on classification [ 28 ] and others on segmentation [ 29 , 30 ]. While these developments are important for the field of clinical imaging, segmentation in pre-clinical imaging comes with its own unique set of challenges.…”

Automated CT Staging of Chronic Obstructive Pulmonary Disease Severity for Predicting Disease Progression and Mortality with a Deep Learning Convolutional Neural Network

“…However, it is often overlooked, as it typically cannot be directly visualized like emphysema, bronchial wall thickening, or endobronchial mucus plugging from a single inspiratory phase. Meanwhile, deformable registration algorithms have been used to both quantify and visualize the distribution of air trapping (13)(14)(15)(16), and recent innovations in deep convolutional neural networks (CNNs) have shown promise for automating and supplementing a variety of tasks in medical imaging (17)(18)(19)(20), including automated lung and lung-lobe segmentation (21)(22)(23)(24). In this study, we recognize that quantitative CT measurements, although explored in the research domain, have not yet permeated the clinical arena.…”