Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks

The Future of Artificial Intelligence Using Images and Clinical Assessment for Difficult Airway Management

Artificial intelligence (AI) algorithms, particularly deep learning, are automatic and sophisticated methods that recognize complex patterns in imaging data providing high qualitative assessments. Several machine-learning and deep-learning models using imaging techniques have been recently developed and validated to predict difficult airways. Despite advances in AI modeling. In this review article, we describe the advantages of using AI models. We explore how these methods could impact clinical practice. Finally, we discuss predictive modeling for difficult laryngoscopy using machine-learning and the future approach with intelligent intubation devices.

CT-based airway changes after smoking cessation in the general population

PURPOSE

Previous research has demonstrated improvements in CT-derived bronchial parameters in the first years after smoking cessation. This study investigates the association between longer smoking cessation duration and bronchial parameters in lung-healthy and lung-unhealthy ex-smokers from the general population.

MATERIALS AND METHODS

We conducted a cross-sectional analysis using low-dose CT scans of ex-smokers from the general population with at least 10 pack-years from the ImaLife study, a sub study within the Lifelines cohort. Participants ⩾45 years who completed a lung-function test were recruited for low-dose CT imaging. We divided them into lung-healthy and lung-unhealthy based on spirometry, self-reported diagnosis and imaging signs of respiratory disease. Bronchial parameters Pi10, wall thickness, luminal area and wall area percent (WAP) were obtained using a previously validated method. Multivariable linear regression (MLR) was used to evaluate the independent associations between smoking cessation duration and bronchial parameters, adjusting for sex, age, height, weight, and pack-years.

RESULTS

The study included 1,869 ex-smokers; 1,421 (76 %) were classified as lung-healthy (58 % men, mean age 64.2 ± 9.8 years, pack-years 16.5 [12.5-23.3], smoking cessation duration 20.0 [14.0-29.0] years) and 448 (24 %) as unhealthy (56 % men, mean age 66.1 ± 10.5 years, pack-years 18.2 [13.4-25.2], smoking cessation duration 20.0 [13.8-29.0] years). In the lung-unhealthy group, individuals with a longer duration of smoking cessation had a lower WAP compared to those with a shorter cessation duration (-0.528 % per 10 years, p = 0.005). In contrast, in MLR no significant associations were observed for the lung-healthy group..

CONCLUSIONS

In individuals with respiratory conditions, longer smoking cessation duration is related to a decrease in wall area percent of the bronchial walls. The results suggest the potential for improvements in airway health when people quit smoking, warranting further investigation with longitudinal studies.

BCNet: Bronchus Classification via Structure Guided Representation Learning

CT-based bronchial tree analysis is a key step for the diagnosis of lung and airway diseases. However, the topology of bronchial trees varies across individuals, which presents a challenge to the automatic bronchus classification. To solve this issue, we propose the Bronchus Classification Network (BCNet), a structure-guided framework that exploits the segment-level topological information using point clouds to learn the voxel-level features. BCNet has two branches, a Point-Voxel Graph Neural Network (PV-GNN) for segment classification, and a Convolutional Neural Network (CNN) for voxel labeling. The two branches are simultaneously trained to learn topology-aware features for their shared backbone while it is feasible to run only the CNN branch for the inference. Therefore, BCNet maintains the same inference efficiency as its CNN baseline. Experimental results show that BCNet significantly exceeds the state-of-the-art methods by over 8.0% both on F1-score for classifying bronchus. Furthermore, we contribute BronAtlas: an open-access benchmark of bronchus imaging analysis with high-quality voxel-wise annotations of both anatomical and abnormal bronchial segments. The benchmark is available at https://osf.io/pskr9/?viewonly=94fa3d87274b4095ac9a4b88cc9a1341.

Label refinement network from synthetic error augmentation for medical image segmentation

Deep convolutional neural networks for image segmentation do not learn the label structure explicitly and may produce segmentations with an incorrect structure, e.g., with disconnected cylindrical structures in the segmentation of tree-like structures such as airways or blood vessels. In this paper, we propose a novel label refinement method to correct such errors from an initial segmentation, implicitly incorporating information about label structure. This method features two novel parts: (1) a model that generates synthetic structural errors, and (2) a label appearance simulation network that produces segmentations with synthetic errors that are similar in appearance to the real initial segmentations. Using these segmentations with synthetic errors and the original images, the label refinement network is trained to correct errors and improve the initial segmentations. The proposed method is validated on two segmentation tasks: airway segmentation from chest computed tomography (CT) scans and brain vessel segmentation from 3D CT angiography (CTA) images of the brain. In both applications, our method significantly outperformed a standard 3D U-Net, four previous label refinement methods, and a U-Net trained with a loss tailored for tubular structures. Improvements are even larger when additional unlabeled data is used for model training. In an ablation study, we demonstrate the value of the different components of the proposed method.

Skeleton-guided 3D convolutional neural network for tubular structure segmentation

PURPOSE

Accurate segmentation of tubular structures is crucial for clinical diagnosis and treatment but is challenging due to their complex branching structures and volume imbalance. The purpose of this study is to propose a 3D deep learning network that incorporates skeleton information to enhance segmentation accuracy in these tubular structures.

METHODS

Our approach employs a 3D convolutional network to extract 3D tubular structures from medical images such as CT volumetric images. We introduce a skeleton-guided module that operates on extracted features to capture and preserve the skeleton information in the segmentation results. Additionally, to effectively train our deep model in leveraging skeleton information, we propose a sigmoid-adaptive Tversky loss function which is specifically designed for skeleton segmentation.

RESULTS

We conducted experiments on two distinct 3D medical image datasets. The first dataset consisted of 90 cases of chest CT volumetric images, while the second dataset comprised 35 cases of abdominal CT volumetric images. Comparative analysis with previous segmentation approaches demonstrated the superior performance of our method. For the airway segmentation task, our method achieved an average tree length rate of 93.0%, a branch detection rate of 91.5%, and a precision rate of 90.0%. In the case of abdominal artery segmentation, our method attained an average precision rate of 97.7%, a recall rate of 91.7%, and an F-measure of 94.6%.

CONCLUSION

We present a skeleton-guided 3D convolutional network to segment tubular structures from 3D medical images. Our skeleton-guided 3D convolutional network could effectively segment small tubular structures, outperforming previous methods.

Effects of acute-phase COVID-19-related indicators on pulmonary fibrosis and follow-up evaluation

BACKGROUND

Post-COVID-19 pulmonary fibrosis is a significant long-term respiratory morbidity affecting patients' respiratory health. This exploratory study aims to investigate the incidence, clinical characteristics, and acute-phase risk factors for pulmonary fibrosis in COVID-19 patients. Additionally, it evaluates pulmonary function and chest CT outcomes to provide clinical evidence for the early identification of high-risk patients and the prevention of post-COVID-19 pulmonary fibrosis.

METHODS

We retrospectively analyzed 595 patients hospitalized for COVID-19 from January 2022 to July 2023. Patients were divided into fibrosis and nonfibrosis groups on the basis of imaging changes. Baseline data, including demographics, disease severity, laboratory indicators, and chest imaging characteristics, were collected. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors for pulmonary fibrosis. Pulmonary function and chest CT follow-ups were conducted for the fibrosis group. The data were processed via SPSS 26.0, with P < 0.05 considered statistically significant.

RESULTS

The incidence of pulmonary fibrosis was 4.37%, with 2.08% in moderate cases and 8.22% in severe cases. Significant differences were found between the fibrosis and nonfibrosis groups in sex; disease severity; NLR; ALB and LDH levels; and percentages of lung reticular lesions, consolidations, and GGOs (P < 0.05). Multivariate analysis revealed LDH (OR = 1.004, 95% CI 1.000-1.007, P = 0.035), ALB (OR = 0.871, 95% CI 0.778-0.974, P = 0.015), lung reticular lesion volume (OR = 1.116, 95% CI 1.040-1.199, P = 0.002), and lung consolidation volume (OR = 1.131, 95% CI 1.012-1.264, P = 0.030) as independent risk factors. The follow-up results revealed significant improvements in pulmonary function, specifically in the FVC%, FEV1%, and DLCO%, but not in the FEV1/FVC. Quantitative chest CT analysis revealed significant differences in lung reticular lesions, consolidation, and GGO volumes but no significant difference in honeycomb volume.

CONCLUSIONS

The incidence of pulmonary fibrosis post-COVID-19 increases with disease severity. LDH, ALB, lung reticular lesions, and consolidation volume are independent risk factors for patients with fibrosis.

Detail-sensitive 3D-UNet for pulmonary airway segmentation from CT images

The segmentation of airway from computed tomography (CT) images plays a vital role in pulmonary disease diagnosis, evaluation, surgical planning, and treatment. Nevertheless, it is still challenging for current methods to handle distal thin and low-contrast airways, leading to mis-segmentation issues. This paper proposes a detail-sensitive 3D-UNet (DS-3D-UNet) that incorporates two new modules into 3D-UNet to segment airways accurately from CT images. The feature recalibration module is designed to give more attention to the foreground airway features through a new attention mechanism. The detail extractor module aims to restore multi-scale detailed features by fusion of features at different levels. Extensive experiments were conducted on the ATM'22 challenge dataset composed of 300 CT scans with airway annotations to evaluate its performance. Quantitative comparisons prove that the proposed model achieves the best performance in terms of Dice similarity coefficient (92.6%) and Intersection over Union (86.3%), outperforming other state-of-the-art methods. Qualitative comparisons further exhibit the superior performance of our method in segmenting thin and confused distal bronchi. The proposed model could provide important references for the diagnosis and treatment of pulmonary diseases, holding promising prospects in the field of digital medicine. Codes are available at https://github.com/nighlevil/DS-3D-UNet/tree/master .

Computational multiphysics modeling of radioactive aerosol deposition in diverse human respiratory tract geometries

The evaluation of aerosol exposure relies on generic mathematical models that assume uniform particle deposition profiles over the human respiratory tract and do not account for subject-specific characteristics. Here we introduce a hybrid-automated computational workflow that generates personalized particle deposition profiles in 3D reconstructed human airways from computed tomography scans using Computational Fluid and Particle Dynamics simulations. This is the first large-scale study to consider realistic airways variability, where 380 lower and 40 upper human respiratory tract 3D geometries are reconstructed and parameterized. The data is clustered into nine groups using random forest regression. Computational fluid and particle dynamics simulations are conducted on these representative geometries using a realistic heavy-breathing respiratory cycle and radioactive iodine-131 as a source term. Monte Carlo radiation transport simulations are performed to obtain detailed energy deposition maps. Our findings emphasize the importance of personalized studies, as minor respiratory tract variations notably influence deposition patterns rather than global parameters of the lower airways, observing more than 30% variance in the mass deposition fraction.

AeroPath: An airway segmentation benchmark dataset with challenging pathology and baseline method

To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. The ATM'22 dataset includes a large group of COVID'19 patients and a range of other lung diseases, however, relatively few patients with severe pathologies affecting the airway tree anatomy was found. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.

Modeling Realistic Geometries in Human Intrathoracic Airways

Geometrical models of the airways offer a comprehensive perspective on the complex interplay between lung structure and function. Originating from mathematical frameworks, these models have evolved to include detailed lung imagery, a crucial enhancement that aids in the early detection of morphological changes in the airways, which are often the first indicators of diseases. The accurate representation of airway geometry is crucial in research areas such as biomechanical modeling, acoustics, and particle deposition prediction. This review chronicles the evolution of these models, from their inception in the 1960s based on ideal mathematical constructs, to the introduction of advanced imaging techniques like computerized tomography (CT) and, to a lesser degree, magnetic resonance imaging (MRI). The advent of these techniques, coupled with the surge in data processing capabilities, has revolutionized the anatomical modeling of the bronchial tree. The limitations and challenges in both mathematical and image-based modeling are discussed, along with their applications. The foundation of image-based modeling is discussed, and recent segmentation strategies from CT and MRI scans and their clinical implications are also examined. By providing a chronological review of these models, this work offers insights into the evolution and potential future of airway geometry modeling, setting the stage for advancements in diagnosing and treating lung diseases. This review offers a novel perspective by highlighting how advancements in imaging techniques and data processing capabilities have significantly enhanced the accuracy and applicability of airway geometry models in both clinical and research settings. These advancements provide unique opportunities for developing patient-specific models.

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Memory-efficient semantic segmentation of large microscopy images using graph-based neural networks

We present a graph neural network (GNN)-based framework applied to large-scale microscopy image segmentation tasks. While deep learning models, like convolutional neural networks (CNNs), have become common for automating image segmentation tasks, they are limited by the image size that can fit in the memory of computational hardware. In a GNN framework, large-scale images are converted into graphs using superpixels (regions of pixels with similar color/intensity values), allowing us to input information from the entire image into the model. By converting images with hundreds of millions of pixels to graphs with thousands of nodes, we can segment large images using memory-limited computational resources. We compare the performance of GNN- and CNN-based segmentation in terms of accuracy, training time and required graphics processing unit memory. Based on our experiments with microscopy images of biological cells and cell colonies, GNN-based segmentation used one to three orders-of-magnitude fewer computational resources with only a change in accuracy of ‒2 % to +0.3 %. Furthermore, errors due to superpixel generation can be reduced by either using better superpixel generation algorithms or increasing the number of superpixels, thereby allowing for improvement in the GNN framework's accuracy. This trade-off between accuracy and computational cost over CNN models makes the GNN framework attractive for many large-scale microscopy image segmentation tasks in biology.

Low-Dose CT-derived Bronchial Parameters in Individuals with Healthy Lungs

Background CT-derived bronchial parameters have been linked to chronic obstructive pulmonary disease and asthma severity, but little is known about these parameters in healthy individuals. Purpose To investigate the distribution of bronchial parameters at low-dose CT in individuals with healthy lungs from a Dutch general population. Materials and Methods In this prospective study, low-dose chest CT performed between May 2017 and October 2022 were obtained from participants who had completed the second-round assessment of the prospective, longitudinal Imaging in Lifelines study. Participants were aged at least 45 years, and those with abnormal spirometry, self-reported respiratory disease, or signs of lung disease at CT were excluded. Airway lumens and walls were segmented automatically. The square root of the bronchial wall area of a hypothetical airway with an internal perimeter of 10 mm (Pi10), luminal area (LA), wall thickness (WT), and wall area percentage were calculated. Associations between sex, age, height, weight, smoking status, and bronchial parameters were assessed using univariable and multivariable analyses. Results The study sample was composed of 8869 participants with healthy lungs (mean age, 60.9 years ± 10.4 [SD]; 4841 [54.6%] female participants), including 3672 (41.4%) never-smokers and 1197 (13.5%) individuals who currently smoke. Bronchial parameters for male participants were higher than those for female participants (Pi10, slope [β] range = 3.49-3.66 mm; LA, β range = 25.40-29.76 mm2; WT, β range = 0.98-1.03 mm; all P < .001). Increasing age correlated with higher Pi10, LA, and WT (r2 range = 0.06-0.09, 0.02-0.01, and 0.02-0.07, respectively; all P < .001). Never-smoking individuals had the lowest Pi10 followed by formerly smoking and currently smoking individuals (3.62 mm ± 0.13, 3.68 mm ± 0.14, and 3.70 mm ± 0.14, respectively; all P < .001). In multivariable regression models, age, sex, height, weight, and smoking history explained up to 46% of the variation in bronchial parameters. Conclusion In healthy individuals, bronchial parameters differed by sex, height, weight, and smoking history; male sex and increasing age were associated with wider lumens and thicker walls. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Emrich and Varga-Szemes in this issue.

Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.

An end-to-end multi-scale airway segmentation framework based on pulmonary CT image

Objective. Automatic and accurate airway segmentation is necessary for lung disease diagnosis. The complex tree-like structures leads to gaps in the different generations of the airway tree, and thus airway segmentation is also considered to be a multi-scale problem. In recent years, convolutional neural networks have facilitated the development of medical image segmentation. In particular, 2D CNNs and 3D CNNs can extract different scale features. Hence, we propose a two-stage and 2D + 3D framework for multi-scale airway tree segmentation.Approach. In stage 1, we use a 2D full airway SegNet(2D FA-SegNet) to segment the complete airway tree. Multi-scale atros spatial pyramid and Atros Residual Skip connection modules are inserted to extract different scales feature. We designed a hard sample selection strategy to increase the proportion of intrapulmonary airway samples in stage 2. 3D airway RefineNet (3D ARNet) as stage 2 takes the results of stage 1 asa prioriinformation. Spatial information extracted by 3D convolutional kernel compensates for the loss of in 2D FA-SegNet. Furthermore, we added false positive losses and false negative losses to improve the segmentation performance of airway branches within the lungs.Main results. We performed data enhancement on the publicly available dataset of ISICDM 2020 Challenge 3, and on which evaluated our method. Comprehensive experiments show that the proposed method has the highest dice similarity coefficient (DSC) of 0.931, and IoU of 0.871 for the whole airway tree and DSC of 0.699, and IoU of 0.543 for the intrapulmonary bronchi tree. In addition, 3D ARNet proposed in this paper cascaded with other state-of-the-art methods to increase detected tree length rate by up to 46.33% and detected tree branch rate by up to 42.97%.Significance. The quantitative and qualitative evaluation results show that our proposed method performs well in segmenting the airway at different scales.

UNSUPERVISED AIRWAY TREE CLUSTERING WITH DEEP LEARNING: THE MULTI-ETHNIC STUDY OF ATHEROSCLEROSIS (MESA) LUNG STUDY

High-resolution full lung CT scans now enable the detailed segmentation of airway trees up to the 6th branching generation. The airway binary masks display very complex tree structures that may encode biological information relevant to disease risk and yet remain challenging to exploit via traditional methods such as meshing or skeletonization. Recent clinical studies suggest that some variations in shape patterns and caliber of the human airway tree are highly associated with adverse health outcomes, including all-cause mortality and incident COPD. However, quantitative characterization of variations observed on CT segmented airway tree remain incomplete, as does our understanding of the clinical and developmental implications of such. In this work, we present an unsupervised deep-learning pipeline for feature extraction and clustering of human airway trees, learned directly from projections of 3D airway segmentations. We identify four reproducible and clinically distinct airway sub-types in the MESA Lung CT cohort.

Persistent mucus plugs in proximal airways are consequential for airflow limitation in asthma

BACKGROUNDInformation about the size, airway location, and longitudinal behavior of mucus plugs in asthma is needed to understand their role in mechanisms of airflow obstruction and to rationally design muco-active treatments.METHODSCT lung scans from 57 patients with asthma were analyzed to quantify mucus plug size and airway location, and paired CT scans obtained 3 years apart were analyzed to determine plug behavior over time. Radiologist annotations of mucus plugs were incorporated in an image-processing pipeline to generate size and location information that was related to measures of airflow.RESULTSThe length distribution of 778 annotated mucus plugs was multimodal, and a 12 mm length defined short ("stubby", ≤12 mm) and long ("stringy", >12 mm) plug phenotypes. High mucus plug burden was disproportionately attributable to stringy mucus plugs. Mucus plugs localized predominantly to airway generations 6-9, and 47% of plugs in baseline scans persisted in the same airway for 3 years and fluctuated in length and volume. Mucus plugs in larger proximal generations had greater effects on spirometry measures than plugs in smaller distal generations, and a model of airflow that estimates the increased airway resistance attributable to plugs predicted a greater effect for proximal generations and more numerous mucus plugs.CONCLUSIONPersistent mucus plugs in proximal airway generations occur in asthma and demonstrate a stochastic process of formation and resolution over time. Proximal airway mucus plugs are consequential for airflow and are in locations amenable to treatment by inhaled muco-active drugs or bronchoscopy.TRIAL REGISTRATIONClinicaltrials.gov; NCT01718197, NCT01606826, NCT01750411, NCT01761058, NCT01761630, NCT01716494, and NCT01760915.FUNDINGAstraZeneca, Boehringer-Ingelheim, Genentech, GlaxoSmithKline, Sanofi-Genzyme-Regeneron, and TEVA provided financial support for study activities at the Coordinating and Clinical Centers beyond the third year of patient follow-up. These companies had no role in study design or data analysis, and the only restriction on the funds was that they be used to support the SARP initiative.

Semiautomated Segmentation and Analysis of Airway Lumen in Pediatric Patients Using Ultra Short Echo Time MRI

RATIONALE AND OBJECTIVES

Ultra short echo time (UTE) magnetic resonance imaging (MRI) pulse sequences have shown promise for airway assessment, but the feasibility and repeatability in the pediatric lung are unknown. The purpose of this work was to develop a semiautomated UTE MRI airway segmentation pipeline from the trachea-to-tertiary airways in pediatric participants and assess repeatability and lumen diameter correlations to lung function.

MATERIALS AND METHODS

A total of 29 participants (n = 7 healthy, n = 11 cystic fibrosis, n = 6 asthma, and n = 5 ex-preterm), aged 7-18 years, were imaged using a 3D stack-of-spirals UTE examination at 3 T. Two independent observers performed airway segmentations using a pipeline developed in-house; observer 1 repeated segmentations 1 month later. Segmentations were extracted using region-growing with leak detection, then manually edited if required. The airway trees were skeletonized, pruned, and labeled. Airway lumen diameter measurements were extracted using ray casting. Intra- and interobserver variability was assessed using the Sørensen-Dice coefficient (DSC) and intra-class correlation coefficient (ICC). Correlations between lumen diameter and pulmonary function were assessed using Spearman's correlation coefficient.

RESULTS

For airway segmentations and lumen diameter, intra- and interobserver DSCs were 0.88 and 0.80, while ICCs were 0.95 and 0.89, respectively. The variability increased from the trachea-to-tertiary airways for intra- (DSC: 0.91-0.64; ICC: 0.91-0.49) and interobserver (DSC: 0.84-0.51; ICC: 0.89-0.21) measurements. Lumen diameter was significantly correlated with forced expiratory volume in 1 second and forced vital capacity (P < .05).

CONCLUSION

UTE MRI airway segmentation from the trachea-to-tertiary airways in pediatric participants across a range of diseases is feasible. The UTE MRI-derived lumen measurements were repeatable and correlated with lung function.

Deep learning-based bronchial tree-guided semi-automatic segmentation of pulmonary segments in computed tomography images

Background

Pulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach.

Methods

The proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation.

Results

For the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm.

Conclusions

This study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.

Multi-site, Multi-domain Airway Tree Modeling

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolution. Since EXACT'09 pulmonary airway segmentation, limited effort has been directed to the quantitative comparison of newly emerged algorithms driven by the maturity of deep learning based approaches and extensive clinical efforts for resolving finer details of distal airways for early intervention of pulmonary diseases. Thus far, public annotated datasets are extremely limited, hindering the development of data-driven methods and detailed performance evaluation of new algorithms. To provide a benchmark for the medical imaging community, we organized the Multi-site, Multi-domain Airway Tree Modeling (ATM'22), which was held as an official challenge event during the MICCAI 2022 conference. ATM'22 provides large-scale CT scans with detailed pulmonary airway annotation, including 500 CT scans (300 for training, 50 for validation, and 150 for testing). The dataset was collected from different sites and it further included a portion of noisy COVID-19 CTs with ground-glass opacity and consolidation. Twenty-three teams participated in the entire phase of the challenge and the algorithms for the top ten teams are reviewed in this paper. Both quantitative and qualitative results revealed that deep learning models embedded with the topological continuity enhancement achieved superior performance in general. ATM'22 challenge holds as an open-call design, the training data and the gold standard evaluation are available upon successful registration via its homepage (https://atm22.grand-challenge.org/).

Reproducibility of a combined artificial intelligence and optimal-surface graph-cut method to automate bronchial parameter extraction

OBJECTIVES

Computed tomography (CT)-based bronchial parameters correlate with disease status. Segmentation and measurement of the bronchial lumen and walls usually require significant manpower. We evaluate the reproducibility of a deep learning and optimal-surface graph-cut method to automatically segment the airway lumen and wall, and calculate bronchial parameters.

METHODS

A deep-learning airway segmentation model was newly trained on 24 Imaging in Lifelines (ImaLife) low-dose chest CT scans. This model was combined with an optimal-surface graph-cut for airway wall segmentation. These tools were used to calculate bronchial parameters in CT scans of 188 ImaLife participants with two scans an average of 3 months apart. Bronchial parameters were compared for reproducibility assessment, assuming no change between scans.

RESULTS

Of 376 CT scans, 374 (99%) were successfully measured. Segmented airway trees contained a mean of 10 generations and 250 branches. The coefficient of determination (R2) for the luminal area (LA) ranged from 0.93 at the trachea to 0.68 at the 6th generation, decreasing to 0.51 at the 8th generation. Corresponding values for Wall Area Percentage (WAP) were 0.86, 0.67, and 0.42, respectively. Bland-Altman analysis of LA and WAP per generation demonstrated mean differences close to 0; limits of agreement (LoA) were narrow for WAP and Pi10 (± 3.7% of mean) and wider for LA (± 16.4-22.8% for 2-6th generations). From the 7th generation onwards, there was a sharp decrease in reproducibility and a widening LoA.

CONCLUSION

The outlined approach for automatic bronchial parameter measurement on low-dose chest CT scans is a reliable way to assess the airway tree down to the 6th generation.

STATEMENT ON CLINICAL RELEVANCE

This reliable and fully automatic pipeline for bronchial parameter measurement on low-dose CT scans has potential applications in screening for early disease and clinical tasks such as virtual bronchoscopy or surgical planning, while also enabling the exploration of bronchial parameters in large datasets.

KEY POINTS

• Deep learning combined with optimal-surface graph-cut provides accurate airway lumen and wall segmentations on low-dose CT scans. • Analysis of repeat scans showed that the automated tools had moderate-to-good reproducibility of bronchial measurements down to the 6th generation airway. • Automated measurement of bronchial parameters enables the assessment of large datasets with less man-hours.

Deep Learning Models for Automatic Upper Airway Segmentation and Minimum Cross-Sectional Area Localisation in Two-Dimensional Images

OBJECTIVE

To develop and validate convolutional neural network algorithms for automatic upper airway segmentation and minimum cross-sectional area (CSAmin) localisation in two-dimensional (2D) radiographic airway images.

MATERIALS AND METHODS

Two hundred and one 2D airway images acquired using cone-beam computed tomography (CBCT) scanning were randomly assigned to a test group (n = 161) to train artificial intelligence (AI) models and a validation group (n = 40) to evaluate the accuracy of AI processing. Four AI models, UNet18, UNet36, DeepLab50 and DeepLab101, were trained to automatically segment the upper airway 2D images in the test group. Precision, recall, Intersection over Union, the dice similarity coefficient and size difference were used to evaluate the performance of the AI-driven segmentation models. The CSAmin height in each image was manually determined using three-dimensional CBCT data. The nonlinear mathematical morphology technique was used to calculate the CSAmin level. Height errors were assessed to evaluate the CSAmin localisation accuracy in the validation group. The time consumed for airway segmentation and CSAmin localisation was compared between manual and AI processing methods.

RESULTS

The precision of all four segmentation models exceeded 90.0%. No significant differences were found in the accuracy of any AI models. The consistency of CSAmin localisation in specific segments between manual and AI processing was 0.944. AI processing was much more efficient than manual processing in terms of airway segmentation and CSAmin localisation.

CONCLUSIONS

We successfully developed and validated a fully automatic AI-driven system for upper airway segmentation and CSAmin localisation using 2D radiographic airway images.

Computational fluid dynamics can detect changes in airway resistance for patients after COVID-19 infection

Infection with COVID-19 can cause severe complication in the respiratory system, which may be related to increased respiratory resistance. Computational fluid dynamics(CFD) was used in this study to calculate the airway resistance based on the airway anatomy and a common air flowrate. The correlation between airway resistance and COVID-19 prognosis was then investigated. A total of 23 COVID-19 patients with 54 CT scans were grouped into the good prognosis and bad prognosis group based on whether the CT scan shows significant decrease in the pneumonia volume after one week treatment and retrospectively analyzed. A baseline group of 8 healthy people with the same age and gender ratio is enrolled for comparison. Results show that the airway resistance at admission is significantly higher for COVID-19 patients with poor prognosis than those with good prognosis and the baseline(0.063 ± 0.055 vs 0.029 ± 0.011 vs 0.017 ± 0.006 Pa/(ml/s),p = 0.01). In the left superior lobe (r = 0.3974,p = 0.01),left inferior lobe (r = 0.4843,p < 0.01), the right inferior lobe (r = 0.5298,p < 0.0001), the airway resistance was significantly correlated with the degree of pneumonia infection. It is concluded that for COVID-19 patients', airway resistance at admission is closely associated with their prognosis, and has the clinical potential to be used as an index for patients' diagnosis.

Airway Detection in COPD at Low-Dose CT Using Deep Learning and Multiparametric Freeze and Grow

PURPOSE

To present and validate a fully automated airway detection method at low-dose CT in patients with chronic obstructive pulmonary disease (COPD).

MATERIALS AND METHODS

In this retrospective study, deep learning (DL) and freeze-and-grow (FG) methods were optimized and applied to automatically detect airways at low-dose CT. Four data sets were used: two data sets consisting of matching standard- and low-dose CT scans from the Genetic Epidemiology of COPD (COPDGene) phase II (2014-2017) cohort (n = 2 × 236; mean age ± SD, 70 years ± 9; 123 women); one data set consisting of low-dose CT scans from the COPDGene phase III (2018-2020) cohort (n = 335; mean age ± SD, 73 years ± 8; 173 women); and one data set consisting of low-dose, anonymized CT scans from the 2003 Dutch-Belgian Randomized Lung Cancer Screening trial (n = 55) acquired by using different CT scanners. Performance measures for different methods were computed and compared by using the Wilcoxon signed rank test.

RESULTS

At low-dose CT, 56 294 of 62 480 (90.1%) airways of the reference total airway count (TAC) and 32 109 of 37 864 (84.8%) airways of the peripheral TAC (TAC_p), detected at standard-dose CT, were detected. Significant losses (P < .001) of 14 526 of 76 453 (19.0%) airways and 884 of 6908 (12.8%) airways in the TAC and 12 256 of 43 462 (28.2%) airways and 699 of 3882 (18.0%) airways in the TAC_p were observed, respectively, for the multiprotocol and multiscanner data without retraining. When using the automated low-dose CT method, TAC values of 347, 342, 323, and 266 and TAC_p values of 205, 202, 289, and 141 were observed for those who have never smoked and participants at Global Initiative for Chronic Obstructive Lung Disease stages 0, 1, and 2, respectively, which were superior to the respective values previously reported for matching groups when using a semiautomated method at standard-dose CT.

CONCLUSION

A low-cost, automated CT-based airway detection method was suitable for investigation of airway phenotypes at low-dose CT.Keywords: Airway, Airway Count, Airway Detection, Chronic Obstructive Pulmonary Disease, CT, Deep Learning, Generalizability, Low-Dose CT, Segmentation, Thorax, LungClinical trial registration no. NCT00608764 Supplemental material is available for this article. © RSNA, 2022.

Human treelike tubular structure segmentation: A comprehensive review and future perspectives

Various structures in human physiology follow a treelike morphology, which often expresses complexity at very fine scales. Examples of such structures are intrathoracic airways, retinal blood vessels, and hepatic blood vessels. Large collections of 2D and 3D images have been made available by medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), Optical coherence tomography (OCT) and ultrasound in which the spatial arrangement can be observed. Segmentation of these structures in medical imaging is of great importance since the analysis of the structure provides insights into disease diagnosis, treatment planning, and prognosis. Manually labelling extensive data by radiologists is often time-consuming and error-prone. As a result, automated or semi-automated computational models have become a popular research field of medical imaging in the past two decades, and many have been developed to date. In this survey, we aim to provide a comprehensive review of currently publicly available datasets, segmentation algorithms, and evaluation metrics. In addition, current challenges and future research directions are discussed.

A deep learning-based post-processing method for automated pulmonary lobe and airway trees segmentation using chest CT images in PET/CT

Background

The proposed algorithm could support accurate localization of lung disease. To develop and validate an automated deep learning model combined with a post-processing algorithm to segment six pulmonary anatomical regions in chest computed tomography (CT) images acquired during positron emission tomography/computed tomography (PET/CT) scans. The pulmonary regions have five pulmonary lobes and airway trees.

Methods

Patients who underwent both PET/CT imaging with an extra chest CT scan were retrospectively enrolled. The pulmonary segmentation of six regions in CT was performed via a convolutional neural network (CNN) of DenseVNet architecture with some post-processing algorithms. Three evaluation metrics were used to assess the performance of this method, which combined deep learning and the post-processing method. The agreement between the combined model and ground truth segmentations in the test set was analyzed.

Results

A total of 640 cases were enrolled. The combined model, which involved deep learning and post-processing methods, had a higher performance than the single deep learning model. In the test set, the all-lobes overall Dice coefficient, Hausdorff distance, and Jaccard coefficient were 0.972, 12.025 mm, and 0.948, respectively. The airway-tree Dice coefficient, Hausdorff distance, and Jaccard coefficient were 0.849, 32.076 mm, and 0.815, respectively. A good agreement was observed between our segmentation in every plot.

Conclusions

The proposed model combining two methods can automatically segment five pulmonary lobes and airway trees on chest CT imaging in PET/CT. The performance of the combined model was higher than the single deep learning model in each region in the test set.

Automated quantification of airway wall thickness on chest CT using retina U-Nets - Performance evaluation and application to a large cohort of chest CTs of COPD patients

PURPOSE

Airway wall thickening is a consequence of chronic inflammatory processes and usually only qualitatively described in CT radiology reports. The purpose of this study is to automatically quantify airway wall thickness in multiple airway generations and assess the diagnostic potential of this parameter in a large cohort of patients with Chronic Obstructive Pulmonary Disease (COPD).

MATERIALS AND METHODS

This retrospective, single-center study included a series of unenhanced chest CTs. Inclusion criteria were the mentioning of an explicit COPD GOLD stage in the written radiology report and time period (01/2019-12/2021). A control group included chest CTs with completely unremarkable lungs according to the report. The DICOM images of all cases (axial orientation; slice-thickness: 1 mm; soft-tissue kernel) were processed by an AI algorithm pipeline consisting of (A) a 3D-U-Net for det detection and tracing of the bronchial tree centerlines (B) extraction of image patches perpendicular to the centerlines of the bronchi, and (C) a 2D U-Net for segmentation of airway walls on those patches. The performance of centerline detection and wall segmentation was assessed. The imaging parameter average wall thickness was calculated for bronchus generations 3-8 (AWT_3-8) across the lungs. Mean AWT_3-8 was compared between five groups (control, COPD Gold I-IV) using non-parametric statistics. Furthermore, the established emphysema score %LAV-950 was calculated and used to classify scans (normal vs. COPD) alone and in combination with AWT_3-8. RESULTS: A total of 575 chest CTs were processed. Algorithm performance was very good (airway centerline detection sensitivity: 86.9%; airway wall segmentation Dice score: 0.86). AWT_3-8 was statistically significantly greater in COPD patients compared to controls (2.03 vs. 1.87 mm, p < 0.001) and increased with COPD stage. The classifier that combined %LAV-950 and AWT_3-8 was superior to the classifier using only %LAV-950 (AUC = 0.92 vs. 0.79).

CONCLUSION

Airway wall thickness increases in patients suffering from COPD and is automatically quantifiable. AWT_3-8 could become a CT imaging parameter in COPD complementing the established emphysema biomarker %LAV-950.

CLINICAL RELEVANCE STATEMENT

Quantitative measurements considering the complete visible bronchial tree instead of qualitative description could enhance radiology reports, allow for precise monitoring of disease progression and diagnosis of early stages of disease.

LTSP: long-term slice propagation for accurate airway segmentation

Purpose:

Bronchoscopic intervention is a widely used clinical technique for pulmonary diseases, which requires an accurate and topological complete airway map for its localization and guidance. The airway map could be extracted from chest computed tomography (CT) scans automatically by airway segmentation methods. Due to the complex tree-like structure of the airway, preserving its topology completeness while maintaining the segmentation accuracy is a challenging task.

Methods:

In this paper, a long-term slice propagation (LTSP) method is proposed for accurate airway segmentation from pathological CT scans. We also design a two-stage end-to-end segmentation framework utilizing the LTSP method in the decoding process. Stage 1 is used to generate a coarse feature map by an encoder–decoder architecture. Stage 2 is to adopt the proposed LTSP method for exploiting the continuity information and enhancing the weak airway features in the coarse feature map. The final segmentation result is predicted from the refined feature map.

Results:

Extensive experiments were conducted to evaluate the performance of the proposed method on 70 clinical CT scans. The results demonstrate the considerable improvements of the proposed method compared to some state-of-the-art methods as most breakages are eliminated and more tiny bronchi are detected. The ablation studies further confirm the effectiveness of the constituents of the proposed method and the efficacy of the framework design.

Conclusion:

Slice continuity information is beneficial to accurate airway segmentation. Furthermore, by propagating the long-term slice feature, the airway topology connectivity is preserved with overall segmentation accuracy maintained.

Creating a training set for artificial intelligence from initial segmentations of airways

Airways segmentation is important for research about pulmonary disease but require a large amount of time by trained specialists. We used an openly available software to improve airways segmentations obtained from an artificial intelligence (AI) tool and retrained the tool to get a better performance. Fifteen initial airway segmentations from low-dose chest computed tomography scans were obtained with a 3D-Unet AI tool previously trained on Danish Lung Cancer Screening Trial and Erasmus-MC Sophia datasets. Segmentations were manually corrected in 3D Slicer. The corrected airway segmentations were used to retrain the 3D-Unet. Airway measurements were automatically obtained and included count, airway length and luminal diameter per generation from the segmentations. Correcting segmentations required 2–4 h per scan. Manually corrected segmentations had more branches (p < 0.001), longer airways (p < 0.001) and smaller luminal diameters (p = 0.004) than initial segmentations. Segmentations from retrained 3D-Unets trended towards more branches and longer airways compared to the initial segmentations. The largest changes were seen in airways from 6th generation onwards. Manual correction results in significantly improved segmentations and is potentially a useful and time-efficient method to improve the AI tool performance on a specific hospital or research dataset.