Airway Segments Research Articles

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.

3D analysis of upper airway morphology related to obstructive sleep apnea severity

BackgroundObstructive sleep apnea (OSA) is the most common sleep-related breathing disorder characterized by repetitive collapse of the upper airway during sleep. However, little evidence is available on the differences between the sub-regions of the upper airway morphology and OSA severity. Since orthodontists frequently perform cone beam computed tomography (CBCT) in the neck area, we aimed to investigate the relationship and the differences between upper airway morphology and OSA severity using CBCT. Materials and methodsThe medical records, CBCT imaging of 21 OSA patients diagnosed by polysomnography, and the apnea-hypopnea index (AHI) results were included to classify OSA severity as mild, moderate, or severe. The minimum cross-sectional areas (MCA) and volumes of the upper pharyngeal airway boundaries in four sub-regions: nasopharynx, retropalatal, retroglossal, and hypopharynx were measured. Dolphin Imaging software was used for upper airway segmentation. The correlation coefficient (r), one-way ANOVA, and the least significant difference post hoc multiple comparison test were applied to fulfill the objectives. ResultsA statistically significant relationship was found between the MCA of the nasopharynx and the AHI (r = −0.473, P < 0.05). Furthermore, a difference was found between mild and moderate and moderate and severe OSA severity in the MCA results of the retroglossal region (P < 0.05). However, no relationship was found between the upper airway volume and OSA severity. ConclusionsMCA was moderately negatively correlated to AHI only in the nasopharynx subregion. Moderate OSA presented significantly less MCA than mild and severe OSA only in the oropharynx and retroglossal subregions.

Congenital cystic diseases of the lung

Congenital cystic diseases of the lung are rare but their incidence is increasing, especially with the widespread use of antenatal ultrasound. Close relationships between airway and respiratory segments and vascular structures during embryonic development can lead to malformations. It should be remembered that congenital cystic lung diseases have the potential to be life-threatening and the possibility of missed diagnosis is high. Surgical resection yields good results in symptomatic lesions, with lobectomy being the most commonly performed surgical approach. Some centers recommend surgical resection even in asymptomatic patients to prevent infection and exclude malignancy.

Effects of Intravenous Infusion of Iodine Contrast Media on the Tracheal Diameter and Lung Volume Measured with Deep Learning-Based Algorithm

This study aimed to investigate the effects of intravenous injection of iodine contrast agent on the tracheal diameter and lung volume. In this retrospective study, a total of 221 patients (71.1 ± 12.4 years, 174 males) who underwent vascular dynamic CT examination including chest were included. Unenhanced, arterial phase, and delayed-phase images were scanned. The tracheal luminal diameters at the level of the thoracic inlet and both lung volumes were evaluated by a radiologist using a commercial software, which allows automatic airway and lung segmentation. The tracheal diameter and both lung volumes were compared between the unenhanced vs. arterial and delayed phase using a paired t-test. The Bonferroni correction was performed for multiple group comparisons. The tracheal diameter in the arterial phase (18.6 ± 2.4 mm) was statistically significantly smaller than those in the unenhanced CT (19.1 ± 2.5 mm) (p < 0.001). No statistically significant difference was found in the tracheal diameter between the delayed phase (19.0 ± 2.4 mm) and unenhanced CT (p = 0.077). Both lung volumes in the arterial phase were 4131 ± 1051 mL which was significantly smaller than those in the unenhanced CT (4332 ± 1076 mL) (p < 0.001). No statistically significant difference was found in both lung volumes between the delayed phase (4284 ± 1054 mL) and unenhanced CT (p = 0.068). In conclusion, intravenous infusion of iodine contrast agent transiently decreased the tracheal diameter and both lung volumes.

Chronic rhinosinusitis in people with cystic fibrosis-an up-to-date review from the perspective of otorhinolaryngology

Cystic fibrosis (CF) is acomplex systemic disease involving numerous organ systems. With improved treatment options and increasing life expectancy of persons with CF (PwCF), extrapulmonary manifestations are coming increasingly into the focus. From birth, almost all PwCF have radiologically detectable pathologies in the upper airways attributable to CF-associated chronic rhinosinusitis (CF-CRS). The aim of this work is to provide an up-to-date overview of CF-CRS from the otorhinolaryngology perspective and to provide the reader with background knowledge and current developments. The cystic fibrosis transmembrane conductance regulator (CFTR) gene defect leads to increased viscosity of sinonasal secretions and reduced mucociliary clearance, causing chronic infection and inflammation in the upper airway segment and, consequently, to CF-CRS. The clinical picture of CF-CRS comprises awide spectrum from asymptomatic to symptomatic courses. CF-CRS is diagnosed clinically and radiologically. Sinonasal saline irrigation is recommended as aconservative treatment measure. Topical corticosteroids are also commonly used. Surgical therapy is reserved for highly symptomatic treatment-refractory patients without asufficient response to conservative treatment including CFTR modulator (CFTRm) therapies. Depending on the CFTR mutation, CFTRm therapies are the treatment of choice. They not only improve the pulmonary and gastrointestinal manifestations in PwCF, but also have positive effects on CF-CRS. The ENT specialist is part of the interdisciplinary team caring for PwCF. Depending on symptom burden and treatment responsiveness, CF-CRS should be treated conservatively and/or surgically. Modern CFTRm have apositive effect on the clinical course of CF-CRS.

Comparison of Lung-RADS Version 1.1 and Lung-RADS Version 2022 in Classifying Airway Nodules Detected at Lung Cancer Screening CT.

Purpose To compare the Lung Imaging Reporting and Data System (Lung-RADS) version 1.1 with version 2022 classification of airway nodules detected at lung cancer screening CT examinations. Materials and Methods This retrospective study included all patients who underwent a lung cancer screening CT examination in the authors' health care network between 2015 and 2021 with a reported airway or endobronchial nodule. A fellowship-trained cardiothoracic radiologist reviewed these CT images and characterized the airway nodules by size, location, multiplicity, morphology, dependent portions of airway, internal air, fluid attenuation, distal changes, outcome at follow-up, and final pathologic diagnosis, if malignant. Sensitivity and specificity of Lung-RADS version 1.1 in detecting malignant nodules were compared with those of Lung-RADS version 2022 using the McNemar test. Results A total of 174 patients were included. Of these, 163 (94%) had airway nodules that were deemed benign, while 11 (6%) had malignant nodules. Airway nodules in the trachea and mainstem bronchi were all benign, while lobar and segmental airway nodules had the highest risk for lung cancer (17.2% and 11.1%, respectively). Of the 12 subsegmental airway nodules that were obstructive, three (25%) were malignant and nine (75%) were benign. Nodules with nonobstructive morphologies, dependent portions of airway, internal air, or fluid attenuation were all benign. Only 10 of the 92 (10.9%) patients with positive Lung-RADS by clinical report had cancer. Lung-RADS version 2022 resulted in higher specificity than version 1.1 (82% vs 50%, P < .001), without sacrificing sensitivity (91% for both). Conclusion Compared with the previous version, Lung-RADS version 2022 reduced the number of false-positive screening CT examinations while still identifying malignant airway nodules. Keywords: CT, Lung, Primary Neoplasms, Pulmonary, Lung Cancer Screening, Lung-RADS, Nodule Risk, Airway Nodule, Endobronchial Nodule © RSNA, 2024.

Airway label prediction in video bronchoscopy: capturing temporal dependencies utilizing anatomical knowledge.

Navigation guidance is a key requirement for a multitude of lung interventions using video bronchoscopy. State-of-the-art solutions focus on lung biopsies using electromagnetic tracking and intraoperative image registration w.r.t. preoperative CT scans for guidance. The requirement of patient-specific CT scans hampers the utilization of navigation guidance for other applications such as intensive care units. This paper addresses bronchoscope tracking by solely incorporating video data. In contrast to state-of-the-art approaches, we entirely omit the use of electromagnetic tracking and patient-specific CT scans to avoid changes in clinical workflows and additional hardware requirements in intensive care units. Guidance is enabled by means of topological bronchoscope localization w.r.t. a generic airway model. Particularly, we take maximally advantage of anatomical constraints of airway trees being sequentially traversed. This is realized by incorporating sequences of CNN-based airway likelihoods into a hidden Markov model. Our approach is evaluated based on multiple experiments inside a lung phantom model. With the consideration of temporal context and use of anatomical knowledge for regularization, we are able to improve the accuracy up to to 0.98 compared to 0.81 (weighted F1: 0.98 compared to 0.81) for a classification based on individual frames. We combine CNN-based single image classification of airway segments with anatomical constraints and temporal HMM-based inference for the first time. Our approach shows first promising results in vision-based guidance for bronchoscopy interventions in the absence of electromagnetic tracking and patient-specific CT scans.

Patients With Post-COVID-19 Respiratory Condition: Chest Computed Tomography Findings and Pulmonary Function Tests and Comparison With Asymptomatic Participants.

The aims of this study were to assess the chest computed tomography (CT) findings in post-COVID-19 respiratory condition (rPCC) patients and compare the findings with asymptomatic participants (APs). It also aimed to evaluate the relationship between CT findings and pulmonary function tests (PFTs) in rPCC patients. Finally, it aimed to compare the quantitative chest CT findings and PFT results of patients with rPCC and APs. We retrospectively enrolled consecutive patients with rPCC who underwent unenhanced chest CT and PFTs between June 2020 and September 2022. In addition, a control group (APs) was prospectively formed and underwent nonenhanced chest CT and PFTs. The presence and extent of abnormalities in unenhanced chest CT images were evaluated qualitatively and semiquantitatively in a blinded manner. We used fully automatic software for automatic lung and airway segmentation and quantitative analyses. Sixty-three patients with rPCC and 23 APs were investigated. Reticulation/interstitial thickening and extent of parenchymal abnormalities on CT were significantly greater in the rPCC group than in the control group ( P = 0.001 and P = 0.004, respectively). Computed tomography extent score was significantly related to length of hospital stay, age, and intensive care unit stay (all P s ≤ 0.006). The rPCC group also had a lower 85th percentile attenuation lung volume ( P = 0.037). The extent of parenchymal abnormalities was significantly correlated with carbon monoxide diffusing capacity ( r = -0.406, P = 0.001), forced vital capacity (FVC) ( r = -0.342, P = 0.002), and forced expiratory volume in 1 second/FVC ( r = 0.427, P < 0.001) values. Pulmonary function tests revealed significantly lower carbon monoxide diffusing capacity ( P < 0.001), FVC ( P = 0.036), and total lung capacity ( P < 0.001) values in the rPCC group. The rPCC is characterized by impaired PFTs, a greater extent of lung abnormalities on CT, and decreased 85th percentile attenuation lung volume. Advanced age, intensive care unit admission history, and extended hospital stay are risk factors for chest CT abnormalities.

Towards Connectivity-Aware Pulmonary Airway Segmentation.

Detailed pulmonary airway segmentation is a clinically important task for endobronchial intervention and treatment of peripheral pulmonary lesions. Convolutional Neural Networks (CNNs) are promising for automated analysis of medical imaging, which however performs poorly on airway segmentation. Specifically, breakage of small bronchi distals cannot be effectively eliminated in the prediction results of CNNs, which is detrimental to use as a reference for bronchoscopic-assisted surgery. In this paper, we proposed a connectivity-aware segmentation framework to improve the performance of airway segmentation. A Connectivity-Aware Surrogate (CAS) module is first proposed to balance the training progress within-class distribution. Furthermore, a Local-Sensitive Distance (LSD) module is designed to identify the breakage and minimize the variation of the distance map between the prediction and ground-truth. The proposed method is validated with the publically available reference airway segmentation datasets. The detected rate of branch and length on public EXACT'09 and BAS datasets are 82.1%/79.6% and 96.5%/91.5% respectively, demonstrating the effectiveness of the method in terms of improving the connectedness of the segmentation performance. The source code is available at: https://github.com/Puzzled-Hui/Connectivity-Aware-Airway-Segmentation.

Review of various vessels and airway segmentation in medical imaging

Review of various vessels and airway segmentation in medical imaging

Accurate Airway Tree Segmentation in CT Scans via Anatomy-aware Multi-class Segmentation and Topology-guided Iterative Learning.

Intrathoracic airway segmentation in computed tomography is a prerequisite for various respiratory disease analyses such as chronic obstructive pulmonary disease, asthma and lung cancer. Due to the low imaging contrast and noises execrated at peripheral branches, the topological-complexity and the intra-class imbalance of airway tree, it remains challenging for deep learning-based methods to segment the complete airway tree (on extracting deeper branches). Unlike other organs with simpler shapes or topology, the airway's complex tree structure imposes an unbearable burden to generate the "ground truth" label (up to 7 or 3 hours of manual or semi-automatic annotation per case). Most of the existing airway datasets are incompletely labeled/annotated, thus limiting the completeness of computer-segmented airway. In this paper, we propose a new anatomy-aware multi-class airway segmentation method enhanced by topology-guided iterative self-learning. Based on the natural airway anatomy, we formulate a simple yet highly effective anatomy-aware multi-class segmentation task to intuitively handle the severe intra-class imbalance of the airway. To solve the incomplete labeling issue, we propose a tailored iterative self-learning scheme to segment toward the complete airway tree. For generating pseudo-labels to achieve higher sensitivity (while retaining similar specificity), we introduce a novel breakage attention map and design a topology-guided pseudo-label refinement method by iteratively connecting breaking branches commonly existed from initial pseudo-labels. Extensive experiments have been conducted on four datasets including two public challenges. The proposed method achieves the top performance in both EXACT'09 challenge using average score and ATM'22 challenge on weighted average score. In a public BAS dataset and a private lung cancer dataset, our method significantly improves previous leading approaches by extracting at least (absolute) 6.1% more detected tree length and 5.2% more tree branches, while maintaining comparable precision.

Impact of reconstruction algorithms on the success rate and quality of automatic airway segmentation in children under ultra-low-dose chest CT scanning

Impact of reconstruction algorithms on the success rate and quality of automatic airway segmentation in children under ultra-low-dose chest CT scanning

Robust Airway Generation Labeling with Airway Segmentation for Reliable Airway Assessment

Robust Airway Generation Labeling with Airway Segmentation for Reliable Airway Assessment

Obstructive sleep apnoea-hypopnoea syndrome.

Obstructive sleep apnoea-hypopnoea syndrome (OSAHS) is a common disorder characterised by repetitive episodes of the complete or partial collapse of the pharyngeal airway during sleep. This results in cessation (apnoea) or reduction (hypopnoea) of airflow, leading to oxygen desaturation and sleep fragmentation. An individual's disposition to develop OSAHS depends on the collapsibility of a segment of the upper airway. The degree of collapsibility can be quantified by the balance between occluding or extraluminal pressures of the surrounding tissues. Patients can experience snoring, unrefreshing sleep, witnessed apnoeas, waking with a choking sensation and excessive daytime sleepiness. OSAHS has a broad range of consequences, including cardiovascular, metabolic, and neurocognitive sequelae. Treatment options include lifestyle measures, in particular weight loss, and strategies to maintain upper airway patency overnight, including continuous positive airway pressure, mandibular advancement devices and positional modifiers.

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/).

Are multi-detector computed tomography and cone-beam computed tomography exams and software accurate to measure the upper airway? A systematic review.

Cone-beam computed tomography (CBCT) has several applications in various fields of dental medicine such as diagnosis and treatment planning. When compared to computed tomography (CT), CBCT's radiation exposure dose is decreased by 3%-20%. However, CBCT produces more scattered signals and may present poorer image quality when compared to medical CT. To review the findings regarding the accuracy of multi-detector computed tomography (MDCT) and CBCT and to compare the different software programs that segment the upper airway. Three databases (PubMed, Medline, and Web of Science) were searched for articles and a manual search was performed. The inclusion criteria were defined following the PICO framework: P-any patient with a CBCT or CT; I-dimensional evaluation of the upper airway using MDCT or CBCT; C-phantoms; O-the primary outcome was MDCT and CBCT accuracy, the secondary outcome was the evaluation and comparison of software programs used to segment the upper airway. Articles that met eligibility criteria were assessed using the Critical Appraisal Skills Program Checklist. Among the 16 eligible studies, 6 articles referred to the accuracy of MDCTs or CBCTs and 10 to the accuracy of the software. Most articles were qualified as high quality. MDCT and CBCT scans' accuracy in upper airway dimensional measurements depends on machine brand, parameters, and segmentation technique. Regarding the segmentation technique, 12 programs were studied. Most either underestimated or overestimated upper airway measurements. In particular, OnDemand3D and INVIVO showed poor accuracy. On the contrary, Invesalius, and MIMICS were accurate in assessing nasal cavities when using an interactive threshold. However, results varied due to methodological differences among the studies. Finally, fully automatic segmentation based on artificial intelligence may represent the future of airway segmentation because it is faster and seems to be accurate. However, further studies are necessary. This study was registered in Prospero (International Prospective Register of Systematic Reviews) with the ID number CRD42022373998.

Adversarial Transformer for Repairing Human Airway Segmentation.

Automated airway segmentation models often suffer from discontinuities in peripheral bronchioles, which limits their clinical applicability. Furthermore, data heterogeneity across different centres and pathological abnormalities pose significant challenges to achieving accurate and robust segmentation in distal small airways. Accurate segmentation of airway structures is essential for the diagnosis and prognosis of lung diseases. To address these issues, we propose a patch-scale adversarial-based refinement network that takes in preliminary segmentation and original CT images and outputs a refined mask of the airway structure. Our method is validated on three datasets, including healthy cases, pulmonary fibrosis, and COVID-19 cases, and quantitatively evaluated using seven metrics. Our method achieves more than a 15% increase in the detected length ratio and detected branch ratio compared to previously proposed models, demonstrating its promising performance. The visual results show that our refinement approach, guided by a patch-scale discriminator and centreline objective functions, effectively detects discontinuities and missing bronchioles. We also demonstrate the generalizability of our refinement pipeline on three previous models, significantly improving their segmentation completeness. Our method provides a robust and accurate airway segmentation tool that can help improve diagnosis and treatment planning for lung diseases.

Three-dimensional evaluation of the association between tongue position and upper airway morphology in adults: A cross-sectional study.

This study aimed to evaluate the association between low tongue position (LTP) and the volume and dimensions of the nasopharyngeal, retropalatal, retroglossal, and hypopharyngeal segments of the upper airway. A total of 194 subjects, including 91 males and 103 females were divided into a resting tongue position (RTP) group and a LTP group according to their tongue position. Subjects in the LTP group were divided into four subgroups (Q1, Q2, Q3, and Q4) according to the intraoral space volume. The 3D slicer software was used to measure the volume and minimum and average cross-sectional areas of each group. Airway differences between the RTP and LTP groups were analyzed to explore the association between tongue position and the upper airway. No significant differences were found in the airway dimensions between the RTP and LTP groups. For both retropalatal and retroglossal segments, the volume and average cross-sectional area were significantly greater in the patients with extremely low tongue position. Regression analysis showed that the retroglossal airway dimensions were positively correlated with the intraoral space volume and negatively correlated with A point-nasion-B point and palatal plane to mandibular plane. Males generally had larger retroglossal and hypopharyngeal airways than females. Tongue position did not significantly influence upper airway volume or dimensions, except in the extremely LTP subgroup.

Two-stage contextual transformer-based convolutional neural network for airway extraction from CT images

Accurate airway segmentation from computed tomography (CT) images is critical for planning navigation bronchoscopy and realizing a quantitative assessment of airway-related chronic obstructive pulmonary disease (COPD). Existing methods face difficulty in airway segmentation, particularly for the small branches of the airway. These difficulties arise due to the constraints of limited labeling and failure to meet clinical use requirements in COPD. We propose a two-stage framework with a novel 3D contextual transformer for segmenting the overall airway and small airway branches using CT images. The method consists of two training stages sharing the same modified 3D U-Net network. The novel 3D contextual transformer block is integrated into both the encoder and decoder path of the network to effectively capture contextual and long-range information. In the first training stage, the proposed network segments the overall airway with the overall airway mask. To improve the performance of the segmentation result, we generate the intrapulmonary airway branch label, and train the network to focus on producing small airway branches in the second training stage. Extensive experiments were performed on in-house and multiple public datasets. Quantitative and qualitative analyses demonstrate that our proposed method extracts significantly more branches and longer lengths of the airway tree while accomplishing state-of-the-art airway segmentation performance. The code is available at https://github.com/zhaozsq/airway_segmentation.

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

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. 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. 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 1secondand forced vital capacity (P<.05). 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.