1
|
Støverud KH, Bouget D, Pedersen A, Leira HO, Amundsen T, Langø T, Hofstad EF. AeroPath: An airway segmentation benchmark dataset with challenging pathology and baseline method. PLoS One 2024; 19:e0311416. [PMID: 39356679 PMCID: PMC11446458 DOI: 10.1371/journal.pone.0311416] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2024] [Accepted: 09/12/2024] [Indexed: 10/04/2024] Open
Abstract
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.
Collapse
Affiliation(s)
| | - David Bouget
- Department of Health Research, SINTEF, Trondheim, Norway
| | - André Pedersen
- Department of Health Research, SINTEF, Trondheim, Norway
- Sopra Steria, Application Solutions, Trondheim, Norway
| | - Håkon Olav Leira
- Department of Thoracic Medicine, St. Olavs Hospital, Trondheim, Norway
| | - Tore Amundsen
- Department of Thoracic Medicine, St. Olavs Hospital, Trondheim, Norway
| | - Thomas Langø
- Department of Health Research, SINTEF, Trondheim, Norway
- Department of Research, St. Olavs Hospital, Trondheim, Norway
| | | |
Collapse
|
2
|
Zhang Q, Li J, Nan X, Zhang X. Detail-sensitive 3D-UNet for pulmonary airway segmentation from CT images. Med Biol Eng Comput 2024:10.1007/s11517-024-03169-x. [PMID: 39017831 DOI: 10.1007/s11517-024-03169-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2024] [Accepted: 07/06/2024] [Indexed: 07/18/2024]
Abstract
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 .
Collapse
Affiliation(s)
- Qin Zhang
- School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, 510000, China
| | - Jiajie Li
- School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, 510000, China
| | - Xiangling Nan
- School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, 510000, China
| | - Xiaodong Zhang
- Shenzhen Children's Hospital, Shenzhen, Guangdong, 518000, China.
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, 518000, China.
| |
Collapse
|
3
|
Yuan Y, Tan W, Xu L, Bao N, Zhu Q, Wang Z, Wang R. An end-to-end multi-scale airway segmentation framework based on pulmonary CT image. Phys Med Biol 2024; 69:115027. [PMID: 38657624 DOI: 10.1088/1361-6560/ad4300] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Accepted: 04/24/2024] [Indexed: 04/26/2024]
Abstract
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.
Collapse
Affiliation(s)
- Ye Yuan
- College of Computer Science and Engineering, Northeastern University, People's Republic of China
- Key Research Laboratory of Intelligent Computing of Medical Images, Ministry of Education, Northeastern University, People's Republic of China
| | - Wenjun Tan
- College of Computer Science and Engineering, Northeastern University, People's Republic of China
- Key Research Laboratory of Intelligent Computing of Medical Images, Ministry of Education, Northeastern University, People's Republic of China
| | - Lisheng Xu
- College of Medicine and Biological information Engineering, Northeastern University, People's Republic of China
| | - Nan Bao
- College of Medicine and Biological information Engineering, Northeastern University, People's Republic of China
| | - Quan Zhu
- The First Affiliated Hospital of Nanjing Medical University, People's Republic of China
| | - Zhe Wang
- Affiliated Zhongshan Hospital of Dalian University, People's Republic of China
| | - Ruoyu Wang
- Affiliated Zhongshan Hospital of Dalian University, People's Republic of China
| |
Collapse
|
4
|
Dudurych I, Garcia-Uceda A, Saghir Z, Tiddens HAWM, Vliegenthart R, de Bruijne M. Creating a training set for artificial intelligence from initial segmentations of airways. Eur Radiol Exp 2021; 5:54. [PMID: 34841480 PMCID: PMC8627914 DOI: 10.1186/s41747-021-00247-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Accepted: 10/04/2021] [Indexed: 12/02/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Ivan Dudurych
- Department of Radiology, University of Groningen, University Medical Centre Groningen, Groningen, Netherlands.
| | - Antonio Garcia-Uceda
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Paediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, Rotterdam, Netherlands
| | - Zaigham Saghir
- Department of Medicine, Section of Pulmonary Medicine, Herlev-Gentofte Hospital, Hellerup, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Harm A W M Tiddens
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Paediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, Rotterdam, Netherlands
| | - Rozemarijn Vliegenthart
- Department of Radiology, University of Groningen, University Medical Centre Groningen, Groningen, Netherlands
| | - Marleen de Bruijne
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
5
|
Garcia-Uceda A, Selvan R, Saghir Z, Tiddens HAWM, de Bruijne M. Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks. Sci Rep 2021; 11:16001. [PMID: 34362949 PMCID: PMC8346579 DOI: 10.1038/s41598-021-95364-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Accepted: 07/21/2021] [Indexed: 12/11/2022] Open
Abstract
This paper presents a fully automatic and end-to-end optimised airway segmentation method for thoracic computed tomography, based on the U-Net architecture. We use a simple and low-memory 3D U-Net as backbone, which allows the method to process large 3D image patches, often comprising full lungs, in a single pass through the network. This makes the method simple, robust and efficient. We validated the proposed method on three datasets with very different characteristics and various airway abnormalities: (1) a dataset of pediatric patients including subjects with cystic fibrosis, (2) a subset of the Danish Lung Cancer Screening Trial, including subjects with chronic obstructive pulmonary disease, and (3) the EXACT'09 public dataset. We compared our method with other state-of-the-art airway segmentation methods, including relevant learning-based methods in the literature evaluated on the EXACT'09 data. We show that our method can extract highly complete airway trees with few false positive errors, on scans from both healthy and diseased subjects, and also that the method generalizes well across different datasets. On the EXACT'09 test set, our method achieved the second highest sensitivity score among all methods that reported good specificity.
Collapse
Affiliation(s)
- Antonio Garcia-Uceda
- Department of Radiology and Nuclear Medicine, Erasmus MC, 3015 CE, Rotterdam, The Netherlands.
- Department of Pediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, 3015 CE, Rotterdam, The Netherlands.
| | - Raghavendra Selvan
- Department of Computer Science, University of Copenhagen, 2100, Copenhagen, Denmark
- Department of Neuroscience, University of Copenhagen, 2200, Copenhagen, Denmark
| | - Zaigham Saghir
- Department of Medicine, Section of Pulmonary Medicine, Herlev-Gentofte Hospital, Copenhagen University Hospital, 2900, Hellerup, Denmark
| | - Harm A W M Tiddens
- Department of Radiology and Nuclear Medicine, Erasmus MC, 3015 CE, Rotterdam, The Netherlands
- Department of Pediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, 3015 CE, Rotterdam, The Netherlands
| | - Marleen de Bruijne
- Department of Radiology and Nuclear Medicine, Erasmus MC, 3015 CE, Rotterdam, The Netherlands.
- Department of Computer Science, University of Copenhagen, 2100, Copenhagen, Denmark.
| |
Collapse
|
6
|
Nardelli P, Ross JC, San José Estépar R. Generative-based airway and vessel morphology quantification on chest CT images. Med Image Anal 2020; 63:101691. [PMID: 32294604 DOI: 10.1016/j.media.2020.101691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2019] [Revised: 03/09/2020] [Accepted: 03/13/2020] [Indexed: 10/24/2022]
Abstract
Accurately and precisely characterizing the morphology of small pulmonary structures from Computed Tomography (CT) images, such as airways and vessels, is becoming of great importance for diagnosis of pulmonary diseases. The smaller conducting airways are the major site of increased airflow resistance in chronic obstructive pulmonary disease (COPD), while accurately sizing vessels can help identify arterial and venous changes in lung regions that may determine future disorders. However, traditional methods are often limited due to image resolution and artifacts. We propose a Convolutional Neural Regressor (CNR) that provides cross-sectional measurement of airway lumen, airway wall thickness, and vessel radius. CNR is trained with data created by a generative model of synthetic structures which is used in combination with Simulated and Unsupervised Generative Adversarial Network (SimGAN) to create simulated and refined airways and vessels with known ground-truth. For validation, we first use synthetically generated airways and vessels produced by the proposed generative model to compute the relative error and directly evaluate the accuracy of CNR in comparison with traditional methods. Then, in-vivo validation is performed by analyzing the association between the percentage of the predicted forced expiratory volume in one second (FEV1%) and the value of the Pi10 parameter, two well-known measures of lung function and airway disease, for airways. For vessels, we assess the correlation between our estimate of the small-vessel blood volume and the lungs' diffusing capacity for carbon monoxide (DLCO). The results demonstrate that Convolutional Neural Networks (CNNs) provide a promising direction for accurately measuring vessels and airways on chest CT images with physiological correlates.
Collapse
Affiliation(s)
- Pietro Nardelli
- Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA.
| | - James C Ross
- Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Raúl San José Estépar
- Applied Chest Imaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA
| |
Collapse
|
7
|
Matsumura K, Kurachi T, Ishikawa S, Kitamura N, Ito S. Regional differences in airway susceptibility to cigarette smoke: An investigational case study of epithelial function and gene alterations in in vitroairway epithelial three-dimensional cultures. TOXICOLOGY RESEARCH AND APPLICATION 2020. [DOI: 10.1177/2397847320911629] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Cigarette smoke (CS) is a risk factor contributing to lung remodeling in chronic obstructive pulmonary disease (COPD). COPD is a heterogeneous disease because many factors contribute in varying degrees to the resulting airflow limitations in different regions of the respiratory tract. This heterogeneity makes it difficult to understand mechanisms behind COPD development. In the current study, we investigate the regional heterogeneity of the acute response to CS exposure between large and small airways using in vitro three-dimensional (3D) cultures. We used two in vitro 3D human airway epithelial tissues from large and small airway epithelial cells, namely, MucilAir™ and SmallAir™, respectively, which were derived from the same single healthy donor to eliminate donor differences. Impaired epithelial functions and altered gene expression were observed in SmallAir™ exposed to CS at the lower dose and earlier period following the last exposure compared with MucilAir™. In addition, severe damage in SmallAir™ was retained for a longer duration than MucilAir™. Transcriptomic analysis showed that although well-known CS-inducible biological processes (i.e. inflammation, cell fate, and metabolism) were disturbed with consistent activity in both tissues exposed to CS, we elucidated distinctively regulated genes in only MucilAir™ and SmallAir™, which were mostly related to catalytic and transporter activities. Our findings suggest that CS exposure elicited epithelial dysfunction through almost the same perturbed pathways in both airways; however, they expressed different genes related to metabolic and transporter activities in response to CS exposure which may contribute to cytotoxic heterogeneity to the response to CS in the respiratory tract.
Collapse
Affiliation(s)
- Kazushi Matsumura
- Scientific Product Assessment Center, R&D Group, Japan Tobacco Inc., Yokohama, Kanagawa, Japan
| | - Takeshi Kurachi
- Scientific Product Assessment Center, R&D Group, Japan Tobacco Inc., Yokohama, Kanagawa, Japan
| | - Shinkichi Ishikawa
- Scientific Product Assessment Center, R&D Group, Japan Tobacco Inc., Yokohama, Kanagawa, Japan
| | - Nobumasa Kitamura
- Scientific Product Assessment Center, R&D Group, Japan Tobacco Inc., Yokohama, Kanagawa, Japan
| | - Shigeaki Ito
- Scientific Product Assessment Center, R&D Group, Japan Tobacco Inc., Yokohama, Kanagawa, Japan
| |
Collapse
|
8
|
Quan K, Tanno R, Shipley RJ, Brown JS, Jacob J, Hurst JR, Hawkes DJ. Reproducibility of an airway tapering measurement in computed tomography with application to bronchiectasis. J Med Imaging (Bellingham) 2019; 6:034003. [PMID: 31548977 PMCID: PMC6745534 DOI: 10.1117/1.jmi.6.3.034003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2019] [Accepted: 08/23/2019] [Indexed: 11/14/2022] Open
Abstract
We propose a pipeline to acquire a scalar tapering measurement from the carina to the most distal point of an individual airway visible on computed tomography (CT). We show the applicability of using tapering measurements on clinically acquired data by quantifying the reproducibility of the tapering measure. We generate a spline from the centerline of an airway to measure the area and arclength at contiguous intervals. The tapering measurement is the gradient of the linear regression between area in log space and arclength. The reproducibility of the measure was assessed by analyzing different radiation doses, voxel sizes, and reconstruction kernel on single timepoint and longitudinal CT scans and by evaluating the effect of airway bifurcations. Using 74 airways from 10 CT scans, we show a statistical difference, p = 3.4 × 10 - 4 , in tapering between healthy airways ( n = 35 ) and those affected by bronchiectasis ( n = 39 ). The difference between the mean of the two populations is 0.011 mm - 1 , and the difference between the medians of the two populations was 0.006 mm - 1 . The tapering measurement retained a 95% confidence interval of ± 0.005 mm - 1 in a simulated 25 mAs scan and retained a 95% confidence of ± 0.005 mm - 1 on simulated CTs up to 1.5 times the original voxel size. We have established an estimate of the precision of the tapering measurement and estimated the effect on precision of the simulated voxel size and CT scan dose. We recommend that the scanner calibration be undertaken with the phantoms as described, on the specific CT scanner, radiation dose, and reconstruction algorithm that are to be used in any quantitative studies.
Collapse
Affiliation(s)
- Kin Quan
- University College London, Center for Medical Image Computing, London, United Kingdom
| | - Ryutaro Tanno
- University College London, Center for Medical Image Computing, London, United Kingdom
| | - Rebecca J. Shipley
- University College London, Department of Mechanical Engineering, London, United Kingdom
| | - Jeremy S. Brown
- University College London, UCL Respiratory, London, United Kingdom
| | - Joseph Jacob
- University College London, Center for Medical Image Computing, London, United Kingdom
- University College London, UCL Respiratory, London, United Kingdom
| | - John R. Hurst
- University College London, UCL Respiratory, London, United Kingdom
| | - David J. Hawkes
- University College London, Center for Medical Image Computing, London, United Kingdom
| |
Collapse
|