|
Impact of reconstruction algorithms on the success rate and quality of automatic airway segmentation in children under ultra-low-dose chest CT scanning
|
J. Sun   , H. Li , Z. Liu , S. Wang , Y. Peng |
| Department of Radiology, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing 100045, China , ppengyun@hotmail.com |
|
|
Abstract: (570 Views) |
Background: To investigate the success rate and quality of automatic airway segmentation using ultra-low dose CT (ULD-CT) images of different reconstruction algorithms. Materials and Methods: Fifty two children who underwent chest ULD-CT were divided into three groups for analysis based on age: group A (n=13, age, 1-2years), group B (n=19, age, 3-6years) and group C (n=20, age, 7-13years). CT images were reconstructed with filtered back-projection (FBP), 50% adaptive statistical iterative reconstruction-Veo (50%ASIR-V), 100%ASIR-V, deep learning image reconstruction (DLIR) with low (DLIR-L), medium (DLIR-M), and high (DLIR-H) strengths. Subjective image quality was evaluated using a 5-point scale. CT value, noise, and sharpness of the trachea were measured. The VCAR software was used to automatically segment airways and reported the total volume. Segmentation success rates were recorded, and segmentation images were subjectively evaluated using a 6-point scale. Results: The average tracheal diameters were 8.53±1.88mm, 10.69±1.65mm, and 12.72±1.97mm, respectively for groups A, B, and C. The segmentation success rate depended on patient groups: group C reached 100%, while group A decreased significantly. In group A, 100%ASIR-V had the lowest rate at 7.69%, while DLIR-M and DLIR-H significantly improved the rate to 38.64% (P=0.03). For the segmented images, DLIR-H provided the lowest noise and highest subjective score while FBP images had the highest noise and 100%ASIR-V had the lowest overall score (P<0.05). There was no significant difference in the total airway volume among the six reconstructions. Conclusion: The airway segmentation success rate in ULD-CT for children depends on the tracheal size. DLIR improves airway segmentation success rate and image quality. |
|
| Keywords: CT, pediatrics, deep learning, image processing, computer-assisted. |
|
|
Full-Text [PDF 683 kb]
(294 Downloads)
|
|
Type of Study: Original Research |
Subject:
Radiation Biology
|
|
|
|
|
|
|
| References |
1. 1. Sun J, Chen C, Peng Y, et al. (2019) Comparison of magnetic resonance imaging and computed tomography to measure preoperative parameters of children with pectus excavatum. Pediatric Investigation, 3(2): 102-109. [ DOI:10.1002/ped4.12132] 2. He M, Wang C, Xu L, et al. (2020) Epidemiological and clinical characteristics of 35 children with COVID-19 in Beijing, China. Pediatric Investigation, 4(4): 230-235. [ DOI:10.1002/ped4.12230] 3. Ye Z, Zhang Y, Wang Y, et al. (2020) Chest CT manifestations of new coronavirus disease 2019 (COVID-19): a pictorial review. European radiology, 30(8): 4381-4389. [ DOI:10.1007/s00330-020-06801-0] 4. Yun J, Cho YH, Lee SM, et al. (2021) Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease. Scientific Reports, 11(1): 15144. [ DOI:10.1038/s41598-021-94535-4] 5. Tanabe N, Sato S, Oguma T, et al. (2019) Associations of airway tree to lung volume ratio on computed tomography with lung function and symptoms in chronic obstructive pulmonary disease. Respiratory Research, 20(1): 77. [ DOI:10.1186/s12931-019-1047-5] 6. Kan CNE, Gilat-Schmidt T, Ye DH (2021) Enhancing reproductive organ segmentation in pediatric CT via adversarial learning. Proceedings of SPIE--the International Society for Optical Engineering, 11596: 1159612. [ DOI:10.1117/12.2582127] 7. Shujaat S, Jazil O, Willems H, et al. (2021) Automatic segmentation of the pharyngeal airway space with convolutional neural network. Journal of Dentistry, 111: 103705. [ DOI:10.1016/j.jdent.2021.103705] 8. Handa T, Tanizawa K, Oguma T, et al. (2022) Novel artificial intelligence-based technology for chest computed tomography analysis of idiopathic pulmonary fibrosis. Annals of the American Thoracic Society, 19(3): 399-406. [ DOI:10.1513/AnnalsATS.202101-044OC] 9. Garrett Fernandes M, Bussink J, Stam B, et al. (2021) Deep learning model for automatic contouring of cardiovascular substructures on radiotherapy planning CT images: Dosimetric validation and reader study based clinical acceptability testing. Radiotherapy and oncology: Journal of the European Society for Therapeutic Radiology and Oncology, 165: 52-59. [ DOI:10.1016/j.radonc.2021.10.008] 10. Fischer AM, Varga-Szemes A, van Assen M, et al. (2020) Comparison of artificial intelligence-based fully automatic chest ct emphysema quantification to pulmonary function testing. AJR. American Journal of Roentgenology, 214(5): 1065-1071. [ DOI:10.2214/AJR.19.21572] 11. Nambu A, Zach J, Schroeder J, et al. (2016) Quantitative computed tomography measurements to evaluate airway disease in chronic obstructive pulmonary disease: Relationship to physiological measurements, clinical index and visual assessment of airway disease. European Journal of Radiology, 85(11): 2144-2151. [ DOI:10.1016/j.ejrad.2016.09.010] 12. Kirby M, Tanabe N, Tan WC, et al. (2018) CanCOLD collaborative research group, Canadian respiratory research network, & CanCOLD collaborative research group, the Canadian respiratory research network (2018). Total airway count on computed tomography and the risk of chronic obstructive pulmonary disease progression. Findings from a population-based study. American Journal of Respiratory and Critical Care Medicine, 197(1): 56-65. 13. Mao L, Chen H, Liang M, et al. (2019) Quantitative radiomic model for predicting malignancy of small solid pulmonary nodules detected by low-dose CT screening. Quantitative Imaging in Medicine and Surgery, 9(2): 263-272. [ DOI:10.21037/qims.2019.02.02] 14. Sun J, Li H, Li J, et al. (2021) Performance evaluation of using shorter contrast injection and 70 kVp with deep learning image reconstruction for reduced contrast medium dose and radiation dose in coronary CT angiography for children: a pilot study. Quantitative Imaging in Medicine and Surgery, 11(9), 4162-4171. [ DOI:10.21037/qims-20-1159] 15. Sun J, Li H, Li J, et al. (2021) Improving the image quality of pediatric chest CT angiography with low radiation dose and contrast volume using deep learning image reconstruction. Quantitative Imaging in Medicine and Surgery, 11(7): 3051-3058. [ DOI:10.21037/qims-20-1158] 16. Park C, Choo KS, Jung Y, et al. (2021) CT iterative vs deep learning reconstruction: comparison of noise and sharpness. European Radiology, 31(5): 3156-3164. [ DOI:10.1007/s00330-020-07358-8] 17. Almén A, Guðjónsdóttir J, Heimland N,et al. (2022). Paediatric diagnostic reference levels for common radiological examinations using the European guidelines. The British journal of radiology, 95(1130): 20210700. [ DOI:10.1259/bjr.20210700] 18. Wei X, Chen X, Lai C, et al. (2021) Automatic liver segmentation in CT images with enhanced GAN and mask region-based CNN architectures. BioMed Research International, 2021, 9956983. [ DOI:10.1155/2021/9956983] 19. Zeng G, Degonda C, Boschung A, et al. (2021) Three-dimensional magnetic resonance imaging bone models of the hip joint using deep learning: Dynamic simulation of hip impingement for diagnosis of intra- and extra-articular hip impingement. Orthopaedic Journal of Sports Medicine, 9(12): 23259671211046916. [ DOI:10.1177/23259671211046916] 20. Song J, Huang SC, Kelly B, et al. (2022) Automatic lung nodule segmentation and intra-nodular heterogeneity image generation. IEEE Journal of Biomedical and Health Informatics, 26(6): 2570-2581. [ DOI:10.1109/JBHI.2021.3135647] 21. Ko H, Huh J, Kim KW, et al. (2022). A deep residual U-net algorithm for automatic detection and quantification of ascites on abdominopelvic computed tomography images acquired in the emergency department: Model development and validation. Journal of Medical Internet Research, 24(1): e34415. [ DOI:10.2196/34415] 22. Beekman C, van Beek S, Stam J, et al. (2022) Improving predictive CTV segmentation on CT and CBCT for cervical cancer by diffeomorphic registration of a prior. Medical Physics, 49(3): 1701-1711. [ DOI:10.1002/mp.15421] 23. Huang Y, Hu G, Ji C, Xiong H (2020) Glass-cutting medical images via a mechanical image segmentation method based on crack propagation. Nat Commun, 11(1): 5669. [ DOI:10.1038/s41467-020-19392-7] 24. Jiang B, Li N, Shi X, et al. (2022) Deep learning reconstruction shows better lung nodule detection for ultra-low-dose chest CT. Radiology, 303(1): 202-212. [ DOI:10.1148/radiol.210551] 25. Sui X, Meinel FG, Song W, et al. (2016) Detection and size measurements of pulmonary nodules in ultra-low-dose CT with iterative reconstruction compared to low dose CT. European Journal of Radiology, 85(3): 564-570. [ DOI:10.1016/j.ejrad.2015.12.013] 26. Greffier J, Hamard A, Pereira F, et al. (2020) Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. European Radiology, 30(7): 3951-3959. [ DOI:10.1007/s00330-020-06724-w] |
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
|
Sun J, Li H, Liu Z, Wang S, Peng Y. Impact of reconstruction algorithms on the success rate and quality of automatic airway segmentation in children under ultra-low-dose chest CT scanning. Int J Radiat Res 2024; 22 (1) :171-177 URL: http://ijrr.com/article-1-5249-en.html
|
