Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming
- PMID: 24989390
- DOI: 10.1118/1.4881096
Cavity contour segmentation in chest radiographs using supervised learning and dynamic programming
Abstract
Purpose: Efficacy of tuberculosis (TB) treatment is often monitored using chest radiography. Monitoring size of cavities in pulmonary tuberculosis is important as the size predicts severity of the disease and its persistence under therapy predicts relapse. The authors present a method for automatic cavity segmentation in chest radiographs.
Methods: A two stage method is proposed to segment the cavity borders, given a user defined seed point close to the center of the cavity. First, a supervised learning approach is employed to train a pixel classifier using texture and radial features to identify the border pixels of the cavity. A likelihood value of belonging to the cavity border is assigned to each pixel by the classifier. The authors experimented with four different classifiers:k-nearest neighbor (kNN), linear discriminant analysis (LDA), GentleBoost (GB), and random forest (RF). Next, the constructed likelihood map was used as an input cost image in the polar transformed image space for dynamic programming to trace the optimal maximum cost path. This constructed path corresponds to the segmented cavity contour in image space.
Results: The method was evaluated on 100 chest radiographs (CXRs) containing 126 cavities. The reference segmentation was manually delineated by an experienced chest radiologist. An independent observer (a chest radiologist) also delineated all cavities to estimate interobserver variability. Jaccard overlap measure Ω was computed between the reference segmentation and the automatic segmentation; and between the reference segmentation and the independent observer's segmentation for all cavities. A median overlap Ω of 0.81 (0.76 ± 0.16), and 0.85 (0.82 ± 0.11) was achieved between the reference segmentation and the automatic segmentation, and between the segmentations by the two radiologists, respectively. The best reported mean contour distance and Hausdorff distance between the reference and the automatic segmentation were, respectively, 2.48 ± 2.19 and 8.32 ± 5.66 mm, whereas these distances were 1.66 ± 1.29 and 5.75 ± 4.88 mm between the segmentations by the reference reader and the independent observer, respectively. The automatic segmentations were also visually assessed by two trained CXR readers as "excellent," "adequate," or "insufficient." The readers had good agreement in assessing the cavity outlines and 84% of the segmentations were rated as "excellent" or "adequate" by both readers.
Conclusions: The proposed cavity segmentation technique produced results with a good degree of overlap with manual expert segmentations. The evaluation measures demonstrated that the results approached the results of the experienced chest radiologists, in terms of overlap measure and contour distance measures. Automatic cavity segmentation can be employed in TB clinics for treatment monitoring, especially in resource limited settings where radiologists are not available.
Similar articles
-
Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review.Sensors (Basel). 2023 Jul 29;23(15):6781. doi: 10.3390/s23156781. Sensors (Basel). 2023. PMID: 37571564 Free PMC article. Review.
-
A review on lung boundary detection in chest X-rays.Int J Comput Assist Radiol Surg. 2019 Apr;14(4):563-576. doi: 10.1007/s11548-019-01917-1. Epub 2019 Feb 7. Int J Comput Assist Radiol Surg. 2019. PMID: 30730032 Free PMC article. Review.
-
Automatic detection of pleural effusion in chest radiographs.Med Image Anal. 2016 Feb;28:22-32. doi: 10.1016/j.media.2015.09.004. Epub 2015 Dec 1. Med Image Anal. 2016. PMID: 26688067
-
Computer-aided detection and quantification of cavitary tuberculosis from CT scans.Med Phys. 2013 Nov;40(11):113701. doi: 10.1118/1.4824979. Med Phys. 2013. PMID: 24320475 Free PMC article.
-
Automated lung segmentation in digital chest tomosynthesis.Med Phys. 2012 Feb;39(2):732-41. doi: 10.1118/1.3671939. Med Phys. 2012. PMID: 22320783 Free PMC article.
Cited by
-
Utility of Machine Learning and Radiomics Based on Cavity for Predicting the Therapeutic Response of MDR-TB.Infect Drug Resist. 2023 Oct 28;16:6893-6904. doi: 10.2147/IDR.S435984. eCollection 2023. Infect Drug Resist. 2023. PMID: 37920476 Free PMC article.
-
Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis: a multicentre study.Eur Radiol. 2023 Jan;33(1):391-400. doi: 10.1007/s00330-022-08997-9. Epub 2022 Jul 19. Eur Radiol. 2023. PMID: 35852573 Free PMC article.
-
Impact of anemia on prognosis in tuberculosis patients.Ann Transl Med. 2022 Mar;10(6):329. doi: 10.21037/atm-22-679. Ann Transl Med. 2022. PMID: 35433932 Free PMC article.
-
Quantification of Pulmonary Inflammatory Processes Using Chest Radiography: Tuberculosis as the Motivating Application.Medicine (Baltimore). 2015 Jul;94(26):e1044. doi: 10.1097/MD.0000000000001044. Medicine (Baltimore). 2015. PMID: 26131814 Free PMC article. Clinical Trial.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical