2026-06-14T06:44:04Zhttps://repisalud.isciii.es/rest/oai/requestoai:repisalud.isciii.es:20.500.12105/65742024-09-27T10:16:21Zcom_20.500.12105_19604com_20.500.12105_2051col_20.500.12105_19607
Repisalud
author
Gordaliza, Pedro M
author
Muñoz-Barrutia, Arrate
author
Abella, Monica
author
Desco, Manuel
author
Sharpe, Sally
author
Vaquero, Juan Jose
funder
Unión Europea
funder
Ministerio de Economía, Industria y Competitividad (España)
funder
Comunidad de Madrid (España)
2018-11-05T11:58:21Z
2018-11-05T11:58:21Z
2018
Sci Rep. 2018; 8(1):9802
10.1038/s41598-018-28100-x
2045-2322
Scientific Reports
29955159
http://hdl.handle.net/20.500.12105/6574
Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis that produces pulmonary damage. Radiological imaging is the preferred technique for the assessment of TB longitudinal course. Computer-assisted identification of biomarkers eases the work of the radiologist by providing a quantitative assessment of disease. Lung segmentation is the step before biomarker extraction. In this study, we present an automatic procedure that enables robust segmentation of damaged lungs that have lesions attached to the parenchyma and are affected by respiratory movement artifacts in a Mycobacterium Tuberculosis infection model. Its main steps are the extraction of the healthy lung tissue and the airway tree followed by elimination of the fuzzy boundaries. Its performance was compared with respect to a segmentation obtained using: (1) a semi-automatic tool and (2) an approach based on fuzzy connectedness. A consensus segmentation resulting from the majority voting of three experts' annotations was considered our ground truth. The proposed approach improves the overlap indicators (Dice similarity coefficient, 94\% +/- 4\%) and the surface similarity coefficients (Hausdorff distance, 8.64 mm +/- 7.36 mm) in the majority of the most difficult-to-segment slices. Results indicate that the refined lung segmentations generated could facilitate the extraction of meaningful quantitative data on disease burden.
eng
DISEASE PROGRESSION
LATENT TUBERCULOSIS
LEVEL
ALGORITHMS
REGRESSION
DIAGNOSIS
FRAMEWORK
MACAQUES
ACCURATE
NODULES
Unsupervised CT Lung Image Segmentation of a Mycobacterium Tuberculosis Infection Model
journal article
URL
https://repisalud.isciii.es/bitstreams/dbe989eb-01ff-4151-a62a-712d9acbd17e/download
File
MD5
a7da302a887bc4e025c81d9ca817ab58
2306437
application/pdf
UnsupervisedCTLungImage_2018.pdf
URL
https://repisalud.isciii.es/bitstreams/66476ebb-19b5-4b19-8fbc-6938fdf3a3df/download
File
MD5
c09ef02d2070a860625ff4fa58292b61
1537016
application/pdf
UnsupervisedCTLungImage_2018_suppl.pdf
URL
https://repisalud.isciii.es/bitstreams/34adcf88-11f0-415f-b0f0-b9bfbf18835c/download
File
MD5
562ea0bf448e5a8191bb592f3bdb4c94
47337
text/plain
UnsupervisedCTLungImage_2018.pdf.txt
URL
https://repisalud.isciii.es/bitstreams/6fa6b431-a1f7-4966-81a9-f35a5c575da7/download
File
MD5
a8f76c1e0b77cbacdac4607c608367d8
14051
text/plain
UnsupervisedCTLungImage_2018_suppl.pdf.txt