Abstract
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.
Highlights
The classic view of TB as latent or active is inadequate
The second best-performing method, the fuzzy connectedness lung segmentation (FC), which was intended for the segmentation of slightly infected lungs, presents a close mean Dice similarity coefficient (DSC) but more distant median DSC
We present a novel method for the automatic unsupervised segmentation of Mtb-infected lungs on chest computed tomography (CT) volumes
Summary
The classic view of TB as latent or active is inadequate. Recent literature shows that TB manifests as a continuous spectrum between both states[2,4]. CT image acquisition in TB animal models is usually performed on free-breathing animals to avoid the additional level of complexity added by the intubation in the manipulation of the animal, resulting in the presence of significant respiratory motion artifacts This effect produces fuzzy boundaries, especially in the diaphragm area (Fig. 1), implying an uncertain delimitation of the lungs beyond the segmentation technique used. Most of the state-of-the-art methods for automatic lung segmentation are not designed to deal with the specific problems present in Mtb-infected lungs under the presence of strong respiratory motion artifacts[15] They generally are not able to differentiate between the neighboring soft tissue and the lesions attached to the pleura since their density (Hounsfield Units) is similar[16]. The more recent approaches, which are mostly based on supervised learning methods[21], require a large dataset labeled by an expert to ensure appropriate training and are not free from bias
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
