Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models.
Summary of "Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models."
Accurate segmentation of a pulmonary nodule is an important and active area of research in medical image processing. Although many algorithms have been reported in literature for this problem, those that are applicable to various density types have not been available until recently. In this paper, we propose a new algorithm that is applicable to solid, non-solid and part-solid types and solitary, vascularized, and juxtapleural types. First, the algorithm separates lung parenchyma and radiographically denser anatomical structures with coupled competition and diffusion processes. The technique tends to derive a spatially more homogeneous foreground map than an adaptive thresholding based method. Second, it locates the core of a nodule in a manner that is applicable to juxtapleural types using a transformation applied on the Euclidean distance transform of the foreground. Third, it detaches the nodule from attached structures by a region growing on the Euclidean distance map followed by a procedure to delineate the surface of the nodule based on the patterns of the region growing and distance maps. Finally, convex hull of the nodule surface intersected with the foreground constitutes the final segmentation. The performance of the technique is evaluated with two Lung Imaging Database Consortium (LIDC) data sets with 23 and 82 nodules each, and another data set with 820 nodules with manual diameter measurements. The experiments show that the algorithm is highly reliable in segmenting nodules of various types in a computationally efficient manner.
Affiliation
Mathematical Sciences, Susquehanna University, Selinsgrove, PA 17870, USA.
Journal Details
This article was published in the following journal.
Name: Medical image analysis
ISSN: 1361-8423
Pages:
Links
- PubMed Source: http://www.ncbi.nlm.nih.gov/pubmed/20863740
- DOI: http://dx.doi.org/10.1016/j.media.2010.08.005
Medical and Biotech [MESH] Definitions
Multiple Pulmonary Nodules
A number of small lung lesions characterized by small round masses of 2- to 3-mm in diameter. They are usually detected by chest CT scans (COMPUTED TOMOGRAPHY, X-RAY). Such nodules can be associated with metastases of malignancies inside or outside the lung, benign granulomas, or other lesions.
Pulmonary Heart Disease
Hypertrophy and dilation of the RIGHT VENTRICLE of the heart that is caused by PULMONARY HYPERTENSION. This condition is often associated with pulmonary parenchymal or vascular diseases, such as CHRONIC OBSTRUCTIVE PULMONARY DISEASE and PULMONARY EMBOLISM.
Pulmonary Edema
Excessive accumulation of extravascular fluid in the lung, an indication of a serious underlying disease or disorder. Pulmonary edema prevents efficient PULMONARY GAS EXCHANGE in the PULMONARY ALVEOLI, and can be life-threatening.
Pulmonary Subvalvular Stenosis
Narrowing below the PULMONARY VALVE or well below it in the infundibuluar chamber where the pulmonary artery originates, usually caused by a defective VENTRICULAR SEPTUM or presence of fibrous tissues. It is characterized by restricted blood outflow from the RIGHT VENTRICLE into the PULMONARY ARTERY, exertional fatigue, DYSPNEA, and chest discomfort.
Pulmonary Valve Insufficiency
Backflow of blood from the PULMONARY ARTERY into the RIGHT VENTRICLE due to imperfect closure of the PULMONARY VALVE.
PubMed Articles
PURPOSE: Pulmonary nodules may indicate the early stage of lung cancer, and the progress of lung cancer causes associated changes in the shape and number of pulmonary blood vessels. The automatic segm...
Effects of Different Reconstruction Parameters on CT Volumetric Measurement of Pulmonary Nodules.
It has been proven that volumetric measurements could detect subtle changes in small pulmonary nodules in serial CT scans, and thus may play an important role in the follow-up of indeterminate pulmona...
AIM: To determine the impact of an additional inspiration CT scan on the conventional (18)F-FDG PET-CT protocol in the detection of small pulmonary nodules. METHOD: One hundred consecutive patients wh...
Pulmonary necrotizing sarcoid granulomatosis in a patient with primary biliary cirrhosis.
HISTORY AND ADMISSION FINDINGS: A 53-year-old woman presented with recurrent episodes of cough and non-specific pulmonary symptoms. For many years she had been known to have primary biliary cirrhosis....
PURPOSE: To determine the frequency and significance of pulmonary nodules detected on thin-section CT in patients with extrapulmonary malignant neoplasms. MATERIALS AND METHODS: The institutional revi...
Clinical Trials
3-D Reconstruction of CT Scan Images in the Evaluation of Non-Specific Pulmonary Nodules
In recent years, more and more people are having lung CT scans performed to screen for various cancers. Many of them have small abnormalities detected, called "nodules", which - for a vari...
Comparative Evaluation of MRI and MDCT for the Detection of Metastic Pulmonary Nodules
The purpose of this study is to apply the techniques of dynamic MRI imaging enhancement to research participants with one or more pulmonary nodule to determine if meaningful information ab...
Because the management of children with solid tumors hinges on the extent of disease, it is crucial to identify metastatic sites. Helical chest computed tomography (CT) is the standard met...
RATIONALE: Imaging procedures, such as fludeoxyglucose F 18 (FDG)-PET/CT scan, done before and after steroid therapy may help doctors assess a patient's response to treatment and help plan...
Biomarkers for Diagnosis of Lung Nodules
A need exists for non-invasive testing to aid in clinical decision-making for CT scan detected lung nodules of indeterminate etiology. The investigators hypothesize that biomarkers detect...
