Document Detail

Adrenal gland abnormality detection using random forest classification.
MedLine Citation:
PMID:  23344259     Owner:  NLM     Status:  MEDLINE    
Adrenal abnormalities are commonly identified on computed tomography (CT) and are seen in at least 5 % of CT examinations of the thorax and abdomen. Previous studies have suggested that evaluation of Hounsfield units within a region of interest or a histogram analysis of a region of interest can be used to determine the likelihood that an adrenal gland is abnormal. However, the selection of a region of interest can be arbitrary and operator dependent. We hypothesize that segmenting the entire adrenal gland automatically without any human intervention and then performing a histogram analysis can accurately detect adrenal abnormality. We use the random forest classification framework to automatically perform a pixel-wise classification of an entire CT volume (abdomen and pelvis) into three classes namely right adrenal, left adrenal, and background. Once we obtain this classification, we perform histogram analysis to detect adrenal abnormality. The combination of these methods resulted in a sensitivity and specificity of 80 and 90 %, respectively, when analyzing 20 adrenal glands seen on volumetric CT datasets for abnormality.
Ganesh Saiprasad; Chein-I Chang; Nabile Safdar; Naomi Saenz; Eliot Siegel
Related Documents :
20566809 - Pulmonary nodules: contrast-enhanced volumetric variation at different ct scan delays.
22865269 - Helical ct-enteroclysis in the detection of small-bowel tumours: a meta-analysis.
2372459 - Comparison of non-enhanced, bolus enhanced, and delayed scanning techniques in computed...
16134309 - Correlative study of angiogenesis and dynamic contrast-enhanced magnetic resonance imag...
23344259 - Adrenal gland abnormality detection using random forest classification.
19964849 - Manganese-enhanced mri of hypoxic-ischemic brain injuries using mn-dpdp.
3872559 - Improved mr imaging of the orbit at 1.5 t with surface coils.
12553659 - Solid and papillary epithelial neoplasm of the pancreas: mr imaging findings.
17026659 - Mechanobiology and force transduction in scars developed in darker skin types.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of digital imaging     Volume:  26     ISSN:  1618-727X     ISO Abbreviation:  J Digit Imaging     Publication Date:  2013 Oct 
Date Detail:
Created Date:  2013-09-25     Completed Date:  2014-04-25     Revised Date:  2014-10-12    
Medline Journal Info:
Nlm Unique ID:  9100529     Medline TA:  J Digit Imaging     Country:  United States    
Other Details:
Languages:  eng     Pagination:  891-7     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Adrenal Glands / abnormalities*,  radiography*
Cone-Beam Computed Tomography / methods*
Image Processing, Computer-Assisted / methods*
Radiographic Image Interpretation, Computer-Assisted / methods*
Reproducibility of Results
Sensitivity and Specificity

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  The discriminatory capacity of BMD measurements by DXA and dual X-ray and laser (DXL) at the calcane...
Next Document:  Using the Microsoft Kinect for patient size estimation and radiation dose normalization: proof of co...