Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2013 Oct;26(5):891-7.
doi: 10.1007/s10278-012-9554-7.

Adrenal gland abnormality detection using random forest classification

Ganesh Saiprasad  1 , Chein-I Chang, Nabile Safdar, Naomi Saenz, Eliot Siegel
Affiliations

Adrenal gland abnormality detection using random forest classification

Ganesh Saiprasad et al. J Digit Imaging. 2013 Oct.

Abstract

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.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Single classification tree
Fig. 2
Fig. 2
Feature, δj: fixed coupling between subvolumes F1 and F2 with respect to pixel “X”
Fig. 3
Fig. 3
Histogram of a normal adrenal and b abnormal adrenal
Fig. 4
Fig. 4
Random forest with three trees
Fig. 5
Fig. 5
Histogram of test adrenal classified to be abnormal
Fig. 6
Fig. 6
3D view of segmentation results of the adrenal glands for two cases
See this image and copyright information in PMC

References

    1. Mayo-Smith WW, Boland GW, Noto RB, Lee MJ. State-of-the-art adrenal imaging. Radiographics. 2001;21(4):995–1012. - PubMed
    1. Blake MA, Krishnamoorthy SK, Boland GW, Sweeney AT, Pitman MB, Mueller PR, Hahn PF. Low-density pheochromocytoma on CT: a mimicker of adrenal adenoma. AJR Am J Roentgenol. 2003;181:1663–1668. doi: 10.2214/ajr.181.6.1811663. - DOI - PubMed
    1. Peña CS, Boland GW, Hahn PF, Lee MJ, Mueller PR. Characterization of indeterminate (lipid-poor) adrenal masses: use of washout characteristics at contrast-enhanced CT. Radiology. 2000;211(3):629–636. - PubMed
    1. “Radiology Associates.” [Online]. Available: http://www.rasloimaging.com/for_physcians/Master Schedules/Newsletters/Feb.2012 Newsletter.pdf. Accessed 10 May 2012.
    1. Yao C, Wada T, Shimizu A, Kobatake H, Nawano S. Simultaneous location detection of multi-organ by atlas-guided eigen-organ method in volumetric medical images. Int J CARS. 2006;1:42–44.

MeSH terms

LinkOut - more resources