D. Koechner et al., SEGMENTATION OF SMALL STRUCTURES IN MR-IMAGES - SEMIAUTOMATED TISSUE HYDRATION MEASUREMENT, Journal of magnetic resonance imaging, 5(3), 1995, pp. 347-351
Segmentation of small anatomic structures in noisy magnetic resonance
(MR) images is inherently challenging because the edge information is
contained in the same high-frequency image component as the noise. The
authors overcame this obstacle in the analysis of the sural nerve in
the ankle by processing images to reduce noise and extracting edges wi
th an edge detection algorithm less sensitive to noise. Anatomic accur
acy of the segmentation was confirmed by a neuroradiologist. A nerve h
ydration coefficient was determined from the signal intensity of the n
erve in these segmented images. These semiautomated measurements of hy
dration agreed closely with those obtained with a previously described
manual method (n = 44, P = .76). Each image in the study was analyzed
identically, with no modification of the computer algorithm parameter
s. The data suggest that this robust method may be useful in a multice
nter evaluation of diabetes treatment protocols.