R. Narayanswamy et Km. Johnson, OPTOELECTRONIC REGION OF INTEREST DETECTION - AN APPLICATION IN AUTOMATED CYTOLOGY, Applied optics, 37(25), 1998, pp. 6011-6025
Diagnostic cytology, which is used to screen for cervical cancer, invo
lves characterizing cellular features such as shape, size, and texture
. Automated screening of cervical smear slides is desirable but comput
ationally challenging since each slide requires processing 2 x 10(9) p
ixels at a resolution of 0.8 mu m per pixel. We demonstrate that the t
hroughput of optical processors can be exploited in automated cervical
smear-screening systems. In particular, we identify a morphological s
hape detector to perform the initial region of interest (ROT) detectio
n and to demonstrate experimentally its optoelectronic implementation.
The ROI detector is tested on 200 images, and its performance is char
acterized as a receiver operating characteristic (ROC). The area under
the ROC curve is as high as 96.4% of the total area. The simulation a
nd the experimental results are found comparable, and the discrepancy
between the two results is determined to be a function of the number o
f bits represented in the filter plane device. (C) 1998 Optical Societ
y of America.