Jj. Berman et Gw. Moore, IMAGE-ANALYSIS SOFTWARE FOR THE DETECTION OF PRENEOPLASTIC AND EARLY NEOPLASTIC LESIONS, Cancer letters, 77(2-3), 1994, pp. 103-109
Preneoplastic lesions are usually small, and often appear as foci of a
typical cells that blend into the surrounding normal tissue without pr
oducing a detectable tumor mass. Since these lesions seldom provide ad
equate tissue for biochemical studies, their detection often depends u
pon subtle distinctions in cytologic features. Image analysis permits
pathologists to obtain quantitative measurements on cytologic and hist
ologic preparations, so that visual impressions can be augmented by qu
antitative morphometry. Preneoplastic lesions have well-described morp
hometric features relating to nuclear area, texture, or shape. It is n
ow feasible for every pathology department to capture images of pathol
ogic material with equipment costing less than the price of a microsco
pe. Captured image files can be analyzed using commercial software or
software developed in several U.S. government agencies and made freely
available to the public. Image analysis has been shown to improve the
detection of preneoplastic cells. Recent improvements in the resoluti
on of captured images, in the algorithms that measure preneoplastic de
scriptors, and in the ease and speed of transmission of images between
laboratories, should increase our ability to detect and treat preneop
lastic lesions.