Minima equalization: a useful strategy in automatic processing of microscopic images

Specifically stained features in microscopic images rarely have a unique range of grey levels which would permit selection of the features by simple thresholding. The spaces between features and immediately surrounding them are often as dark or darker than the more lightly stained features. An algorithm for minima equalization which facilitates the extraction and segmentation of such features was designed and is explained in intuitive terms. It is applied to the analysis of cross-sections of peripheral myelinated nerve fibers. It is shown that the binary image obtained can be combined with a gradient image to give a binary image which accurately reflects the thickness of the myelin in the original image. Using silver-impregnated nerve endings and bile canaliculi stained for thiamine pyrophosphatase, binary images like those prepared manually from thick specimens using a camera lucida can be obtained using the minima equalization procedure. The image processor is used to develop a composite image by combining images at various focal planes through the thick specimen. This image is then processed to obtain the binary image.