A method for counting objects in an image includes the steps of: (a) providing an image including at least one object defined in the image in shades of at least one color; (b) identifying objects in the image having a shade of color which exceeds a threshold shade so as to provide a number of identified objects; (c) evaluating objects of the number of identified objects based upon object criteria to determine whether each object satisfies the criteria and can be counted, or does not satisfy the criteria and is suspect and needs further analysis; (d) repeating steps (b) and (c) for objects which are suspect at shades of color increasingly exceeding the threshold shade until all objects satisfy the criteria; and (e) providing a count of the objects, whereby accuracy of the count is enhanced. Each object is preferably tested for one or more criteria including object size, visibility, color, surface quality and shape.

A method for counting objects in an image includes the steps of: (a) providing an image including at least one object defined in the image in shades of at least one color; (b) identifying objects in the image having a shade of color which exceeds a threshold shade so as to provide a number of identified objects; (c) evaluating objects of the number of identified objects based upon object criteria to determine whether each object satisfies the criteria and can be counted, or does not satisfy the criteria and is suspect and needs further analysis; (d) repeating steps (b) and (c) for objects which are suspect at shades of color increasingly exceeding the threshold shade until all objects satisfy the criteria; and (e) providing a count of the objects, whereby accuracy of the count is enhanced. Each object is preferably tested for one or more criteria including object size, visibility, color, surface quality and shape.

The system and method for evaluating the amount of marker identifying precipitate in a cellular specimen on a microscope slide is disclosed. The automated microscope system performs a low magnification and high magnification scan of a cellular specimen to identify and confirm candidate objects of interest which correspond to cells containing a marker identifying precipitate. A regularly shaped area centered about a centroid computed for a candidate object of interest is used to define the pixels to be processed. A color ratio is computed for each pixel and those color ratios indicative of being dominated by the color corresponding to the marker identified precipitate are summed and normalized. The normalized color ratio is compared to at least one predetermined threshold to assign a grade to the candidate objects of interest. The grades for a predetermined number of candidate objects of interest are summed to form an aggregate score and the aggregate score is compared to a threshold. If the aggregate score exceeds a threshold, the candidate object of interest is determined to indicate the medical condition typically associated with the marker.

An apparatus and method in which a still image, or still images, are obtained of a plurality of particles suspended in a fluid medium. Each still image is transferred to an image analyzing unit that measures a set of dimensional characteristics per particle for particles appearing in the image and determine an occurrence characteristic for particles having a matching set of dimensional characteristics. Preferably, a three dimensional representation of the characteristics is displayed in real time. More preferably, the displayed three-dimensional representation is continuously updated and further entries are accumulated on the display as image analysis is performed. The display provides information to a viewer enabling the viewer to determine a shape distribution of the particles within the suspension even when multiple particle shapes are present.

A system is provided for analysis of neoplasia in tissue at a very early stage as well as later stages of its progression and for reporting the progression or regression of the neoplasia. The system performs multi-parametric measurements of the morphological structure and texture of the tissue structure and correlates these measurements on a common morphological grading scale. The system performs certain tissue measurements which are more highly discriminating for one kind of neoplasia and performs other tissue measurement, which are more highly discriminating, for another kind of neoplasia. Diverse tissue measurements may be made on diverse tissue types such as breast, colon, or cervix tissue, etc. from animals or humans which tissue has subjected to different carcinogens or chemopreventive agents. The measurements are made in different units and on different scales; and then these measurements are combined and reported on a valid, objective, common, universal scale. Microscopic images of stained neoplastic tissue sections are optically and microscopically scanned to provide electronic tissue sample images that are electronically recorded. Then, morphometric features of tissue sample images are measured in first unit vales and texture measurements of the tissue samples, such as a Markovian texture measurement. Usually, normal tissue samples and abnormal cancerous tissue samples are analyzed using the same morphometric and texture measurements and their respective results are reported onto a grading common scale so that progression of the cancer can be ascertained relative to the normal tissue.