PathMaster: Content-based cell image retrieval using automated feature extraction

Objective: Currently, when cytopathology images are archived, they are typi cally stored with a limited text-based description of their content. Such a description inherently fails to quantify the properties of an image and re fers to an extremely small fraction of its information content. This paper describes a method for automatically indexing images of individual cells an d their associated diagnoses by computationally derived cell descriptors. T his methodology may serve to better index data contained in digital image d atabases, thereby enabling cytologists and pathologists to cross-reference cells of unknown etiology or nature. Design: The indexing method, implemented in a program called PathMaster, us es a series of computer-based feature extraction routines. Descriptors of i ndividual cell characteristics generated by these routines are employed as indexes of cell morphology, texture, color, and spatial orientation. Measurements: The indexing fidelity of the program was tested after populat ing its database with images of 152 lymphocytes/lymphoma cells captured fro m lymph node touch preparations stained with hematoxylin and eosin. Images of "unknown" lymphoid cells, previously unprocessed, were then submitted fo r feature extraction and diagnostic cross-referencing analysis. Results: PathMaster listed the correct diagnosis as its first differential in 94 percent of recognition trials. In the remaining 6 percent of trials, PathMaster listed the correct diagnosis within the first three "differentia ls." Conclusion: PathMaster is a pilot cell image indexing program/search engine that creates an indexed reference of images. Use of such a reference may p rovide assistance in the diagnostic/prognostic process by furnishing a prio ritized list of possible identifications for a cell of uncertain etiology.