Journals Proceedings

Abstract

IN traditional cancer diagnosis, pathologists examine biopsies to make diagnostic assessments largely based on cell morphology and tissue distribution. However, this is subjective and often leads to considerable variability. On the other hand, computational diagnostic tools enable objective judgments by making use of quantitative measures. This paper presents steps in autoamted cancer diagnosis based on histomorphometry.As well as GUI related to the diagnosis. The GUI is made in Matlab with automatic report generation facility. These steps are 1.) Image preprocessing to determine the focal areas 2.) Feature extraction to qunatify the properties of these focal areas and3.) Classifying the focal areas as cancer grade two or three using nuclear morphometry. In step 1, comprises nucleus /cell segmentation using kmeans clustring .step 2 defines objective measures. In step 3, automated diagnostic systems that operate on quantitative measures are designed. In this paper, we detail these computational steps , and address their challenges.