Preliminary results on automatic quantification of histological studies in allergic asthma

Abstract

The evaluation of new therapies to treat allergic asthma makes frequent use of histological studies. Some of these studies are based on the microscope observation of stained paraffin lung sections to quantify cellular infiltration, an effect directly related to allergic processes. To our knowledge, there is no software tool for doing this quantification automatically nowadays. This paper presents a method for the quantification of cellular infiltrate of lung tissue images in a mouse model of allergic asthma. Each image is divided into regions of equal size that are classified by means of a segmentation algorithm based on texture analysis. The classification uses three discriminant functions, built from parameters derived from the histogram and the co-occurrence matrix and calculated by performing an initial stepwise discriminant analysis on 79 samples from a training set. Results provide a correct classification of 96.8 % on an independent test set of 251 samples labeled manually.