AUTOMATED RECOGNITION AND MAPPING OF IMMUNOLABELED NEURONS IN THE DEVELOPING BRAIN

The cerebral cortex is distinguished by layers of neurons of different morphologies and densities. The layers are formed by the migration of newly generated neurons from the ventricular zone to the cortical pla te near the outer (pial) boundary of the cortex, along radial paths ap proximately perpendicular to the cortical. surface, Immunochemical lab elling makes these cells' patterns visible in brightfield microscopy s o that layer formation can be studied, We developed a suite of program s that automatically digitize the entire cortex, identify the labelled cells and compute cell densities along local radial paths. Cell ident ification used supervised classification on all the significantly stai ned objects corresponding to maxima in lowpass filtered versions of th e digital micrographs. Classification of all the stained objects as ce lls or noncell objects was made by a decision rule based on morphometr ic and grey-level texture features, including features based on Gabor functions, Detection sensitivity and classification accuracy were join tly maximized on training data consisting of about 3000 expert-identif ied neurons in micrographs, Total program performance was tested on a separate (test) set of labelled neurons the same size as the training data set, The program detected 85% of the cells in the test set with a total error of 0.19. The identified cells' locations were used to com pute population densities along normals to the cortical layers, and th ese densities served as a measure of neuronal migration. Transcortical density profiles obtained by computation and by manual cell counting were very similar, The cell identification program was built on well-e stablished methods in statistical pattern recognition and image analys is and should generalize readily to other histological preparations.