Detection of malignancy associated changes in cervical cell nuclei using feed-forward neural networks

Normal cells in the presence of a precancerous lesion undergo subtle changes of their DNA distribution when observed by visible microscopy. These changes have been termed Malignancy Associated Changes (MACs). Using statistical models such as neural networks and discriminant functions it is possible to design classifiers that can separate these objects from truly normal cells. The correct classification rate using feed-forward neural networks is compared to linear discriminant analysis when applied to detecting MACs. Classifiers were designed using 53 nuclear features calculated from images for each of 25,360 normal appearing cells taken from 344 slides diagnosed as normal or containing severe dysplasia. A linear discriminant function achieved a correct classification rate of 61.6% on the test data while neural networks scored as high as 72.5% on a cell-by-cell basis. The cell classifiers were applied to a library of 93,494 cells from 395 slides, and the results were jackknifed using a single slide feature. The discriminant function achieved a correct classification rate of 67.6% while the neural networks managed as high as 76.2%.