Automatic morphological sieving: comparison between different methods, application to DNA ploidy measurements

The aim of the present study is to propose alternative automatic methods to time consuming interactive sorting of elements for DNA ploidy measurements . One archival brain tumour and two archival breast carcinoma were studied, corresponding to 7120 elements (3764 nuclei, 3356 debris and aggregates). Three automatic classification methods were tested to eliminate debris and aggregates from DNA ploidy measurements (mathematical morphology (MM), mult iparametric analysis (MA) and neural network (NN)). Performances were evalu ated by reference to interactive sorting. The results obtained for the thre e methods concerning the percentage of debris and aggregates automatically removed reach 63, 75 and 85% for MM, MA and NN methods, respectively, with false positive rates of 6, 21 and 25%. Information about DNA ploidy abnorma lities were globally preserved after automatic elimination of debris and ag gregates by MM and MA methods as opposed to NN method, showing that automat ic classification methods can offer alternatives to tedious interactive eli mination of debris and aggregates, for DNA ploidy measurements of archival tumours.