Computer-assisted discrimination of glioblastomas

OBJECTIVE: To measure a number of nuclear features in a series of glioblastomas and compare the data with those from a set of anaplastic and low grade astrocytomas. STUDY DESIGN: The material consisted of toluidine blue-stained smears from 13 consecutive cases of glioblastoma. Smears from 12 high gr ade astrocytomas and 13 low grade fibrillary astrocytomas were used for comparison. Fifty nuclei were measured in each case. Cell images were segmented by an interactive procedure. A set of features representing both morphometric and nuclear texture characteristics was computed. RESULTS: The use of a discriminant function based on two features related to the gray value distribution resulted in the separation of all low grade astrocytomas from glioblastomas. When the corresponding discriminant function was computed for high grade astrocytomas and the values were plotted against optical density, the glioblastomas formed a group at a greater distance from the low grade astrocytomas than from the high grade astrocytomas. A second discriminant function based on two features allowed complete separation of the glioblastoma cases from the high grade astrocytomas. CONCLUSION: In our material, chromatin texture analysis allowed effective separation of astrocytic tumors with different histologic grades of malignancy.