Value of morphometry, texture analysis, densitometry, and histometry in the differential diagnosis and prognosis of malignant mesothelioma

Malignant mesothelioma is a tumour with increasing incidence due to widespr ead use of its causative agent, asbestos, in the past decades, The poor sur vival necessitates a correct differentiation from other lesions at the same site, such as hyperplastic mesothelium and carcinomas metastatic to pleura or peritoneum, Since genetic and immunohistochemical markers are not absol utely differentiating, the diagnosis is based on the histology complemented with (immuno)histochemistry. However, as the tumour presents itself in num erous heterogeneous histological forms, visual evaluation is extremely diff icult, In order to evaluate the prognostic and diagnostic performance of sy ntactic structure analysis (SSA), chromatin texture analysis, densitometry, and morphometry, an automated KNN-classification system has been used to c ompare Feulgen-stained tissue sections of hyperplastic mesothelium, maligna nt mesothelioma, and pulmonary adenocarcinoma, In addition, we also studied most discriminative aspects in the:differentiation, typing, and prediction of survival. The results indicate that for the diagnosis of malignant meso thelioma, chromatin texture parameters outperform SSA, densitometry, and mo rphometry (recognition score = 96.8 per cent), Most discriminative paramete rs highlight spatial patterns of the chromatin distribution that are hard t o appraise visually and directly show the benefits of a quantitative approa ch. Typing of the tumour is best described by SSA parameters, relating to t he spatial arrangement of the cells in the tissue (recognition score (82.9 per cent). In survival time classifications, chromatin texture yields the h ighest recognition score (82.9 per cent), although accurate estimations are unreliable due to a large degree of misclassification. Copyright (C) 1999 John Wiley & Sons, Ltd.