Objectives: To determine quantitative nuclear morpho-and densitometric classifiers and classification techniques for analysis of gastric, Feulgen-stained brush smears.
Design: TV image analysis-based quantitative DNA and morphometric analysis of gastric brush smears in a prospective study.
Patients and methods: Ninety-eight (11 normal, 77 gastritis (17 with intestinal metaplasia) and 10 adenocarcinoma) Feulgen-Schiff-stained gastric brush smears were analysed by TV image analysis. The classification of the smears was based on parallel histological examination. For standards, DNA content of lymphocyte cell cultures was determined by the image and by flow cytometry. From every nucleus, six morphometric (surface, layers, minimum diameter, maximum diameter, perimeter and form factor) and six densitometric (integrated optical density (IOD), average density, sigma density, minimum and maximum density and density range) parameters were simultaneously determined. The smear parameters (object cells CV, DNA index, 2c deviation index, 5c exceeding rate, G1 -S-G2 ratio) were analysed together with the mean and SD values of the nuclear parameters by discriminant analysis and back-propagation neural networks.
Result: The normal smears were all diploid and their S + G2 ratio was 15.24+/-7.75% (mean +/- SD). The gastritis smears were all diploid with a proliferation fraction of 20.89+/-6.75%. The tumours were aneuploid in eight of the ten cases with 5c exceeding rate > 6.23%, the S + G2 fraction ratio was 34.72+/-10.12%. The mean nuclear surface area was 46+/-20, 58+/-20 and 74+/-22 microm2 in normal, gastritis and malignant groups, respectively. Significant differences (P<0.05) were found in nuclear surface, minimum and maximum diameter, and perimeter parameters. Using linear discriminant analysis, 100% of the non-malignant cases and 70% of the tumour cases were correctly classified. Using 30 non-malignant and five malignant cases as a training set, the neural networks classified 95% of the remaining cases correctly. The DNA index increased significantly (P<0.05) in Helicobacter pylori-positive cases compared to the negative ones. In gastritis with intestinal metaplasia, the proliferation ratio decreased significantly (P<0.05).
Conclusions: The image analysis is a useful tool for quantitative gastric cytology. The combination of nuclear morphometric parameters and neural network classifiers with multivariate quantitative DNA analysis is suggested for gastric brush smear quantitative cytology analysis.