Syntactic structure analysis was carried out successfully on 92 paraff
in embedded uveal melanomas, taken from patients with a minimum follow
up of 5 years. This simple, fast, and reproducible method of describi
ng the tumour architecture has been significantly correlated with mali
gnancy in tumours from several sites. Paraffin sections 5 mu m thick,
were cut and stained with haematoxylin and eosin. Tumours were classif
ied according to a modification of the Callender classification. A min
imum spanning tree (MST), using the centre points of tumour nuclei, wa
s constructed in five randomly chosen fields with an interactive digit
ising video overlay system. Ten syntactic structure features were deri
ved from each MST; subsequently, the mean and standard deviation of th
e five fields analysed were calculated for further statistical analysi
s. Reproducibility was acceptable with a mean correlation coefficient
of 0.70. In univariate survival analysis, the percentage of points wit
h three neighbours yielded prognostic significance (p<0.05). Minimum s
panning tree variables were compared (chi(2) test) with classic tumour
prognosticators and there was a significant correlation between Calle
nder cell. type and the following MST parameters: mean number of point
s (p<0.003); MST length (p<0.003); mean line length (p<0.01); number o
f nuclei with one neighbour (p<0.004); number of nuclei with two neigh
bours (p<0.02), and number of nuclei with three neighbours (p<0.005).
Syntactic structure analysis is an evolving technique, but may be able
to mathematically (and reproducibly) describe melanoma architecture a
cross the spectrum of the Callender classes. This would also allow arc
hitectural grading of tumours within the specific Callender groups, pr
oviding more precise prognostic information. Further modifications of
this technique are necessary to optimise prognostic potential when app
lied to uveal melanomas.