To compare the Visage 2000 analysis system (Bio Image, Ann Arbor, MI, USA) with the GELLAB-II analysis system (National Cancer Institute, Frederick, MD, USA), we used each to perform image analysis of the same 29 silver-stained two-dimensional electrophoresis (2DE) gel image files from a study of urinary proteins in metal recovery plant workers who had confirmed body burdens of cadmium. Visage, aided by interactive analysis, detected an average of 890 +/- 177.6 spots per gel, or a total of 25,800 spots, whereas GELLAB-II detected 1971 +/- 198.5 spots per gel, or a total of 57,160 (a 222% increase over the Visage system), without operator intervention. Visage automatically quantified 52.5% (13,556) of the spots; 47.2% (12,173), consisting mostly of larger spots, had to be quantified interactively with an image editor, and 0.3% (71) were not quantified. GELLAB-II automatically quantified all detected spots. After we interactively assigned the maximum allowed number of landmarks (30 for Visage and 52 for GELLAB-II), we found that Visage matched 657 +/- 211.2 spots per gel, and GELLAB-II matched all detected spots and also extrapolated an average of 1269 virtual spots per gel. Plots of densities from the two systems on selected spots showed excellent agreement, and both systems showed high correlation between their measurements of the beta-2-microglobulin spot densities and an independent radioimmunoassay quantification of the original urine samples. By comparing the regression of the densities of all spots with urinary cadmium (UCD) levels, we found that several of the same detected spots from each system were highly correlated. The densities of four acidic proteins with relative molecular weights of approximately 112,000 Da (as quantified by GELLAB-II but not by Visage) were highly correlated with UCD concentrations. These proteins are new candidate biomarkers of cadmium toxicity. We compared the estimated labor costs of using each system to analyse a hypothetical 20-sample (60 gels) 2DE study and found that GELLAB-II was six times less expensive to use than Visage, primarily because of the operator time required to do interactive error correction with the Visage system.