Development and evaluation of an open source Delphi-based software for morphometric quantification of liver fibrosis

Abstract

Background: Computer-based morphometry can minimize subjectivity in the assessment of liver fibrosis. An image processing program was developed with Delphi for the quantification of fibrosis in liver tissue samples stained with Sirius Red. Bile duct ligated and sham operated wild type C57BL/6 mice served as a model of time-dependent induction of liver fibrosis. Formation of fibrosis was determined with the developed software at day 0, 3, 7, 10, 14, 20, 30 and 60. The results were compared to a semi-quantitative scoring system.

Results: Quantitative accumulation of collagen fibres was observed from day 3 to day 14, with a slight further increase thereafter. During ongoing fibrogenesis, there was a significant elevation of alanine aminotransferase (ALT), aspartate transaminase (AST) and bilirubin. The results from our computer-based morphometric analysis were highly correlated with the results that were obtained in a standardized pathology semi-quantitative scoring system (R 2 = 0.89, n = 38).

Conclusions: Using our Delphi-based image analysing software, the morphometric assessment of fibrosis is as precise as semi-quantitative scoring by an experienced pathologist. This program can be a valuable tool in any kind of experimental or clinical setting for standardized quantitative assessment of fibrosis.

Figure 1

Study design and experimental setting. Bile duct ligation was performed on day 0. Analysis was performed on day 3 and 7 after the procedure to measure short time effects. Time-points after 10, 14 and 20 days were chosen to display intermediate and 30 and 60 days to analyse long-term effects.

Figure 2

Serum markers of cholestasis and hepatocellular injury during bile duct ligation. Biochemical markers are shown for (A) bilirubin, (B) total protein, (C) alanine aminotransferase and (D) aspartate transaminase.

Figure 3

Semi-quantitative analysis versus computer-based morphometrical analysis. (A) A semi-quantitative score that considers both periportal and perisinusoidal fibrosis was determined and compared to (B) the morphometric analysis determined in Sirius Red stained specimen.

Figure 4

Correlation between semi-quantitative and computer-based analysis. Linear regression fit between semi-quantitative total (A; R2 = 0.89), periportal (B; R2 = 0.86) and perisinuidal (C; R2 = 0.64) score and morphometric assessment (Percentage of positively stained surface, Sirius Red Staining; n = 38.)

Figure 5

Computer-based morphometry. (A) Photograph of a Sirius Red stain of a liver section (100 × magnifications). (B) Grey transformation, blurring and shading of respective photograph. (C) Resulting image of respective photograph. Background is black, liver parenchyma light green and fibrosis intuitively red.

Figure 6

Screenshot of program interface. The original photographs are shown in the upper left corner. In the upper right corner the same picture is shown after adding the grey transformation, blurring and shading. The histogram analysis is shown in the lower right corner. The image in the lower middle shows the calculated background in black, the liver parenchyma in a light green and fibrosis intuitively red. The percentage of fibrous tissue is calculated on the lower left side (black arrow).