Re-narrowing or restenosis of a human coronary artery occurs within six months in one third of balloon angioplasty procedures. Accurate and repeatable quantitative analysis of vessel shape is important to characterize the progression and type of restenosis, and to evaluate effects new therapies might have. A combination of complicated geometry and image variability, and the need for high resolution and large image size makes visual/manual analysis slow, difficult, and prone to error. The image processing and analysis described here was developed to automate feature extraction of the lumen, internal elastic lamina, neointima, external elastic lamina, and tunica adventitia and to enable an objective, quantitative definition of blood vessel geometry. The quantitative geometrical analysis enables the measurement of several features including perimeter, area, and other metrics of vessel damage. Automation of feature extraction creates a high throughput capability that enables analysis of serial sections for more accurate measurement of restenosis dimensions. Measurement results are input into a relational database where they can be statistically analyzed compared across studies. As part of the integrated process, results are also imprinted on the images themselves to facilitate auditing of the results. The analysis is fast, repeatable and accurate while allowing the pathologist to control the measurement process.