Automatic quantification of microvessels using unsupervised image analysis

Article type: Research Article

Authors: Ranefall, Petter^; | Wester, Kenneth | Busch, Christer | Malmström, Per‐Uno | Bengtsson, Ewert

Affiliations: Centre for Image Analysis, Uppsala University, Sweden | Department of Pathology, Uppsala University, Sweden | Department of Urology, Uppsala University, Sweden

Note: [] Correspondence to: Petter Ranefall, Centre for Image Analysis, Lägerhyddvägen 17, S‐752 37 Uppsala, Sweden. Tel.: +46 18 471 78 49; Fax: +46 18 55 34 47; E‐mail: [email protected].

Abstract: An automatic method for quantification of images of microvessels by computing area proportions and number of objects is presented. The objects are segmented from the background using dynamic thresholding of the average component size histogram. To be able to count the objects, fragmented objects are connected, all objects are filled, and touching objects are separated using a watershed segmentation algorithm. The method is fully automatic and robust with respect to illumination and focus settings. A test set consisting of images grabbed with different focus and illumination for each field of view, was used to test the method, and the proposed method showed less variation than the intraoperator variation using manual threshold. Further, the method showed good correlation to manual object counting (r=0.80) on an other test set.

Journal: Analytical Cellular Pathology, vol. 17, no. 2, pp. 83-92, 1998