ECE 533 Project Proposal
Small Intestine Villi Counting
Jittapat Bunnag
Meghan Olson
Background: Anemia, a condition in which the blood is not efficient in bring oxygen to tissue, is a continuing problem in premature infants. When the body detects anemia it reacts by producing erythropoietin, which is a hormone that stimulates red blood cell development. The red blood cells then need iron to produce hemoglobin, the component of the blood that carries oxygen to the tissues, however if iron is unavailable the cell can not function properly and the individual becomes anemic. One reason an infant or person may become anemic is poor iron absorption in the small intestine.
Problem: A current study is being done to look at the affects of diet on iron absorption in the intestine in lab rats. After the diet has been administered for set amount of time, tissues from the lab rats are obtained and put on microscope slides. The slides are stained so iron becomes blue in color. Currently the number of villi which contain iron and the number of cells within the villi that contain iron are counted manually. This procedure is very time consuming, contains human errors, and is somewhat subjective. It would be ideal to create a digital imaging tool to automate the counting process and in some way quantify the degree of iron absorption, i.e. find percentage of blue compared to red cells.
Proposed Approach: Past studies have shown that counting cells through digital image processing can be done. The image is usually first put through some preprocessing to isolate the cells from the rest of the image and then watersheding is done to separate the individual cells so that they can be counted. We propose to apply a transformation to the image to stretch out the grayscale values to add more contrast to the images so it is easier to find a threshold which can be applied to all the images. We then plan to separate the blue and red cells from the rest of the image by using thresholding in the red, green, and blue channels and then combining the binary images obtained so that only pixels of interest are passed. Edge detection may also be implemented to eliminate noise from the edge of the villi. Once the blue (iron cells) and red cells are separated we then plan to use watersheding to separate the individual cells from one another. Using a connectivity detection algorithm,the cells can then be counted and the percentage of blue cells to red cells can be compared.
References:
Kleven, Kelsey. Analyzing the Presence of Iron in Small Intestinal Villi. Available [Online] November 7, 2005.
Malpica, Norberto et. al. Applying Watershed Algorithms to the Segmentation of Clustered Nuclei. Cytometry, 28: 289-297. 1997.
Wahlby, Carolina. Algorithms for Applied Digital Image Cytometry. Theses from UppsalaUniversity. Acta Universitatis Upsaliensis, Uppsala, 2003. Avaliable [Online] November, 2005.