Researchers in the areas of regenerative medicine and tissue engineering have an enormous interest in understanding the relationship of different sets of culturing conditions and applied mechanical stimuli on the behavior of Mesenchymal Stem Cells (MSCs). However, it remains a challenge to design a general tool to perform automatic cell image analysis due to the diverse morphologies of MSCs. Therefore, as a primary step towards developing the tool, we propose a novel adaptive approach for accurate cell image segmentation. We collected three MSC datasets cultured on different surfaces and exposed to diverse mechanical stimuli. As shown in the figure below, cells are cultured on a substrate with a constant applied stretch as a stimuli. This substrate and the stretch device are then placed under a microscope for observing cell growth. A computer interfaces with the microscope and captures the images. By analyzing the existing approaches on our data, we choose to substantially extend the binarization-based extraction of alignment score (BEAS) approach by extracting novel discriminating features and developing an adaptive threshold estimation model. Experimental results on our data shows our approach is superior to seven conventional techniques. We also define three quantitative measures to compare and analyze the characteristics of the images from our three datasets. To the best of our knowledge, this is the first study that applied automatic segmentation to live MSC cultured on different surfaces with applied stimuli.
We release the part of our collected dataset that was used in our WACV paper. To obtain a copy of this dataset, please email Jamal Afridi at afridimu[at]msu[dot]edu with the subject: "MSC dataset download".
Any publications arising from the use of this database, including but not limited to academic journal and conference publications, technical reports and manuals, must cite the following work: