<span lang="EN-US">Cell counting is a required procedure in biomedical experiments and drug testing</span><em><span lang="TH">. </span></em><span lang="EN-US">Manual cell counting performed with a hemocytometer is time consuming and individual dependence</span><em><span lang="TH">. </span></em><span lang="EN-US">This study reported</span><em></em><span lang="EN-US">the development of a computer</span><em><span lang="TH">-</span></em><span lang="EN-US">assisted program for trypan blue stained</span><em><span lang="TH">-</span></em><span lang="EN-US">cell counting using digital image analysis</span><em><span lang="TH">. </span></em><span lang="EN-US">Images of trypan blue</span><em><span lang="TH">-</span></em><span lang="EN-US">stained breast cancer cells line were obtained by a microscope with a digital camera</span><em><span lang="TH">. </span></em><span lang="EN-US">Undesired noise and debris were removed by applying a guided image filter</span><em><span lang="TH">. </span></em><span lang="EN-US">Color space HSV </span><span lang="EN-US">(</span><span lang="EN-US">Hue, Saturation and Value)</span><em></em><span lang="EN-US">conversion and grayscale conversion were performed for distinguishing between live and dead cells</span><em><span lang="TH">.  </span></em><span lang="EN-US">Image thresholding and morphological operators were applied for image segmentation</span><em><span lang="TH">. </span></em><span lang="EN-US">Live and dead cells were counted after image segmentation and the results were compared with manual counting by three well</span><em><span lang="TH">-</span></em><span lang="EN-US">experienced counters</span><em><span lang="TH">. </span></em><span lang="EN-US">The computer</span><em><span lang="TH">-</span></em><span lang="EN-US">assisted cell counting from thirty</span><em><span lang="TH">-</span></em><span lang="EN-US">six trypan blue</span><em><span lang="TH">-</span></em><span lang="EN-US">stained microscopic images had a high correlation coefficient with the live cell results of the experts (r</span><em><span lang="TH">=</span></em><span lang="EN-US">0</span><em><span lang="TH">.</span></em><span lang="EN-US">99</span><span lang="EN-US">)</span><em><span lang="TH">. </span></em><span lang="EN-US">The correlation coefficient of the number of dead cells comparing the computer</span><em><span lang="TH">-</span></em><span lang="EN-US">assisted count and the experts</span><em><span lang="TH">’ </span></em><span lang="EN-US">count was 0</span><em><span lang="TH">.</span></em><span lang="EN-US">74</span><em><span lang="TH">. </span></em><span lang="EN-US">Our approach offers high accuracy (&gt;85</span><em><span lang="TH">%</span></em><span lang="EN-US">)</span><em></em><span lang="EN-US">on counting live cells compared with the experts</span><em><span lang="TH">’ </span></em><span lang="EN-US">counting</span><em><span lang="TH">. </span></em><span lang="EN-US">This automated cell counting approach can assist biomedical researchers for both live and dead cells counting</span><em><span lang="TH">.</span></em>

Computer-assisted image analysis can be employed to reduce the time consumed in the routine task such as cell counting. This study aimed to establish a method to perform this routine task based on an image analysis to automatically count live and dead cells after staining with trypan blue dye. Gray scale conversion and morphological operation were applied to the input images to enhance the image quality before image segmentation, then adaptive k-means clustering was applied to classify the groups of live and dead cells. Circular Hough transform and object labelling were carried out to identify the number of each cell type. The counting results from the proposed method were compared with the counting of three experts and the ImageJ software. The results showed that the proposed method had very high correlation with the results of the three experts in counting live cells (R 2 >0.95) and was better than the counting results achieved by ImageJ. The number of dead cells counted by our program was in good agreement with the experts' counting (R 2 >0.64). In conclusion, this study suggests that using new image analysis program can be confidently substituted for a manual counting in routine cell counting.