“…1). Therefore, we enhanced the image contrast using contrast stretch and histogram equalization (HE) (Bansal et al, 2007; Song et al, 2011), and then subjected the image to medium filtering using 3×3 neighborhoods to remove noise, particularly nonspecific salt- and pepper-like noise, and further smooth the images (Uchida, 2013). The above processes were achieved using the corresponding Matlab program. Figure 1 Immunofluorescence images of microtubules.…”
Microtubule analysis is of significant value for a better understanding of normal and pathological cellular processes. Although immunofluorescence microscopic techniques have proven useful in the study of microtubules, comparative results commonly rely on a descriptive and subjective visual analysis. We developed an objective and quantitative method based on image processing and analysis of fluorescently labeled microtubular patterns in cultured cells. We used a multi-parameter approach by analyzing four quantifiable characteristics to compose our quantitative feature set. Then we interpreted specific changes in the parameters and revealed the contribution of each feature set using principal component analysis. In addition, we verified that different treatment groups could be clearly discriminated using principal components of the multi-parameter model. High predictive accuracy of four commonly used multi-classification methods confirmed our method. These results demonstrated the effectiveness and efficiency of our method in the analysis of microtubules in fluorescence images. Application of the analytical methods presented here provides information concerning the organization and modification of microtubules, and could aid in the further understanding of structural and functional aspects of microtubules under normal and pathological conditions.
“…1). Therefore, we enhanced the image contrast using contrast stretch and histogram equalization (HE) (Bansal et al, 2007; Song et al, 2011), and then subjected the image to medium filtering using 3×3 neighborhoods to remove noise, particularly nonspecific salt- and pepper-like noise, and further smooth the images (Uchida, 2013). The above processes were achieved using the corresponding Matlab program. Figure 1 Immunofluorescence images of microtubules.…”
Microtubule analysis is of significant value for a better understanding of normal and pathological cellular processes. Although immunofluorescence microscopic techniques have proven useful in the study of microtubules, comparative results commonly rely on a descriptive and subjective visual analysis. We developed an objective and quantitative method based on image processing and analysis of fluorescently labeled microtubular patterns in cultured cells. We used a multi-parameter approach by analyzing four quantifiable characteristics to compose our quantitative feature set. Then we interpreted specific changes in the parameters and revealed the contribution of each feature set using principal component analysis. In addition, we verified that different treatment groups could be clearly discriminated using principal components of the multi-parameter model. High predictive accuracy of four commonly used multi-classification methods confirmed our method. These results demonstrated the effectiveness and efficiency of our method in the analysis of microtubules in fluorescence images. Application of the analytical methods presented here provides information concerning the organization and modification of microtubules, and could aid in the further understanding of structural and functional aspects of microtubules under normal and pathological conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
