Limits...
Cell segmentation by multi-resolution analysis and maximum likelihood estimation (MAMLE).

Chowdhury S, Kandhavelu M, Yli-Harja O, Ribeiro AS - BMC Bioinformatics (2013)

Bottom Line: From this result, a correction procedure is applied that exploits maximum likelihood estimate as an objective function.The new method attained very high (above 90%) cell segmentation accuracy in all cases.Finally, its accuracy was compared to several existing methods, and in all tests, MAMLE outperformed them in segmentation accuracy.

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: Cell imaging is becoming an indispensable tool for cell and molecular biology research. However, most processes studied are stochastic in nature, and require the observation of many cells and events. Ideally, extraction of information from these images ought to rely on automatic methods. Here, we propose a novel segmentation method, MAMLE, for detecting cells within dense clusters.

Methods: MAMLE executes cell segmentation in two stages. The first relies on state of the art filtering technique, edge detection in multi-resolution with morphological operator and threshold decomposition for adaptive thresholding. From this result, a correction procedure is applied that exploits maximum likelihood estimate as an objective function. Also, it acquires morphological features from the initial segmentation for constructing the likelihood parameter, after which the final segmentation is obtained.

Conclusions: We performed an empirical evaluation that includes sample images from different imaging modalities and diverse cell types. The new method attained very high (above 90%) cell segmentation accuracy in all cases. Finally, its accuracy was compared to several existing methods, and in all tests, MAMLE outperformed them in segmentation accuracy.

Show MeSH
Scatter plot of total cell intensity (left plot), length of the cell (middle plot) and width of the cell (right plot) in pixel by pixel comparison test.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3750476&req=5

Figure 3: Scatter plot of total cell intensity (left plot), length of the cell (middle plot) and width of the cell (right plot) in pixel by pixel comparison test.

Mentions: As a proof of concept, the efficiency of the segmentation method is evaluated against manually labelled cells at pixel level. This is carried out for three illustrative features: total cell intensity, cell length, and cell width. The test comprises approximately 1100 GFP labelled E. coli cells collected from 13 images. Figure 3 shows the quantitative results in scatter plots with a least square regression line. The horizontal axis represents the results from manual labelling and the vertical axis represents the results from the automated segmentation. A strong correspondence between manual and automated segmentation is evident. The correlation coefficients for the listed features were 0.98 (total cell intensity), 0.91 (cell length) and 0.31 (cell width), respectively. The correlation of the cell width feature is lower due to substantial inaccuracy in the manual segmentation of this feature. The presence of cells dividing was the other main cause for this error rate.


Cell segmentation by multi-resolution analysis and maximum likelihood estimation (MAMLE).

Chowdhury S, Kandhavelu M, Yli-Harja O, Ribeiro AS - BMC Bioinformatics (2013)

Scatter plot of total cell intensity (left plot), length of the cell (middle plot) and width of the cell (right plot) in pixel by pixel comparison test.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3750476&req=5

Figure 3: Scatter plot of total cell intensity (left plot), length of the cell (middle plot) and width of the cell (right plot) in pixel by pixel comparison test.
Mentions: As a proof of concept, the efficiency of the segmentation method is evaluated against manually labelled cells at pixel level. This is carried out for three illustrative features: total cell intensity, cell length, and cell width. The test comprises approximately 1100 GFP labelled E. coli cells collected from 13 images. Figure 3 shows the quantitative results in scatter plots with a least square regression line. The horizontal axis represents the results from manual labelling and the vertical axis represents the results from the automated segmentation. A strong correspondence between manual and automated segmentation is evident. The correlation coefficients for the listed features were 0.98 (total cell intensity), 0.91 (cell length) and 0.31 (cell width), respectively. The correlation of the cell width feature is lower due to substantial inaccuracy in the manual segmentation of this feature. The presence of cells dividing was the other main cause for this error rate.

Bottom Line: From this result, a correction procedure is applied that exploits maximum likelihood estimate as an objective function.The new method attained very high (above 90%) cell segmentation accuracy in all cases.Finally, its accuracy was compared to several existing methods, and in all tests, MAMLE outperformed them in segmentation accuracy.

View Article: PubMed Central - HTML - PubMed

ABSTRACT

Background: Cell imaging is becoming an indispensable tool for cell and molecular biology research. However, most processes studied are stochastic in nature, and require the observation of many cells and events. Ideally, extraction of information from these images ought to rely on automatic methods. Here, we propose a novel segmentation method, MAMLE, for detecting cells within dense clusters.

Methods: MAMLE executes cell segmentation in two stages. The first relies on state of the art filtering technique, edge detection in multi-resolution with morphological operator and threshold decomposition for adaptive thresholding. From this result, a correction procedure is applied that exploits maximum likelihood estimate as an objective function. Also, it acquires morphological features from the initial segmentation for constructing the likelihood parameter, after which the final segmentation is obtained.

Conclusions: We performed an empirical evaluation that includes sample images from different imaging modalities and diverse cell types. The new method attained very high (above 90%) cell segmentation accuracy in all cases. Finally, its accuracy was compared to several existing methods, and in all tests, MAMLE outperformed them in segmentation accuracy.

Show MeSH