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

Related in: MedlinePlus

Illustrative examples from the test samples. (a) Fluorescent protein labelled E. coli cells captured with confocal microscope, (b) Segmented result of (a), (c) Fluorescent protein labelled Staphylococcus cells in Epifluorescence microscopy image. (d) Segmented result of (c), (e) Human HT29 Colon Cancer 1 image set (Source [8]), (f) Segmented result of (e), (g) E. coli cells captured with phase contrast microscope (Source [11]), (h) Segmented result of (g).
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 2: Illustrative examples from the test samples. (a) Fluorescent protein labelled E. coli cells captured with confocal microscope, (b) Segmented result of (a), (c) Fluorescent protein labelled Staphylococcus cells in Epifluorescence microscopy image. (d) Segmented result of (c), (e) Human HT29 Colon Cancer 1 image set (Source [8]), (f) Segmented result of (e), (g) E. coli cells captured with phase contrast microscope (Source [11]), (h) Segmented result of (g).

Mentions: We carried out an empirical evaluation of the algorithm with several test sets. The results are categorized into four classes: i) true positive (TP), if a cell is segmented properly; ii) over-segmentation, if a cell is split into more than one piece; iii) under-segmentation, if more than one cell is recognized as a single cell; and iv) false negative (FN), if a clearly visible cell is not detected. Apart from these, some cells were undergoing division which, depending on the stage, is classified as a single cell or as two independent cells, according to the specifications of the algorithm (these classifications are not considered in errors estimation). A small fraction of detections were false positives (less than 0.1%), and since the overall contribution of false positives is insignificant, we discard this result from the evaluation. The results from the fluorescent labelled E. coli test sample are listed in the Table 1, and compared to the manual annotation. The results in Tables 1 and 2 reveal the high segmentation accuracy and generality of the method. Illustrative examples from test samples are presented in Figure 2.


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

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

Illustrative examples from the test samples. (a) Fluorescent protein labelled E. coli cells captured with confocal microscope, (b) Segmented result of (a), (c) Fluorescent protein labelled Staphylococcus cells in Epifluorescence microscopy image. (d) Segmented result of (c), (e) Human HT29 Colon Cancer 1 image set (Source [8]), (f) Segmented result of (e), (g) E. coli cells captured with phase contrast microscope (Source [11]), (h) Segmented result of (g).
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 2: Illustrative examples from the test samples. (a) Fluorescent protein labelled E. coli cells captured with confocal microscope, (b) Segmented result of (a), (c) Fluorescent protein labelled Staphylococcus cells in Epifluorescence microscopy image. (d) Segmented result of (c), (e) Human HT29 Colon Cancer 1 image set (Source [8]), (f) Segmented result of (e), (g) E. coli cells captured with phase contrast microscope (Source [11]), (h) Segmented result of (g).
Mentions: We carried out an empirical evaluation of the algorithm with several test sets. The results are categorized into four classes: i) true positive (TP), if a cell is segmented properly; ii) over-segmentation, if a cell is split into more than one piece; iii) under-segmentation, if more than one cell is recognized as a single cell; and iv) false negative (FN), if a clearly visible cell is not detected. Apart from these, some cells were undergoing division which, depending on the stage, is classified as a single cell or as two independent cells, according to the specifications of the algorithm (these classifications are not considered in errors estimation). A small fraction of detections were false positives (less than 0.1%), and since the overall contribution of false positives is insignificant, we discard this result from the evaluation. The results from the fluorescent labelled E. coli test sample are listed in the Table 1, and compared to the manual annotation. The results in Tables 1 and 2 reveal the high segmentation accuracy and generality of the method. Illustrative examples from test samples are presented in Figure 2.

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
Related in: MedlinePlus