Limits...
FogBank: a single cell segmentation across multiple cell lines and image modalities.

Chalfoun J, Majurski M, Dima A, Stuelten C, Peskin A, Brady M - BMC Bioinformatics (2014)

Bottom Line: This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images.We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets.The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

View Article: PubMed Central - PubMed

Affiliation: Information Technology Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA. joe.chalfoun@nist.gov.

ABSTRACT

Background: Many cell lines currently used in medical research, such as cancer cells or stem cells, grow in confluent sheets or colonies. The biology of individual cells provide valuable information, thus the separation of touching cells in these microscopy images is critical for counting, identification and measurement of individual cells. Over-segmentation of single cells continues to be a major problem for methods based on morphological watershed due to the high level of noise in microscopy cell images. There is a need for a new segmentation method that is robust over a wide variety of biological images and can accurately separate individual cells even in challenging datasets such as confluent sheets or colonies.

Results: We present a new automated segmentation method called FogBank that accurately separates cells when confluent and touching each other. This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images. The method is based on morphological watershed principles with two new features to improve accuracy and minimize over-segmentation. First, FogBank uses histogram binning to quantize pixel intensities which minimizes the image noise that causes over-segmentation. Second, FogBank uses a geodesic distance mask derived from raw images to detect the shapes of individual cells, in contrast to the more linear cell edges that other watershed-like algorithms produce. We evaluated the segmentation accuracy against manually segmented datasets using two metrics. FogBank achieved segmentation accuracy on the order of 0.75 (1 being a perfect match). We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets. FogBank outperformed all related algorithms. The accuracy has also been visually verified on data sets with 14 cell lines across 3 imaging modalities leading to 876 segmentation evaluation images.

Conclusions: FogBank produces single cell segmentation from confluent cell sheets with high accuracy. It can be applied to microscopy images of multiple cell lines and a variety of imaging modalities. The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

Show MeSH

Related in: MedlinePlus

Histogram quantization. Image histogram with every pixel frequency displayed (top left), every bin contains a unique intensity value. Percentile binned histogram (top right and bottom): every bin contains 1% of the intensity values. Potential local minima correspond to peak values in the histogram where the corresponding intensity/location in the image might be considered as a seed point. Histogram quantization minimizes the number of local minima in the image, thus reducing the chances of over-segmenting the image.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4301455&req=5

Fig4: Histogram quantization. Image histogram with every pixel frequency displayed (top left), every bin contains a unique intensity value. Percentile binned histogram (top right and bottom): every bin contains 1% of the intensity values. Potential local minima correspond to peak values in the histogram where the corresponding intensity/location in the image might be considered as a seed point. Histogram quantization minimizes the number of local minima in the image, thus reducing the chances of over-segmenting the image.

Mentions: This computational step computes seed points as a function of histogram percentile binning quantization with seed size constraint. In contrast to other techniques, intensity thresholds are not defined at every unique intensity value in the image but rather at each percentile value of the image. Using every unique value leads to multiple local peaks and hence to over-segmentation, while binning the pixel intensities reduces over-segmentation. For our purposes we used bins containing 1% of pixels. An illustration of the corresponding intensity interval is shown in Figure 4. The quantization reduces the number of potential seed points to consider, thus reducing the chances of over-segmenting the image. Furthermore, the use of percentiles helps to focus on the intensity levels that are more consistent across each quantile, and has a much faster execution time since we are considering only 100 intensity levels in any image. Figure 4 shows that the intensity levels are more concentrated in the middle section of the histogram and less on the boundaries.Figure 4


FogBank: a single cell segmentation across multiple cell lines and image modalities.

Chalfoun J, Majurski M, Dima A, Stuelten C, Peskin A, Brady M - BMC Bioinformatics (2014)

Histogram quantization. Image histogram with every pixel frequency displayed (top left), every bin contains a unique intensity value. Percentile binned histogram (top right and bottom): every bin contains 1% of the intensity values. Potential local minima correspond to peak values in the histogram where the corresponding intensity/location in the image might be considered as a seed point. Histogram quantization minimizes the number of local minima in the image, thus reducing the chances of over-segmenting the image.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4301455&req=5

Fig4: Histogram quantization. Image histogram with every pixel frequency displayed (top left), every bin contains a unique intensity value. Percentile binned histogram (top right and bottom): every bin contains 1% of the intensity values. Potential local minima correspond to peak values in the histogram where the corresponding intensity/location in the image might be considered as a seed point. Histogram quantization minimizes the number of local minima in the image, thus reducing the chances of over-segmenting the image.
Mentions: This computational step computes seed points as a function of histogram percentile binning quantization with seed size constraint. In contrast to other techniques, intensity thresholds are not defined at every unique intensity value in the image but rather at each percentile value of the image. Using every unique value leads to multiple local peaks and hence to over-segmentation, while binning the pixel intensities reduces over-segmentation. For our purposes we used bins containing 1% of pixels. An illustration of the corresponding intensity interval is shown in Figure 4. The quantization reduces the number of potential seed points to consider, thus reducing the chances of over-segmenting the image. Furthermore, the use of percentiles helps to focus on the intensity levels that are more consistent across each quantile, and has a much faster execution time since we are considering only 100 intensity levels in any image. Figure 4 shows that the intensity levels are more concentrated in the middle section of the histogram and less on the boundaries.Figure 4

Bottom Line: This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images.We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets.The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

View Article: PubMed Central - PubMed

Affiliation: Information Technology Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA. joe.chalfoun@nist.gov.

ABSTRACT

Background: Many cell lines currently used in medical research, such as cancer cells or stem cells, grow in confluent sheets or colonies. The biology of individual cells provide valuable information, thus the separation of touching cells in these microscopy images is critical for counting, identification and measurement of individual cells. Over-segmentation of single cells continues to be a major problem for methods based on morphological watershed due to the high level of noise in microscopy cell images. There is a need for a new segmentation method that is robust over a wide variety of biological images and can accurately separate individual cells even in challenging datasets such as confluent sheets or colonies.

Results: We present a new automated segmentation method called FogBank that accurately separates cells when confluent and touching each other. This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images. The method is based on morphological watershed principles with two new features to improve accuracy and minimize over-segmentation. First, FogBank uses histogram binning to quantize pixel intensities which minimizes the image noise that causes over-segmentation. Second, FogBank uses a geodesic distance mask derived from raw images to detect the shapes of individual cells, in contrast to the more linear cell edges that other watershed-like algorithms produce. We evaluated the segmentation accuracy against manually segmented datasets using two metrics. FogBank achieved segmentation accuracy on the order of 0.75 (1 being a perfect match). We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets. FogBank outperformed all related algorithms. The accuracy has also been visually verified on data sets with 14 cell lines across 3 imaging modalities leading to 876 segmentation evaluation images.

Conclusions: FogBank produces single cell segmentation from confluent cell sheets with high accuracy. It can be applied to microscopy images of multiple cell lines and a variety of imaging modalities. The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

Show MeSH
Related in: MedlinePlus