Correlation-based Method for Automatic Mitotic Cell Detection in Phase Contrast Microscopy

Mirosław, Łukasz; Chorążyczewski, Artur; Buchholz, Frank; Kittler, Ralf

doi:10.1007/3-540-32390-2_74

Cited by 14 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fully automatic methodology of the microscopic image segmentation described in literature [1,11] is adjusted to the specific and relatively homogeneous in appearance cells' population and to the images captured by using a specific type of microscopic techniques. For example, methodology presented in Ref.…”

Section: Subject Of Papermentioning

confidence: 99%

Multistage morphological segmentation of bright-field and fluorescent microscopy images

Korzyńska

Iwanowski

2012

Opto-Electronics Review

View full text Add to dashboard Cite

This paper describes the multistage morphological segmentation method (MSMA) for microscopic cell images. The proposed method enables us to study the cell behaviour by using a sequence of two types of microscopic images: bright field images and/or fluorescent images. The proposed method is based on two types of information: the cell texture coming from the bright field images and intensity of light emission, done by fluorescent markers. The method is dedicated to the image sequences segmentation and it is based on mathematical morphology methods supported by other image processing techniques. The method allows for detecting cells in image independently from a degree of their flattening and from presenting structures which produce the texture. It makes use of some synergic information from the fluorescent light emission image as the support information. The MSMA method has been applied to images acquired during the experiments on neural stem cells as well as to artificial images. In order to validate the method, two types of errors have been considered: the error of cell area detection and the error of cell position using artificial images as the “gold standard”.

show abstract

Section: Subject Of Papermentioning

confidence: 99%

Multistage morphological segmentation of bright-field and fluorescent microscopy images

Korzyńska

Iwanowski

2012

Opto-Electronics Review

View full text Add to dashboard Cite

show abstract

“…Moreover, the time to process each image of our data set should be acceptable (<1 min per image) using a common computer. These are the main reasons why several algorithms can display interesting results but are not selected for comparison in our study .…”

Section: Resultsmentioning

confidence: 99%

“…In point of view of the flexibility in use, development of specific algorithms leads to focus on case study and is limited to local setting. Numerous type algorithms are also developed for cell counting or recognition but are not dedicated to output accurate information of the cell morphology like area . For example, highly variable cell shapes or sizes may reduce the efficiency of the data extraction process in the case of algorithms using pattern recognition .…”

mentioning

confidence: 99%

Algorithm for the precise detection of single and cluster cells in microfluidic applications

et al. 2016

View full text Add to dashboard Cite

Recent advances in imaging flow cytometry and microfluidic applications have led to the development of suitable mathematical algorithms capable of detecting and identifying targeted cells in images. In contrast to currently existing algorithms, we herein proposed the identification and reconstruction of cell edges based on original approaches that overcome frequent detection limitations such as halos, noise, and droplet boundaries in microfluidic applications. Reconstructed cells are then discriminated between single cells and clusters of round-shaped cells, and cell information such as the area and location of a cell in an image is output. Using this method, 76% of cells detected in an image had an error <5% of the cell area size and 41% of the image had an error <1% of the cell area size (n 5 1,000). The method developed in the present study is the first image processing algorithm designed to be flexible in use (i.e. independent of the size of an image, using a microfluidic droplet system or not, and able to recognize cell clusters in an image) and provides the scientific community with a very accurate imaging algorithm in the field of microfluidic applications. V C 2016 International Society for Advancement of CytometryKey terms algorithm; microfluidic; cell detection; cell reconstruction; imaging processing; droplet THE morphological identification of a cell offers numerous advantages when discriminating elements such as cell populations based on their shapes. However, this time-consuming method is limited to the skills of the operator and is associated with difficulty in imaging cell sorters where quick decisions must be made based on the information contained in each image. The combination of a high speed camera and algorithm has been proposed in order to routinely and rapidly measure the concentration of target cells in a sample. This recent imaging cytometric approach associated with microfluidic devices indicates that the automatic detection of a cell in an image is applicable to the identification of rare cell types (e.g., possible circulating tumor cells) without any fluorescence label (1). In this context, the morphological properties of a cell such as size area, diameter, and circularity must be calculated with the highest precision in order to limit inaccurate diagnoses.In the image processing field, numerous algorithms have been created and improved with the aim of correctly identifying the edge of an object and providing reliable data in greyscale and color images (2-7). However, in imaging flow cytometric systems and microfluidic devices, cells moving in the flow may hamper these common edge detectors and led to the incomplete detection of cell walls. To overcome this limitation and improve the detection of a cell in an image, several specific algorithms have been developed in the past decade (8-11). Although these algorithms provided interesting findings, some common limitations remained. In point of view of the flexibility in use, development of specific algorithms leads to focus on ca...

show abstract

“…2a). Correlation based methods [5,6,7,8] partly overcome those drawbacks by using cell image templates, but still there are problems (Fig. 2b).…”

Section: Introductionmentioning

confidence: 99%

Detection of hematopoietic stem cells in microscopy images using a bank of ring filters

Eom

Bise

Kanade

2010

2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

We present a method for robustly detecting hematopoietic stem cells (HSCs) in phase contrast microscopy images. HSCs appear to be easy to detect since they typically appear as round objects. However, when HSCs are touching and overlapping, showing the variations in shape and appearance, standard pattern detection methods, such as Hough transform and correlation, do not perform well. The proposed method exploits the output pattern of a ring filter bank applied to the input image, which consists of a series of matched filters with multiple-radius ring-shaped templates. By modeling the profile of each filter response as a quadratic surface, we explore the variations of peak curvatures and peak values of the filter responses when the ring radius varies. The method is validated on thousands of phase contrast microscopy images with different acquisition settings, achieving 96.5% precision and 94.4% recall.

show abstract

Correlation-based Method for Automatic Mitotic Cell Detection in Phase Contrast Microscopy

Cited by 14 publications

References 10 publications

Multistage morphological segmentation of bright-field and fluorescent microscopy images

Multistage morphological segmentation of bright-field and fluorescent microscopy images

Algorithm for the precise detection of single and cluster cells in microfluidic applications

Detection of hematopoietic stem cells in microscopy images using a bank of ring filters

Contact Info

Product

Resources

About