Limits...
Computer vision for microscopy diagnosis of malaria.

Tek FB, Dempster AG, Kale I - Malar. J. (2009)

Bottom Line: Existing works interpret the diagnosis problem differently or propose partial solutions to the problem.A critique of these works is furnished.In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described.

View Article: PubMed Central - HTML - PubMed

Affiliation: Applied DSP & VLSI Research Group, University of Westminster, London, UK. boraytek@yahoo.co.uk

ABSTRACT
This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.

Show MeSH

Related in: MedlinePlus

Size granulometry vs. area granulometry. (a) negative image of the grey level sickle cell image, (b) granulometry using disk shaped structuring elements, (c) area granulometry, (d) area granulometry based cell size estimation varies in different fields of a thin film although the magnification is constant.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2719653&req=5

Figure 4: Size granulometry vs. area granulometry. (a) negative image of the grey level sickle cell image, (b) granulometry using disk shaped structuring elements, (c) area granulometry, (d) area granulometry based cell size estimation varies in different fields of a thin film although the magnification is constant.

Mentions: To provide a comparison, Figure 4 shows the plots of granulometry and area granulometry calculations on the grey level negative of a thin film image of a specimen with sickle cell condition (irregular cell shapes). In this image, the RBC diameters changes between 20–35 pixels. Since RBCs are not all circular and homogeneous (they may have holes), size-granulometry, which uses circular structuring elements, could not produce an informative result. On the other hand, area granulometry is more accurate because there is no assumption on the shape of the cells and it has the computational advantage because it can be computed within a single pass and independent of the number of scales [63]. Therefore, it should be preferred to granulometry with the fixed shape structuring elements.


Computer vision for microscopy diagnosis of malaria.

Tek FB, Dempster AG, Kale I - Malar. J. (2009)

Size granulometry vs. area granulometry. (a) negative image of the grey level sickle cell image, (b) granulometry using disk shaped structuring elements, (c) area granulometry, (d) area granulometry based cell size estimation varies in different fields of a thin film although the magnification is constant.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2719653&req=5

Figure 4: Size granulometry vs. area granulometry. (a) negative image of the grey level sickle cell image, (b) granulometry using disk shaped structuring elements, (c) area granulometry, (d) area granulometry based cell size estimation varies in different fields of a thin film although the magnification is constant.
Mentions: To provide a comparison, Figure 4 shows the plots of granulometry and area granulometry calculations on the grey level negative of a thin film image of a specimen with sickle cell condition (irregular cell shapes). In this image, the RBC diameters changes between 20–35 pixels. Since RBCs are not all circular and homogeneous (they may have holes), size-granulometry, which uses circular structuring elements, could not produce an informative result. On the other hand, area granulometry is more accurate because there is no assumption on the shape of the cells and it has the computational advantage because it can be computed within a single pass and independent of the number of scales [63]. Therefore, it should be preferred to granulometry with the fixed shape structuring elements.

Bottom Line: Existing works interpret the diagnosis problem differently or propose partial solutions to the problem.A critique of these works is furnished.In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described.

View Article: PubMed Central - HTML - PubMed

Affiliation: Applied DSP & VLSI Research Group, University of Westminster, London, UK. boraytek@yahoo.co.uk

ABSTRACT
This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.

Show MeSH
Related in: MedlinePlus