Limits...
Image-Processing Scheme to Detect Superficial Fungal Infections of the Skin.

Mäder U, Quiskamp N, Wildenhain S, Schmidts T, Mayser P, Runkel F, Fiebich M - Comput Math Methods Med (2015)

Bottom Line: The results show that the sensitivity for hyphae is 94% and 89% for singular and clustered hyphae, respectively.Although the performance is lower for the clinical images than for the test dataset, a reliable and fast diagnosis can be achieved since it is not crucial to detect every hypha to conclude that a sample consisting of several images is infected.The proposed analysis therefore enables a high diagnostic quality and a fast sample assessment to be achieved.

View Article: PubMed Central - PubMed

Affiliation: Institute of Medical Physics and Radiation Protection, Technische Hochschule Mittelhessen - University of Applied Sciences, 35390 Giessen, Germany.

ABSTRACT
The incidence of superficial fungal infections is assumed to be 20 to 25% of the global human population. Fluorescence microscopy of extracted skin samples is frequently used for a swift assessment of infections. To support the dermatologist, an image-analysis scheme has been developed that evaluates digital microscopic images to detect fungal hyphae. The aim of the study was to increase diagnostic quality and to shorten the time-to-diagnosis. The analysis, consisting of preprocessing, segmentation, parameterization, and classification of identified structures, was performed on digital microscopic images. A test dataset of hyphae and false-positive objects was created to evaluate the algorithm. Additionally, the performance for real clinical images was investigated using 415 images. The results show that the sensitivity for hyphae is 94% and 89% for singular and clustered hyphae, respectively. The mean exclusion rate is 91% for the false-positive objects. The sensitivity for clinical images was 83% and the specificity was 79%. Although the performance is lower for the clinical images than for the test dataset, a reliable and fast diagnosis can be achieved since it is not crucial to detect every hypha to conclude that a sample consisting of several images is infected. The proposed analysis therefore enables a high diagnostic quality and a fast sample assessment to be achieved.

No MeSH data available.


Related in: MedlinePlus

Binarized representation of a singular hypha (white pixel) with skeleton (red line) and perpendicular width evaluation along the exemplarily shown green lines.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4663297&req=5

fig6: Binarized representation of a singular hypha (white pixel) with skeleton (red line) and perpendicular width evaluation along the exemplarily shown green lines.

Mentions: Width Analysis. As hyphae are of uniform width and show a smooth surface, the width distribution perpendicular to the structures skeleton is calculated between two adjacent pixels for every other pixel position (example shown in Figure 6). Furthermore, junctions in the skeleton are detected to distinguish between singular and clustered hyphae. The mean thickness and the standard deviation are subsequently compared to thresholds (for singular hyphae: mean thickness between 4.4 and 9 pixel, standard deviation lower than 2.8; for clustered hyphae: mean thickness between 4.4 and 10 pixel, standard deviation lower than 12). Using this information, irregular structures such as cellulose fibers, plastic particles, other contaminations, and too thin or thick structures such as air inclusions are identified and excluded from the dataset of infected structures.


Image-Processing Scheme to Detect Superficial Fungal Infections of the Skin.

Mäder U, Quiskamp N, Wildenhain S, Schmidts T, Mayser P, Runkel F, Fiebich M - Comput Math Methods Med (2015)

Binarized representation of a singular hypha (white pixel) with skeleton (red line) and perpendicular width evaluation along the exemplarily shown green lines.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4663297&req=5

fig6: Binarized representation of a singular hypha (white pixel) with skeleton (red line) and perpendicular width evaluation along the exemplarily shown green lines.
Mentions: Width Analysis. As hyphae are of uniform width and show a smooth surface, the width distribution perpendicular to the structures skeleton is calculated between two adjacent pixels for every other pixel position (example shown in Figure 6). Furthermore, junctions in the skeleton are detected to distinguish between singular and clustered hyphae. The mean thickness and the standard deviation are subsequently compared to thresholds (for singular hyphae: mean thickness between 4.4 and 9 pixel, standard deviation lower than 2.8; for clustered hyphae: mean thickness between 4.4 and 10 pixel, standard deviation lower than 12). Using this information, irregular structures such as cellulose fibers, plastic particles, other contaminations, and too thin or thick structures such as air inclusions are identified and excluded from the dataset of infected structures.

Bottom Line: The results show that the sensitivity for hyphae is 94% and 89% for singular and clustered hyphae, respectively.Although the performance is lower for the clinical images than for the test dataset, a reliable and fast diagnosis can be achieved since it is not crucial to detect every hypha to conclude that a sample consisting of several images is infected.The proposed analysis therefore enables a high diagnostic quality and a fast sample assessment to be achieved.

View Article: PubMed Central - PubMed

Affiliation: Institute of Medical Physics and Radiation Protection, Technische Hochschule Mittelhessen - University of Applied Sciences, 35390 Giessen, Germany.

ABSTRACT
The incidence of superficial fungal infections is assumed to be 20 to 25% of the global human population. Fluorescence microscopy of extracted skin samples is frequently used for a swift assessment of infections. To support the dermatologist, an image-analysis scheme has been developed that evaluates digital microscopic images to detect fungal hyphae. The aim of the study was to increase diagnostic quality and to shorten the time-to-diagnosis. The analysis, consisting of preprocessing, segmentation, parameterization, and classification of identified structures, was performed on digital microscopic images. A test dataset of hyphae and false-positive objects was created to evaluate the algorithm. Additionally, the performance for real clinical images was investigated using 415 images. The results show that the sensitivity for hyphae is 94% and 89% for singular and clustered hyphae, respectively. The mean exclusion rate is 91% for the false-positive objects. The sensitivity for clinical images was 83% and the specificity was 79%. Although the performance is lower for the clinical images than for the test dataset, a reliable and fast diagnosis can be achieved since it is not crucial to detect every hypha to conclude that a sample consisting of several images is infected. The proposed analysis therefore enables a high diagnostic quality and a fast sample assessment to be achieved.

No MeSH data available.


Related in: MedlinePlus