Limits...
Automated Segmentation of Skin Strata in Reflectance Confocal Microscopy Depth Stacks.

Hames SC, Ardigò M, Soyer HP, Bradley AP, Prow TW - PLoS ONE (2016)

Bottom Line: This approach was developed and tested using a dataset of 308 depth stacks from 54 volunteers in two age groups (20-30 and 50-70 years of age).The classification accuracy on the test set was 85.6%.The mean absolute error in determining the interface depth for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces were 3.1 μm, 6.0 μm and 5.5 μm respectively.

View Article: PubMed Central - PubMed

Affiliation: Dermatology Research Centre, The University of Queensland, School of Medicine, Translational Research Institute, Brisbane, Australia.

ABSTRACT
Reflectance confocal microscopy (RCM) is a powerful tool for in-vivo examination of a variety of skin diseases. However, current use of RCM depends on qualitative examination by a human expert to look for specific features in the different strata of the skin. Developing approaches to quantify features in RCM imagery requires an automated understanding of what anatomical strata is present in a given en-face section. This work presents an automated approach using a bag of features approach to represent en-face sections and a logistic regression classifier to classify sections into one of four classes (stratum corneum, viable epidermis, dermal-epidermal junction and papillary dermis). This approach was developed and tested using a dataset of 308 depth stacks from 54 volunteers in two age groups (20-30 and 50-70 years of age). The classification accuracy on the test set was 85.6%. The mean absolute error in determining the interface depth for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces were 3.1 μm, 6.0 μm and 5.5 μm respectively. The probabilities predicted by the classifier in the test set showed that the classifier learned an effective model of the anatomy of human skin.

No MeSH data available.


Related in: MedlinePlus

Example interfaces and probability output from the classifier.A-C) Comparison of the dermatologist identified interfaces with the automatically identified interfaces on the stacks with the highest, average and lowest accuracy respectively. D-F) The corresponding probability of each anatomical strata occurring in a section through the depth of the stack.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4835045&req=5

pone.0153208.g003: Example interfaces and probability output from the classifier.A-C) Comparison of the dermatologist identified interfaces with the automatically identified interfaces on the stacks with the highest, average and lowest accuracy respectively. D-F) The corresponding probability of each anatomical strata occurring in a section through the depth of the stack.

Mentions: A) Classification accuracy across all test stacks, organised by participant. The annotated examples are the best, average and worst accuracy stacks shown in Fig 3. B-D) The correlation between the dermatologist identified interface and the automatically identified interface for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces.


Automated Segmentation of Skin Strata in Reflectance Confocal Microscopy Depth Stacks.

Hames SC, Ardigò M, Soyer HP, Bradley AP, Prow TW - PLoS ONE (2016)

Example interfaces and probability output from the classifier.A-C) Comparison of the dermatologist identified interfaces with the automatically identified interfaces on the stacks with the highest, average and lowest accuracy respectively. D-F) The corresponding probability of each anatomical strata occurring in a section through the depth of the stack.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4835045&req=5

pone.0153208.g003: Example interfaces and probability output from the classifier.A-C) Comparison of the dermatologist identified interfaces with the automatically identified interfaces on the stacks with the highest, average and lowest accuracy respectively. D-F) The corresponding probability of each anatomical strata occurring in a section through the depth of the stack.
Mentions: A) Classification accuracy across all test stacks, organised by participant. The annotated examples are the best, average and worst accuracy stacks shown in Fig 3. B-D) The correlation between the dermatologist identified interface and the automatically identified interface for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces.

Bottom Line: This approach was developed and tested using a dataset of 308 depth stacks from 54 volunteers in two age groups (20-30 and 50-70 years of age).The classification accuracy on the test set was 85.6%.The mean absolute error in determining the interface depth for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces were 3.1 μm, 6.0 μm and 5.5 μm respectively.

View Article: PubMed Central - PubMed

Affiliation: Dermatology Research Centre, The University of Queensland, School of Medicine, Translational Research Institute, Brisbane, Australia.

ABSTRACT
Reflectance confocal microscopy (RCM) is a powerful tool for in-vivo examination of a variety of skin diseases. However, current use of RCM depends on qualitative examination by a human expert to look for specific features in the different strata of the skin. Developing approaches to quantify features in RCM imagery requires an automated understanding of what anatomical strata is present in a given en-face section. This work presents an automated approach using a bag of features approach to represent en-face sections and a logistic regression classifier to classify sections into one of four classes (stratum corneum, viable epidermis, dermal-epidermal junction and papillary dermis). This approach was developed and tested using a dataset of 308 depth stacks from 54 volunteers in two age groups (20-30 and 50-70 years of age). The classification accuracy on the test set was 85.6%. The mean absolute error in determining the interface depth for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces were 3.1 μm, 6.0 μm and 5.5 μm respectively. The probabilities predicted by the classifier in the test set showed that the classifier learned an effective model of the anatomy of human skin.

No MeSH data available.


Related in: MedlinePlus