Limits...
Three-dimensional spectral-domain optical coherence tomography data analysis for glaucoma detection.

Xu J, Ishikawa H, Wollstein G, Bilonick RA, Folio LS, Nadler Z, Kagemann L, Schuman JS - PLoS ONE (2013)

Bottom Line: Features of super pixel map were extracted and used as inputs to machine classifier (LogitBoost adaptive boosting) to automatically identify diseased eyes.The super pixel analysis showed statistically significantly higher AUC than the cpRNFL (0.855 vs. 0.707, respectively, p = 0.031, Jackknife test) when glaucoma suspects were discriminated from healthy, while no significant difference was found when confirmed glaucoma eyes were discriminated from healthy eyes.This new method has the potential to improve early detection of glaucomatous damage.

View Article: PubMed Central - PubMed

Affiliation: University of Pittsburgh Medical Center Eye Center, Eye and Ear Institute, Ophthalmology and Visual Science Research Center, Department of Ophthalmology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.

ABSTRACT

Purpose: To develop a new three-dimensional (3D) spectral-domain optical coherence tomography (SD-OCT) data analysis method using a machine learning technique based on variable-size super pixel segmentation that efficiently utilizes full 3D dataset to improve the discrimination between early glaucomatous and healthy eyes.

Methods: 192 eyes of 96 subjects (44 healthy, 59 glaucoma suspect and 89 glaucomatous eyes) were scanned with SD-OCT. Each SD-OCT cube dataset was first converted into 2D feature map based on retinal nerve fiber layer (RNFL) segmentation and then divided into various number of super pixels. Unlike the conventional super pixel having a fixed number of points, this newly developed variable-size super pixel is defined as a cluster of homogeneous adjacent pixels with variable size, shape and number. Features of super pixel map were extracted and used as inputs to machine classifier (LogitBoost adaptive boosting) to automatically identify diseased eyes. For discriminating performance assessment, area under the curve (AUC) of the receiver operating characteristics of the machine classifier outputs were compared with the conventional circumpapillary RNFL (cpRNFL) thickness measurements.

Results: The super pixel analysis showed statistically significantly higher AUC than the cpRNFL (0.855 vs. 0.707, respectively, p = 0.031, Jackknife test) when glaucoma suspects were discriminated from healthy, while no significant difference was found when confirmed glaucoma eyes were discriminated from healthy eyes.

Conclusions: A novel 3D OCT analysis technique performed at least as well as the cpRNFL in glaucoma discrimination and even better at glaucoma suspect discrimination. This new method has the potential to improve early detection of glaucomatous damage.

Show MeSH

Related in: MedlinePlus

Normalized histogram distribution of super pixel.(A) RNFL thickness and (B) super pixel size for healthy (H), glaucoma suspect (GS), and glaucomatous (G) eyes.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3569462&req=5

pone-0055476-g005: Normalized histogram distribution of super pixel.(A) RNFL thickness and (B) super pixel size for healthy (H), glaucoma suspect (GS), and glaucomatous (G) eyes.

Mentions: Super pixel map provided a qualitative representation of the structural damage. To summarize the map as quantitative disease indices, a total of 68 super pixel features were extracted and used as the inputs of machine learning classifiers analysis (Table 1). Three thresholds, Tmin, T1, and T2 were set to 50, 133, and 400 pixels respecitvely based on the experiments to obtain two sub-groups of super pixel with large size and small size. The features were calculated from all super pixels together with two sub-groups.


Three-dimensional spectral-domain optical coherence tomography data analysis for glaucoma detection.

Xu J, Ishikawa H, Wollstein G, Bilonick RA, Folio LS, Nadler Z, Kagemann L, Schuman JS - PLoS ONE (2013)

Normalized histogram distribution of super pixel.(A) RNFL thickness and (B) super pixel size for healthy (H), glaucoma suspect (GS), and glaucomatous (G) eyes.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3569462&req=5

pone-0055476-g005: Normalized histogram distribution of super pixel.(A) RNFL thickness and (B) super pixel size for healthy (H), glaucoma suspect (GS), and glaucomatous (G) eyes.
Mentions: Super pixel map provided a qualitative representation of the structural damage. To summarize the map as quantitative disease indices, a total of 68 super pixel features were extracted and used as the inputs of machine learning classifiers analysis (Table 1). Three thresholds, Tmin, T1, and T2 were set to 50, 133, and 400 pixels respecitvely based on the experiments to obtain two sub-groups of super pixel with large size and small size. The features were calculated from all super pixels together with two sub-groups.

Bottom Line: Features of super pixel map were extracted and used as inputs to machine classifier (LogitBoost adaptive boosting) to automatically identify diseased eyes.The super pixel analysis showed statistically significantly higher AUC than the cpRNFL (0.855 vs. 0.707, respectively, p = 0.031, Jackknife test) when glaucoma suspects were discriminated from healthy, while no significant difference was found when confirmed glaucoma eyes were discriminated from healthy eyes.This new method has the potential to improve early detection of glaucomatous damage.

View Article: PubMed Central - PubMed

Affiliation: University of Pittsburgh Medical Center Eye Center, Eye and Ear Institute, Ophthalmology and Visual Science Research Center, Department of Ophthalmology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.

ABSTRACT

Purpose: To develop a new three-dimensional (3D) spectral-domain optical coherence tomography (SD-OCT) data analysis method using a machine learning technique based on variable-size super pixel segmentation that efficiently utilizes full 3D dataset to improve the discrimination between early glaucomatous and healthy eyes.

Methods: 192 eyes of 96 subjects (44 healthy, 59 glaucoma suspect and 89 glaucomatous eyes) were scanned with SD-OCT. Each SD-OCT cube dataset was first converted into 2D feature map based on retinal nerve fiber layer (RNFL) segmentation and then divided into various number of super pixels. Unlike the conventional super pixel having a fixed number of points, this newly developed variable-size super pixel is defined as a cluster of homogeneous adjacent pixels with variable size, shape and number. Features of super pixel map were extracted and used as inputs to machine classifier (LogitBoost adaptive boosting) to automatically identify diseased eyes. For discriminating performance assessment, area under the curve (AUC) of the receiver operating characteristics of the machine classifier outputs were compared with the conventional circumpapillary RNFL (cpRNFL) thickness measurements.

Results: The super pixel analysis showed statistically significantly higher AUC than the cpRNFL (0.855 vs. 0.707, respectively, p = 0.031, Jackknife test) when glaucoma suspects were discriminated from healthy, while no significant difference was found when confirmed glaucoma eyes were discriminated from healthy eyes.

Conclusions: A novel 3D OCT analysis technique performed at least as well as the cpRNFL in glaucoma discrimination and even better at glaucoma suspect discrimination. This new method has the potential to improve early detection of glaucomatous damage.

Show MeSH
Related in: MedlinePlus