Biomedical subjects

Mei-Ling Huang

Publications and source records attributed to Mei-Ling Huang.

4 recordsLinked to original sources

PubMed2007

Rule extraction for glaucoma detection with summary data from StratusOCT.

PURPOSE: To extract and induce rules of association for differentiating between normal and glaucomatous eyes based on the quantitative assessment of summary data reports from the StratusOCT (optical coherence tomography; Carl Zeiss Meditec, Inc., Dublin, CA) in a Taiwan Chinese population. METHODS: One randomly selected eye of each of the 64 patients with glaucoma and each of the 71 normal subjects was included in the study. Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head analysis results) were obtained with the StratusOCT. A self-organizing map and decision tree were applied to extract features and determine rules of association for glaucoma detection. RESULTS: The average visual field mean deviation was -0.55 +/- 0.57 dB in the normal group and -4.30 +/- 3.32 dB in the glaucoma group. Vertical cup-to-disc (C/D) ratio and inferior quadrant thickness were extracted from the decision tree, and three association rules were determined for glaucoma detection. CONCLUSIONS: The precise rules of association induced by a novel application of the decision tree may enhance glaucoma detection.

Adult↗

PubMed2006

Logistic regression analysis for glaucoma diagnosis using Stratus Optical Coherence Tomography.

PURPOSES: The purposes of this study are to investigate the diagnostic performance of logistic regression analysis (LRA) applied to multidimensional information on glaucoma disease and to determine the area under receiver operator characteristic curves (AROCs) for differentiating between normal and glaucomatous eyes in the Taiwan Chinese population based on the summary data from the Stratus Optical Coherence Tomography (OCT). METHODS: One randomly selected eye from each of the 89 patients with glaucoma and from each of the 88 age- and gender-matched normal individuals were included in the study. Nine glaucomatous eyes and eight normal eyes were excluded as a result of poor OCT scans. Finally, 80 normal eyes and 80 glaucomatous eyes (mean deviation, -4.5 +/- 4.12 dB) were analyzed. The whole dataset was split into four equal sets. Each set combines 20 patients with glaucoma and 20 normal individuals. Fourfold crossvalidation was conducted. Retinal nerve fiber layer thickness and optic nerve head were measured by Stratus OCT in each patient. Twenty-five OCT parameters were included in a LRA method to determine the best combination of parameters for discriminating between glaucomatous and healthy eyes based on AROCs. RESULTS: With the LRA method, the AROC for glaucoma detection was 0.911 with sensitivity at 80% and 90% specificity were 83.7% and 80.0%, respectively. CONCLUSIONS: Compared with the OCT-provided parameters, the LRA method improved the ability to differentiate between normal and glaucomatous eyes in the Taiwan Chinese population.

Adolescent↗

PubMed2005

Discrimination between normal and glaucomatous eyes using Stratus optical coherence tomography in Taiwan Chinese subjects.

BACKGROUND: We differentiated between normal and glaucomatous eyes in the Taiwan Chinese population based solely on the quantitative assessment of summary data reports from Stratus optical coherence tomography (OCT) by comparing their area under the receiver operating characteristic (ROC) curve. METHODS: One randomly selected eye from each of the 62 patients with early glaucomatous damage (mean deviation -2.8 +/- 1.8 dB) and from each of the 62 age- and sex-matched normal individuals were included in the study. Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head analysis results) were obtained by Stratus OCT. Twenty-one OCT parameters were included in a linear discriminant analysis (LDA) using forward selection and backward elimination to determine the best combination of parameters for discriminating between glaucomatous and healthy eyes based on ROC curve area. RESULTS: The average RNFL thickness was the best individual parameter for differentiating between normal eyes and glaucomatous eyes (ROC curve area 0.793). The maximum area under the ROC curve of six input parameters (average RNFL thickness; 10, 11, and 12 o'clock segment thicknesses; cup area; and vertical integrated rim area) generated by the forward selection method was 0.881. Whereas the maximum area under the ROC curve of 15 input parameters (average RNFL thickness; 1, 3, 4, 6, 8-10, 12 o'clock segment thicknesses; vertical integrated rim area; horizontal integrated rim area; disc area; cup to disc area ratio; cup to disc horizontal ratio; and cup to disc vertical ratio) generated by backward elimination method was 0.929. CONCLUSIONS: The performance of individual parameters obtained from Stratus OCT is fairly reliable for differentiating the early glaucomatous eyes from normal eyes. However, the discriminant power increases when LDA with forward selection and backward elimination methods is applied.

Adult↗

PubMed2005

Development and comparison of automated classifiers for glaucoma diagnosis using Stratus optical coherence tomography.

PURPOSE: To develop and compare the ability of several automated classifiers to differentiate between normal and glaucomatous eyes based on the quantitative assessment of summary data reports from Stratus optical coherence tomography (OCT; Carl Zeiss Meditec Inc., Dublin, CA) in a Chinese population in Taiwan. METHODS: One randomly selected eye from each of 89 patients with glaucoma and each of 100 age- and sex-matched normal individuals were included in the study. Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head analysis results) were obtained by Stratus OCT. With the Stratus OCT parameters used as input, receiver operative characteristic (ROC) curves were generated by three methods, to classify eyes as either glaucomatous or normal: linear discriminant analysis (LDA), Mahalanobis distance (MD), and artificial neural network (ANN). The area under the ROC curve was optimized by principal component analysis (PCA). Classification accuracy was determined by cross validation. RESULTS: The average visual field mean deviation was -0.7 +/- 0.6 dB in the normal group and -2.7 +/- 1.9 dB in the glaucoma group. The areas under the ROC curves were 0.824 (LDA), 0.849 (MD), 0.821 (ANN), 0.915 (LDA with PCA), 0.991 (MD with PCA), and 0.874 (ANN with PCA). CONCLUSIONS: With Stratus OCT parameters used as input, automated classifiers show promise for discriminating between glaucomatous and normal eyes. MD measured from multivariate data can predict the severity of glaucoma through the construction of a measurement space. After PCA, implementation results show that the Mahalanobis space created by MD surpasses LDA and ANN in diagnosing glaucoma.

Adult↗