Complex wavelet based quality assessment for AS-OCT images with application to Angle Closure Glaucoma diagnosis.

BACKGROUND AND OBJECTIVES: Angle closure disease in the eye can be detected using time-domain Anterior Segment Optical Coherence Tomography (AS-OCT). The Anterior Chamber (AC) characteristics can be quantified from AS-OCT image, which is dependent on the image quality at the image acquisition stage. To date, to the best of our knowledge there are no objective or automated subjective measurements to assess the quality of AS-OCT images. METHODS: To address AS-OCT image quality assessment issue, we define a method for objective assessment of AS-OCT images using complex wavelet based local binary pattern features. These features are pooled using the Naïve Bayes classifier to obtain the final quality parameter. To evaluate the proposed method, a subjective assessment has been performed by clinical AS-OCT experts, who graded the quality of AS-OCT images on a scale of good, fair, and poor. This was done based on the ability to identify the AC structures including the position of the scleral spur. RESULTS: We compared the results of the proposed objective assessment with the subjective assessments. From this comparison, it is validated that the proposed objective assessment has the ability of differentiating the good and fair quality AS-OCT images for glaucoma diagnosis from the poor quality AS-OCT images. CONCLUSIONS: This proposed algorithm is an automated approach to evaluate the AS-OCT images with the intention for collecting of high quality data for further medical diagnosis. Our proposed quality index has the ability of automatic objective and quantitative assessment of AS-OCT image quality and this quality index is similar to glaucoma specialist.

Automated anterior segment OCT image analysis for Angle Closure Glaucoma mechanisms classification.

BACKGROUND AND OBJECTIVES: Angle closure glaucoma (ACG) is an eye disease prevalent throughout the world. ACG is caused by four major mechanisms: exaggerated lens vault, pupil block, thick peripheral iris roll, and plateau iris. Identifying the specific mechanism in a given patient is important because each mechanism requires a specific medication and treatment regimen. Traditional methods of classifying these four mechanisms are based on clinically important parameters measured from anterior segment optical coherence tomography (AS-OCT) images, which rely on accurate segmentation of the AS-OCT image and identification of the scleral spur in the segmented AS-OCT images by clinicians. METHODS: In this work, a fully automated method of classifying different ACG mechanisms based on AS-OCT images is proposed. Since the manual diagnosis mainly based on the morphology of each mechanism, in this study, a complete set of morphological features is extracted directly from raw AS-OCT images using compound image transforms, from which a small set of informative features with minimum redundancy are selected and fed into a Naïve Bayes Classifier (NBC). RESULTS: We achieved an overall accuracy of 89.2% and 85.12% with a leave-one-out cross-validation and 10-fold cross-validation method, respectively. This study proposes a fully automated way for the classification of different ACG mechanisms, which is without intervention of doctors and less subjective when compared to the existing methods. CONCLUSIONS: We directly extracted the compound image transformed features from the raw AS-OCT images without any segmentation and parameter measurement. Our method provides a completely automated and efficient way for the classification of different ACG mechanisms.

Learning ECOC Code Matrix for Multiclass Classification with Application to Glaucoma Diagnosis.

Classification of different mechanisms of angle closure glaucoma (ACG) is important for medical diagnosis. Error-correcting output code (ECOC) is an effective approach for multiclass classification. In this study, we propose a new ensemble learning method based on ECOC with application to classification of four ACG mechanisms. The dichotomizers in ECOC are first optimized individually to increase their accuracy and diversity (or interdependence) which is beneficial to the ECOC framework. Specifically, the best feature set is determined for each possible dichotomizer and a wrapper approach is applied to evaluate the classification accuracy of each dichotomizer on the training dataset using cross-validation. The separability of the ECOC codes is maximized by selecting a set of competitive dichotomizers according to a new criterion, in which a regularization term is introduced in consideration of the binary classification performance of each selected dichotomizer. The proposed method is experimentally applied for classifying four ACG mechanisms. The eye images of 152 glaucoma patients are collected by using anterior segment optical coherence tomography (AS-OCT) and then segmented, from which 84 features are extracted. The weighted average classification accuracy of the proposed method is 87.65 % based on the results of leave-one-out cross-validation (LOOCV), which is much better than that of the other existing ECOC methods. The proposed method achieves accurate classification of four ACG mechanisms which is promising to be applied in diagnosis of glaucoma.

Cross-Examination for Angle-Closure Glaucoma Feature Detection.

Effective feature selection plays a vital role in anterior segment imaging for determining the mechanism involved in angle-closure glaucoma (ACG) diagnosis. This research focuses on the use of redundant features for complex disease diagnosis such as ACG using anterior segment optical coherence tomography images. Both supervised [minimum redundancy maximum relevance (MRMR)] and unsupervised [Laplacian score (L-score)] feature selection algorithms have been cross-examined with different ACG mechanisms. An AdaBoost machine learning classifier is then used for classifying the five various classes of ACG mechanism such as iris roll, lens, pupil block, plateau iris, and no mechanism using both feature selection methods. The overall accuracy has shown that the usefulness of redundant features by L-score method in improved ACG diagnosis compared to minimum redundant features by MRMR method.