Diagnostic Performance of Three-Dimensional Endothelium/Descemet Membrane Complex Thickness Maps in Active Corneal Graft Rejection.

PURPOSE: To evaluate the performance of 3-dimensional (3D) endothelium/Descemet membrane complex thickness (En/DMT) maps vs total corneal thickness (TCT) maps in the diagnosis of active corneal graft rejection. DESIGN: Cross-sectional study. METHODS: Eighty-one eyes (32 clear grafts and 17 with active rejection, along with 32 age-matched control eyes) were imaged using high-definition optical coherence tomography (HD-OCT), and a custom-built segmentation algorithm was used to generate 3D color-coded maps of TCT and En/DMT of the central 6-mm cornea. Regional En/DMT and TCT were analyzed and compared between the studied groups. Receiver operating characteristic curves were used to determine the accuracy of En/DMT and TCT maps in differentiating between studied groups. Main outcome measures were regional En/DMT and TCT. RESULTS: Both regional TCT and En/DMT were significantly greater in actively rejecting grafts compared to both healthy corneas and clear grafts (P < .001). Using 3D thickness maps, central, paracentral, and peripheral En/DMT achieved 100% sensitivity and 100% specificity in diagnosing actively rejecting grafts (optimal cut-off value [OCV] of 19 µm, 24 µm, and 26 µm, respectively), vs only 82% sensitivity and 96% specificity for central TCT, OCV of 587 µm. Moreover, central, paracentral, and peripheral En/DMT correlated significantly with graft rejection severity (r = 0.972, r = 0.729, and r = 0.823, respectively; P < .001). CONCLUSION: 3D En/DMT maps can diagnose active corneal graft rejection with excellent accuracy, sensitivity, and specificity. Future longitudinal studies are required to evaluate the predictive and prognostic role of 3D En/DMT maps in corneal graft rejection.

MindEdit: A P300-based text editor for mobile devices.

Practical application of Brain-Computer Interfaces (BCIs) requires that the whole BCI system be portable. The mobility of BCI systems involves two aspects: making the electroencephalography (EEG) recording devices portable, and developing software applications with low computational complexity to be able to run on low computational-power devices such as tablets and smartphones. This paper addresses the development of MindEdit; a P300-based text editor for Android-based devices. Given the limited resources of mobile devices and their limited computational power, a novel ensemble classifier is utilized that uses Principal Component Analysis (PCA) features to identify P300 evoked potentials from EEG recordings. PCA computations in the proposed method are channel-based as opposed to concatenating all channels as in traditional feature extraction methods; thus, this method has less computational complexity compared to traditional P300 detection methods. The performance of the method is demonstrated on data recorded from MindEdit on an Android tablet using the Emotiv wireless neuroheadset. Results demonstrate the capability of the introduced PCA ensemble classifier to classify P300 data with maximum average accuracy of 78.37±16.09% for cross-validation data and 77.5±19.69% for online test data using only 10 trials per symbol and a 33-character training dataset. Our analysis indicates that the introduced method outperforms traditional feature extraction methods. For a faster operation of MindEdit, a variable number of trials scheme is introduced that resulted in an online average accuracy of 64.17±19.6% and a maximum bitrate of 6.25bit/min. These results demonstrate the efficacy of using the developed BCI application with mobile devices.

Performance analysis of a Principal Component Analysis ensemble classifier for Emotiv headset P300 spellers.

The current trend to use Brain-Computer Interfaces (BCIs) with mobile devices mandates the development of efficient EEG data processing methods. In this paper, we demonstrate the performance of a Principal Component Analysis (PCA) ensemble classifier for P300-based spellers. We recorded EEG data from multiple subjects using the Emotiv neuroheadset in the context of a classical oddball P300 speller paradigm. We compare the performance of the proposed ensemble classifier to the performance of traditional feature extraction and classifier methods. Our results demonstrate the capability of the PCA ensemble classifier to classify P300 data recorded using the Emotiv neuroheadset with an average accuracy of 86.29% on cross-validation data. In addition, offline testing of the recorded data reveals an average classification accuracy of 73.3% that is significantly higher than that achieved using traditional methods. Finally, we demonstrate the effect of the parameters of the P300 speller paradigm on the performance of the method.