CLAHE-CapsNet: Efficient retina optical coherence tomography classification using capsule networks with contrast limited adaptive histogram equalization.

Manual detection of eye diseases using retina Optical Coherence Tomography (OCT) images by Ophthalmologists is time consuming, prone to errors and tedious. Previous researchers have developed a computer aided system using deep learning-based convolutional neural networks (CNNs) to aid in faster detection of the retina diseases. However, these methods find it difficult to achieve better classification performance due to noise in the OCT image. Moreover, the pooling operations in CNN reduce resolution of the image that limits the performance of the model. The contributions of the paper are in two folds. Firstly, this paper makes a comprehensive literature review to establish current-state-of-act methods successfully implemented in retina OCT image classifications. Additionally, this paper proposes a capsule network coupled with contrast limited adaptive histogram equalization (CLAHE-CapsNet) for retina OCT image classification. The CLAHE was implemented as layers to minimize the noise in the retina image for better performance of the model. A three-layer convolutional capsule network was designed with carefully chosen hyperparameters. The dataset used for this study was presented by University of California San Diego (UCSD). The dataset consists of 84,495 X-Ray images (JPEG) and 4 categories (NORMAL, CNV, DME, and DRUSEN). The images went through a grading system consisting of multiple layers of trained graders of expertise for verification and correction of image labels. Evaluation experiments were conducted and comparison of results was done with state-of-the-art models to find out the best performing model. The evaluation metrics; accuracy, sensitivity, precision, specificity, and AUC are used to determine the performance of the models. The evaluation results show that the proposed model achieves the best performing model of accuracies of 97.7%, 99.5%, and 99.3% on overall accuracy (OA), overall sensitivity (OS), and overall precision (OP), respectively. The results obtained indicate that the proposed model can be adopted and implemented to help ophthalmologists in detecting retina OCT diseases.

Predictive signs and symptoms of bacterial meningitis isolates in Northern Ghana.

Cerebrospinal meningitis (CSM) is a public health burden in Ghana that causes up to 10% mortality in confirmed cases annually. About 20% of those who survive the infection suffer permanent sequelae. The study sought to understand the predictive signs and symptoms of bacterial meningitis implicated in its outcomes. Retrospective data from the Public Health Division, Ghana Health Service on bacterial meningitis from 2015 to 2019 was used for this study. A pre-tested data extraction form was used to collect patients' information from case-based forms kept at the Disease Control Unit from 2015 to 2019. Data were transcribed from the case-based forms into a pre-designed Microsoft Excel template. The data was cleaned and imported into SPSS version 26 for analysis. Between 2015 and 2019, a total of 2446 suspected bacterial meningitis cases were included in the study. Out of these, 842 (34.4%) were confirmed. Among the confirmed cases, males constituted majority with 55.3% of the cases. Children below 14 years of age were most affected (51.4%). The pathogens commonly responsible for bacterial meningitis were Neisseria meningitidis (43.7%) and Streptococcus pneumoniae (53.0%) with their respective strains Nm W135 (36.7%), Nm X (5.1%), Spn St. 1 (26.2%), and Spn St. 12F/12A/12B/44/4 (5.3%) accounting for more than 70.0% of the confirmed cases. The presence of neck stiffness (AOR = 1.244; C.I 1.026-1.508), convulsion (AOR = 1.338; C.I 1.083-1.652), altered consciousness (AOR = 1.516; C.I 1.225-1.876), and abdominal pains (AOR = 1.404; C.I 1.011-1.949) or any of these signs and symptoms poses a higher risk for testing positive for bacterial meningitis adjusting for age. Patients presenting one and/or more of these signs and symptoms (neck stiffness, convulsion, altered consciousness, and abdominal pain) have a higher risk of testing positive for bacterial meningitis after statistically adjusting for age.

Uncertainty Estimation Using Variational Mixture of Gaussians Capsule Network for Health Image Classification.

Capsule Networks have shown great promise in image recognition due to their ability to recognize the pose, texture, and deformation of objects and object parts. However, the majority of the existing capsule networks are deterministic with limited ability to express uncertainty. Many of them tend to be overconfident on out-of-distribution data, making them less trustworthy and hence reducing their suitability for practical adoption in safety-critical areas such as health and self-driving cars. In this work, we propose a capsule network based on a variational mixture of Gaussians to train distributions of network weights as opposed to a single set of weights and enable the model to express its predictive uncertainty on out-of-distribution data. Training distributions of weights have the added advantage of avoiding overfitting on smaller datasets which are common in health and other fields. Although Bayesian neural networks are known to exhibit slow training and convergence, experimental results show that the proposed model can retrieve only relevant features, converge faster, is less computationally complex, can effectively express its predictive uncertainties, and achieve performance values that are comparable to the state-of-the-art models. This is an indication that CapsNets can exhibit the transparency, credibility, reliability, and interpretability required for practical adoption.