Accurate noninvasive diagnosis of retinal disorders is required for appropriate treatment or precision medicine. This work proposes a multi-stage classification network built on a multi-scale (pyramidal) feature ensemble architecture for retinal image classification using optical coherence tomography (OCT) images. First, a scale-adaptive neural network is developed to produce multi-scale inputs for feature extraction and ensemble learning. The larger input sizes yield more global information, while the smaller input sizes focus on local details. Then, a feature-rich pyramidal architecture is designed to extract multi-scale features as inputs using DenseNet as the backbone. The advantage of the hierarchical structure is that it allows the system to extract multi-scale, information-rich features for the accurate classification of retinal disorders. Evaluation on two public OCT datasets containing normal and abnormal retinas (e.g., diabetic macular edema (DME), choroidal neovascularization (CNV), age-related macular degeneration (AMD), and Drusen) and comparison against recent networks demonstrates the advantages of the proposed architecture’s ability to produce feature-rich classification with average accuracy of 97.78%, 96.83%, and 94.26% for the first (binary) stage, second (three-class) stage, and all-at-once (four-class) classification, respectively, using cross-validation experiments using the first dataset. In the second dataset, our system showed an overall accuracy, sensitivity, and specificity of 99.69%, 99.71%, and 99.87%, respectively. Overall, the tangible advantages of the proposed network for enhanced feature learning might be used in various medical image classification tasks where scale-invariant features are crucial for precise diagnosis.

In this study, we took advantage of the emergence of accurate biomechanical human hand models to develop a system in which the interaction between a human arm and a rehabilitation robot while performing a planar trajectory tracking task can be simulated. Seven biomechanical arm models were based on the 11-degree-of-freedom Dynamic Arm Simulation model and implemented in OpenSim. The model of the robot was developed in MatlabSimulink and interaction between the arm and robot models was achieved using the OpenSim API. The models were tested by simulating the performance of each model while moving the end effector of a simulated planar robot model through an elliptical trajectory with an eccentricity of 0.94. Without assistance from the robot, the average root-mean-square error (RMSE) for all subjects was 3.98 mm. With the simulated robot providing assistive torque, the average RMSE error reduced to 2.88 mm. The test was repeated after modifying the length of the robot links, and an average RMSE of 2.91 mm recorded. A single-factor ANOVA test revealed that there was no significant difference in the RMSE for the two different robot geometries (p-value = 0.479), revealing that the simulator was not sensitive to robot geometry.