A hybrid model for the detection of retinal disorders using artificial intelligence techniques.

The prevalence of vision impairment is increasing at an alarming rate. The goal of the study was to create an automated method that uses optical coherence tomography (OCT) to classify retinal disorders into four categories: choroidal neovascularization, diabetic macular edema, drusen, and normal cases. This study proposed a new framework that combines machine learning and deep learning-based techniques. The utilized classifiers were support vector machine (SVM), K-nearest neighbor (K-NN), decision tree (DT), and ensemble model (EM). A feature extractor, the InceptionV3 convolutional neural network, was also employed. The performance of the models was evaluated against nine criteria using a dataset of 18000 OCT images. For the SVM, K-NN, DT, and EM classifiers, the analysis exhibited state-of-the-art performance, with classification accuracies of 99.43%, 99.54%, 97.98%, and 99.31%, respectively. A promising methodology has been introduced for the automatic identification and classification of retinal disorders, leading to reduced human error and saved time.

Computer-aided diagnosis system for retinal disorder classification using optical coherence tomography images.

The incidence of vision impairment is rapidly increasing. Diagnosis and classifying retinal abnormalities in ophthalmological applications is a significant challenge. Using Optical Coherence Tomography (OCT), the study aims to develop a computer aided diagnosis system for detecting and classifying retinal disorders. Choroidal neovascularization, diabetic macular edema, drusen, and normal cases are the investigated groups. Both deep learning and machine learning are combined to build the system. The SqueezeNet neural network was modified to extract features. The Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Decision Tree (DT), and Ensemble Model (EM) algorithms were used for disorder classification. The Bayesian optimization technique was also used to determine the best hyperparameters for each model. The model' performance was evaluated through nine criteria using 12,000 OCT images. The results have demonstrated accuracies of 97.39, 97.47, 96.98, and 95.25% for the SVM, K-NN, DT, and EM, respectively. When results are compared to relevant studies in terms of accuracy and tested samples, they show superior performance. As a result, a novel computer-aided diagnosis system for detecting and classifying retinal diseases has been developed, reducing human error while also saving time.

Rapid Characterization and Parameter Space Exploration of Perovskites Using an Automated Routine.

Hybrid, e.g., organic inorganic, perovskites from the type methylammonium lead iodide CH3NH3PbI3 are promising solar cell materials. However, due to the large parameter space spanned by the manifold combinations of divalent metals with organic cations and anions, an efficient approach is needed to rapidly test and categorize new promising materials. Herein, we developed a high throughput approach for the automated synthesis of perovskite layers with different precursor ratios at varying annealing temperatures. The layers were analyzed by optical absorption and photoluminescence (PL) spectroscopy as well as X-ray diffraction (XRD) and evaluated using two different procedures. The first one is a stepwise exclusion of nonperforming reactant ratios and synthesis conditions by using both spectroscopic techniques, followed by a final validation of the procedure by XRD. In the second procedure, only PL results were consulted in combination with high throughput screening using design of experiments (DoE) to reduce the total number of experiments needed and compared to the manual cascade approach. Noteworthy, by simple PL screening, it was possible to identify the best ratio of perovskite to byproducts and annealing temperature. Thus, only with PL, more detailed results as with the manual protocol were reached, while at the same time the effort for characterization was significantly reduced (by 60% of the experimental time). In conclusion, our approach opens a way toward fast and efficient identification of new promising materials under different reaction and process conditions.