One of the most prevalent chronic conditions that can result in permanent vision loss is diabetic retinopathy (DR). Diabetic retinopathy occurs in five stages: no DR, and mild, moderate, severe, and proliferative DR. The early detection of DR is essential for preventing vision loss in diabetic patients. In this paper, we propose a method for the detection and classification of DR stages to determine whether patients are in any of the non-proliferative stages or in the proliferative stage. The hybrid approach based on image preprocessing and ensemble features is the foundation of the proposed classification method. We created a convolutional neural network (CNN) model from scratch for this study. Combining Local Binary Patterns (LBP) and deep learning features resulted in the creation of the ensemble features vector, which was then optimized using the Binary Dragonfly Algorithm (BDA) and the Sine Cosine Algorithm (SCA). Moreover, this optimized feature vector was fed to the machine learning classifiers. The SVM classifier achieved the highest classification accuracy of 98.85% on a publicly available dataset, i.e., Kaggle EyePACS. Rigorous testing and comparisons with state-of-the-art approaches in the literature indicate the effectiveness of the proposed methodology.

This paper addresses the problem of event detection and localization in long football (soccer) videos. Our key idea is that understanding the long-range dependencies between video frames is imperative for accurate event localization in long football videos. Additionally, proper event detection is not likely for fast movements in football videos without considering mid-range and short-range correlations between neighboring video frames. We argue that event spotting can be considerably improved by considering short-range to long-range frame dependencies in a unified architecture. To model long-range and mid-range dependencies, we propose to use the dilated recurrent neural network (DilatedRNN) with long short-term memory (LSTM) units, grounded on two-stream convolutional neural network (Two-stream CNN) features. While two-stream CNN extracts local spatiotemporal features necessary for fine-level details, the DilatedRNN makes the information obtained from distant frames available for the classifier and spotting algorithms. Evaluating our event spotting algorithm on the largest publicly available benchmark football dataset -SoccerNet- shows an accuracy improvement of 0.8% - 13.6% compared to state of the art, and up to 30.1% accuracy gain in comparison to the baselines. We also investigate the contribution of each neural network component in spotting accuracy through an extensive ablation study.

Background: Artificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification. Methods: External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance. Results: RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs. Conclusion: In general, all DLMs have similar performance on ERR identification. However, the performance can be improved by combining FST with DLMs.

Age estimation is an essential task in medical dentistry and forensic sciences. Dental Age Estimation (DAE) is one of the most common methods for age estimation. Teeth are commonly used for age estimation because the schedules of tooth development and eruption are barely affected by the environment, nutrition, and socio-economic factors. However, conventional DAE methods are manually performed by clinicians, exposing bias and error to the estimated age. Moreover, the potentials of buccal alveolar bone level in DAE are rarely investigated. The aim of this study is to assess the effectiveness of buccal alveolar bone level of mandibular posterior teeth in DAE using Artificial Intelligence (AI) for children. A total of 421 Dental Panoramic Tomography (DPT) of children ranging from 5 to 15 years of age were used to train multiple UNet segmentation models. Segmented images of teeth were extracted and fed into a Localization Convolutional Neural Network (CNN) to train them for measuring buccal alveolar bone level. Moreover, the buccal alveolar bone level measurements were then fed to the machine learning regression models for DAE. The transfer learning based UNet with VGG16 as its backbone achieved the best performance with an IoU score of 0.66 and the best performing Localization CNN achieved Mean Squared Error (MSE) of 0.0009 and [Formula: see text] score of 0.8266. The Support Vector Machine (SVM) regression model achieved the best mean absolute error of 0.99 year. The results revealed the potential of buccal alveolar bone level for dental age estimation in children. Best performing model achieved an acceptable Mean Absolute Error (MAE) and similar results to Demirjian and London Atlas methods performed by human experts, showing promising results. Not applicable.