Convolutional neural network for automated classification of osteonecrosis and related mandibular trabecular patterns.

Objective: The present study aimed to develop and validate a tool for the automated classification of normal, affected, and osteonecrosis mandibular trabecular bone patterns in panoramic radiographs using convolutional neural networks (CNNs). Methods: A dataset of 402 panoramic images from 376 patients was selected, comprising 112 control radiographs from healthy patients and 290 images from patients treated with antiresorptive drugs (ARD). The latter was subdivided in 70 radiographs showing thickening of the lamina dura, 128 with abnormal bone patterns, and 92 images of clinically diagnosed osteonecrosis of the jaw (ONJ). Four pre-trained CNNs were fined-tuned and customized to detect and classify the different bone patterns. The best performing network was selected to develop the classification tool. The output was arranged as a colour-coded risk index showing the category and their odds. Classification performance of the networks was assessed through evaluation metrics, receiver operating characteristic curves (ROC), and a confusion matrix. Furthermore, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualise class-discriminative regions. Results: All networks correctly detected and classified the mandibular bone patterns with optimal performance metrics. InceptionResNetV2 showed the best results with an accuracy of 96 %, precision, recall and F1-score of 93 %, and a specificity of 98 %. Overall, most misclassifications occurred between normal and abnormal trabecular bone patterns. Conclusion: CNNs offer reliable potentials for automatic classification of abnormalities in the mandibular trabecular bone pattern in panoramic radiographs of antiresorptive treated patients. Clinical significance: A novel method that supports clinical decision making by identifying sites at high risk for ONJ.

Investigation of Effectiveness of Shuffled Frog-Leaping Optimizer in Training a Convolution Neural Network.

One of the leading algorithms and architectures in deep learning is Convolution Neural Network (CNN). It represents a unique method for image processing, object detection, and classification. CNN has shown to be an efficient approach in the machine learning and computer vision fields. CNN is composed of several filters accompanied by nonlinear functions and pooling layers. It enforces limitations on the weights and interconnections of the neural network to create a good structure for processing spatial and temporal distributed data. A CNN can restrain the numbering of free parameters of the network through its weight-sharing property. However, the training of CNNs is a challenging approach. Some optimization techniques have been recently employed to optimize CNN's weight and biases such as Ant Colony Optimization, Genetic, Harmony Search, and Simulated Annealing. This paper employs the well-known nature-inspired algorithm called Shuffled Frog-Leaping Algorithm (SFLA) for training a classical CNN structure (LeNet-5), which has not been experienced before. The training method is investigated by employing four different datasets. To verify the study, the results are compared with some of the most famous evolutionary trainers: Whale Optimization Algorithm (WO), Bacteria Swarm Foraging Optimization (BFSO), and Ant Colony Optimization (ACO). The outcomes demonstrate that the SFL technique considerably improves the performance of the original LeNet-5 although using this algorithm slightly increases the training computation time. The results also demonstrate that the suggested algorithm presents high accuracy in classification and approximation in its mechanism.

Lung Infection Segmentation for COVID-19 Pneumonia Based on a Cascade Convolutional Network from CT Images.

The COVID-19 pandemic is a global, national, and local public health concern which has caused a significant outbreak in all countries and regions for both males and females around the world. Automated detection of lung infections and their boundaries from medical images offers a great potential to augment the patient treatment healthcare strategies for tackling COVID-19 and its impacts. Detecting this disease from lung CT scan images is perhaps one of the fastest ways to diagnose patients. However, finding the presence of infected tissues and segment them from CT slices faces numerous challenges, including similar adjacent tissues, vague boundary, and erratic infections. To eliminate these obstacles, we propose a two-route convolutional neural network (CNN) by extracting global and local features for detecting and classifying COVID-19 infection from CT images. Each pixel from the image is classified into the normal and infected tissues. For improving the classification accuracy, we used two different strategies including fuzzy c-means clustering and local directional pattern (LDN) encoding methods to represent the input image differently. This allows us to find more complex pattern from the image. To overcome the overfitting problems due to small samples, an augmentation approach is utilized. The results demonstrated that the proposed framework achieved precision 96%, recall 97%, F score, average surface distance (ASD) of 2.8 ± 0.3 mm, and volume overlap error (VOE) of 5.6 ± 1.2%.