The SARS‐COV‐2 virus, which causes COVID‐19 disease, continues to threaten the whole world with its mutations. Many methods developed for COVID‐19 detection are validated on the data sets generally including severe forms of the disease. Since the severe forms of the disease have prominent signatures on X‐ray images, the performance to be achieved is high. To slow the spread of the disease, effective computer‐assisted screening tools with the ability to detect the mild and the moderate forms of the disease that do not have prominent signatures are needed. In this work, various pretrained networks, namely GoogLeNet, ResNet18, SqueezeNet, ShuffleNet, EfficientNetB0, and Xception, are used as feature extractors for the COVID‐19 detection with severity level analysis. The best feature extraction layer for each pre‐trained network is determined to optimize the performance. After that, features obtained by the best layer are selected by following a wrapper‐based feature selection strategy using the features ranked based on Laplacian scores. The experimental results achieved on two publicly available data sets including all the forms of COVID‐19 disease reveal that the method generalized well on unseen data. Moreover, 66.67%, 90.32%, and 100% sensitivity are obtained in the detection of mild, moderate, and severe cases, respectively.

In this study, a deep learning method for kidney stone detection is proposed. The method utilizes transfer learning by extracting features from a pre-trained ImageNet model. However, unlike traditional transfer learning, which directly applies or fine-tunes a pre-trained model, the proposed approach integrates a custom-designed CNN that operates in parallel with the pre-trained network. The feature maps obtained from both networks are fused to enhance the model's representation power. After this integration, task-specific classification layers are added, and the training process is conducted on both the classification layers and the optimized model. This approach improves the overall performance of the model while providing a more efficient training process. As part of this study, a new dataset was created, consisting of 2166 axial slice images from 241 patients and 2018 axial slice images from 46 healthy individuals. Experiments conducted using EfficientNetV2s, MobileNetV4s, SqueezeNet, and ResNet18-based models revealed that the EfficientNetV2s and MobileNetV4s-based models excelled in terms of accuracy, while the SqueezeNet and ResNet18-based models provided stronger results in terms of interpretability.

Kidney stone disease is a major global health concern due to its rising prevalence and related complications. Although computed tomography (CT) is highly sensitive for diagnosis, its volumetric nature increases radiologists’ workload and review time. This study proposes a lightweight and low-cost deep learning-based pre-classification model to distinguish between CT slices containing the kidney and those that do not, as a preliminary step for kidney stone detection systems. The model aims to eliminate irrelevant slices and direct only meaningful images to both the second-stage AI model and the radiologist. Vision Transformer (ViT) was used to capture the global spatial context of the kidney, while ResNet18 extracted local features. These features were fused and classified using a shallow neural network. The model was tested within an interactive interface built using real patient data and integrated into a pilot application. Results showed that the proposed system achieved an average of 64.1% time saving per patient (~24 minutes) by filtering out non-relevant slices, with 89.4% accuracy, 89.4% recall, and 89.5% specificity. These findings suggest that the model is a practical and efficient pre-screening component for clinical workflows and highlights the importance of pilot testing and expert feedback before real-world deployment of AI systems.