Optimization of pneumonia CT classification model using RepVGG and spatial attention features.

Introduction: Pneumonia is a common and widespread infectious disease that seriously affects the life and health of patients. Especially in recent years, the outbreak of COVID-19 has caused a sharp rise in the number of confirmed cases of epidemic spread. Therefore, early detection and treatment of pneumonia are very important. However, the uneven gray distribution and structural intricacy of pneumonia images substantially impair the classification accuracy of pneumonia. In this classification task of COVID-19 and other pneumonia, because there are some commonalities between this pneumonia, even a small gap will lead to the risk of prediction deviation, it is difficult to achieve high classification accuracy by directly using the current network model to optimize the classification model. Methods: Consequently, an optimization method for the CT classification model of COVID-19 based on RepVGG was proposed. In detail, it is made up of two essential modules, feature extraction backbone and spatial attention block, which allows it to extract spatial attention features while retaining the benefits of RepVGG. Results: The model's inference time is significantly reduced, and it shows better learning ability than RepVGG on both the training and validation sets. Compared with the existing advanced network models VGG-16, ResNet-50, GoogleNet, ViT, AlexNet, MobileViT, ConvNeXt, ShuffleNet, and RepVGG_b0, our model has demonstrated the best performance in a lot of indicators. In testing, it achieved an accuracy of 0.951, an F1 score of 0.952, and a Youden index of 0.902. Discussion: Overall, multiple experiments on the large dataset of SARS-CoV-2 CT-scan dataset reveal that this method outperforms most basic models in terms of classification and screening of COVID-19 CT, and has a significant reference value. Simultaneously, in the inspection experiment, this method outperformed other networks with residual structures.

Classification of Diabetic Retinopathy Severity in Fundus Images Using the Vision Transformer and Residual Attention.

Diabetic retinopathy (DR) is a common retinal vascular disease, which can cause severe visual impairment. It is of great clinical significance to use fundus images for intelligent diagnosis of DR. In this paper, an intelligent DR classification model of fundus images is proposed. This method can detect all the five stages of DR, including of no DR, mild, moderate, severe, and proliferative. This model is composed of two key modules. FEB, feature extraction block, is mainly used for feature extraction of fundus images, and GPB, grading prediction block, is used to classify the five stages of DR. The transformer in the FEB has more fine-grained attention that can pay more attention to retinal hemorrhage and exudate areas. The residual attention in the GPB can effectively capture different spatial regions occupied by different classes of objects. Comprehensive experiments on DDR datasets well demonstrate the superiority of our method, and compared with the benchmark method, our method has achieved competitive performance.

Longitudinal Changes in Functional Connectivity of the Caudate Is Associated With Recovery From Bell's Palsy.

Several studies have demonstrated through resting-state functional magnetic resonance imaging (fMRI) that functional connectivity changes are important in the recovery from Bell's palsy (BP); however, these studies have only focused on the cortico-cortical connectivity. It is unclear how corticostriatal connectivity relates to the recovery process of patients with BP. In the present study, we evaluated the relationship between longitudinal changes of caudate-based functional connectivity and longitudinal changes of facial performance in patients with intractable BP. Twenty-one patients with intractable BP underwent resting-state fMRI as well as facial behavioral assessments prior to treatment (PT) and at the middle stage of treatment (MT); and 21 age- and sex-matched healthy controls (HC) were recruited and received the same protocol. The caudate was divided into dorsal and ventral sub-regions and separate functional connectivity was calculated. Compared with HC, patients with intractable BP at the PT stage showed decreased functional connectivity of both the dorsal and ventral caudate mainly distributed in the somatosensory network, including the bilateral precentral gyrus (MI), left postcentral gyrus, media frontal gyrus, and superior temporal gyrus (STG). Alternatively, patients in the MT stage showed decreased functional connectivity primarily distributed in the executive network and somatosensory network, including the bilateral cingulate cortex (CC), left anterior cingulate cortex (LACC), inferior prefrontal gyrus (IFG), MI, STG, and paracentral lobe. The longitudinal changes in functional connectivity of both the dorsal and ventral caudate were mainly observed in the executive network, including the right ACC, left CC, and IFG. Functional connectivity changes in the right ACC and left IFG were significantly correlated with changes in facial behavioral performance. These findings indicated that corticostriatal connectivity changes are associated with recovery from BP.