The accurate segmentation of retinal blood vessels in fundus is of great practical significance to help doctors diagnose fundus diseases. Aiming to solve the problems of serious segmentation errors and low accuracy in traditional retinal segmentation, a scheme based on the combination of U-Net and Dense-Net was proposed. Firstly, the vascular feature information was enhanced by fusion limited contrast histogram equalization, median filtering, data normalization and multi-scale morphological transformation, and the artifact was corrected by adaptive gamma correction. Secondly, the randomly extracted image blocks are used as training data to increase the data and improve the generalization ability. Thirdly, stochastic gradient descent was used to optimize the Dice loss function to improve the segmentation accuracy. Finally, the Dense-U-net model was used for segmentation. The specificity, accuracy, sensitivity and AUC of this algorithm are 0.9896, 0.9698, 0.7931, 0.8946 and 0.9738, respectively. The proposed method improves the segmentation accuracy of vessels and the segmentation of small vessels.

Fundus diseases can cause irreversible vision loss in both eyes if not diagnosed and treated immediately. Due to the complexity of fundus diseases, the probability of fundus images containing two or more diseases is extremely high, while existing deep learning-based fundus image classification algorithms have low diagnostic accuracy in multi-labeled fundus images. In this paper, a multi-label classification of fundus disease with binocular fundus images is presented, using a neural network algorithm model based on attention mechanisms and feature fusion. The algorithm highlights detailed features in binocular fundus images, and then feeds them into a ResNet50 network with attention mechanisms to extract fundus image lesion features. The model obtains global features of binocular images through feature fusion and uses Softmax to classify multi-label fundus images. The ODIR binocular fundus image dataset was used to evaluate the network classification performance and conduct ablation experiments. The model’s backend is the Tensorflow framework. Through experiments on the test images, this method achieved accuracy, precision, recall, and F1 values of 94.23%, 99.09%, 99.23%, and 99.16%, respectively.

Fundus diseases cause damage to any part of the retina. Untreated fundus diseases can lead to severe vision loss and even blindness. Analyzing optical coherence tomography (OCT) images using deep learning methods can provide early screening and diagnosis of fundus diseases. In this paper, a deep learning model based on Swin Transformer V2 was proposed to diagnose fundus diseases rapidly and accurately. In this method, calculating self-attention within local windows was used to reduce computational complexity and improve its classification efficiency. Meanwhile, the PolyLoss function was introduced to further improve the model’s accuracy, and heat maps were generated to visualize the predictions of the model. Two independent public datasets, OCT 2017 and OCT-C8, were applied to train the model and evaluate its performance, respectively. The results showed that the proposed model achieved an average accuracy of 99.9% on OCT 2017 and 99.5% on OCT-C8, performing well in the automatic classification of multi-fundus diseases using retinal OCT images.

Resting-state electroencephalogram (EEG) microstate analysis resolves EEG signals into topographical maps representing discrete, sequential network activations. These maps can be used to identify patterns in EEGs that may be indicative of underlying neurological conditions. One such pattern is observed in EEGs of patients with Alzheimer’s disease (AD), where a global microstate disorganization is evident. We initially investigated the classification efficacy of microstate parameters as markers for AD classification. Subsequently, we compared the classification efficacy of EEG conventional features to ascertain the superiority of microstate features. We extracted raw EEG data from a public, independent database, OpenNeuro EEG. The raw EEG was subjected to preprocessing and band-pass filtering to obtain five distinct frequency bands. The SVM classifier was used to input the microstate feature set to determine the one with the best classification effect as the main band. In order to verify the advantage of the microstate features, the AD group and the healthy control group were filtered for the main frequency bands respectively. Then the microstate feature set and the regular feature set were extracted. The two feature sets were input into four different conventional machine learning classifiers, namely SVM, KNN, RF, and LR, in order to avoid the classifiers as the dependent variable. And the comparison of the classification results of simply two feature sets as the dependent variable can be obtained. The results show that in the Alpha (8–13 Hz) sub-band, the microstate feature set as model input to SVM is optimal for the recognition of AD, with a classification accuracy of 99.22%. The Alpha band, as the main frequency band, the microstate feature set as model input to the four classifiers obtains an average classification accuracy of 98.61%, and the average classification accuracy obtained by the conventional EEG feature set as model is 91.19%. Based on four different classifiers, microstate parameters can be served as markers to effectively classify the EEG of AD patients. The microstate feature set outperforms the conventional EEG feature set after excluding the effect of classifiers.

Timely detection of dynamic and static obstacles and accurate identification of signal lights using image processing techniques is one of the key technologies for guidance robots and is a necessity to assist blind people with safe travel. Due to the complexity of real-time road conditions, current obstacle and traffic light detection methods generally suffer from missed detection and false detection. In this paper, an improved deep learning model based on YOLOv5 is proposed to address the above problems and to achieve more accurate and faster recognition of different obstacles and traffic lights that the blind may encounter. In this model, a coordinate attention layer is added to the backbone network of YOLOv5 to improve its ability to extract effective features. Then, the feature pyramid network in YOLOv5 is replaced with a weighted bidirectional feature pyramid structure to fuse the extracted feature maps of different sizes and obtain more feature information. Finally, a SIoU loss function is introduced to increase the angle calculation of the frames. The proposed model’s detection performance for pedestrians, vehicles, and traffic lights under different conditions is tested and evaluated using the BDD100K dataset. The results show that the improved model can achieve higher mean average precision and better detection ability, especially for small targets.

A brain tumor magnetic resonance image processing algorithm can help doctors to diagnose and treat the patient’s condition, which has important application significance in clinical medicine. This paper proposes a network model based on the combination of U-net and DenseNet to solve the problems of class imbalance in multi-modal brain tumor image segmentation and the loss of effective information features caused by the integration of features in the traditional U-net network. The standard convolution blocks of the coding path and decoding path on the original network are improved to dense blocks, which enhances the transmission of features. The mixed loss function composed of the Binary Cross Entropy Loss function and the Tversky coefficient is used to replace the original single cross-entropy loss, which restrains the influence of irrelevant features on segmentation accuracy. Compared with U-Net, U-Net++, and PA-Net the algorithm in this paper has significantly improved the segmentation accuracy, reaching 0.846, 0.861, and 0.782 respectively in the Dice coefficient index of WT, TC, and ET. The PPV coefficient index has reached 0.849, 0.883, and 0.786 respectively. Compared with the traditional U-net network, the Dice coefficient index of the proposed algorithm exceeds 0.8%, 4.0%, and 1.4%, respectively, and the PPV coefficient index in the tumor core area and tumor enhancement area increases by 3% and 1.2% respectively. The proposed algorithm has the best performance in tumor core area segmentation, and its Sensitivity index has reached 0.924, which has good research significance and application value.