Variational Autoencoder(VAE) combines the ideas of autoencoders and variational inference, introducing the concept of latent space and variational inference to endow autoencoders to generate new images. VAE typically assumes that data follows a Gaussian distribution, but real data may follow other distributions. This inconsistency between the assumption and the true distribution can affect the modeling and reconstruction capabilities of VAE, which makes it difficult for traditional models to accurately capture the true distribution. To address the aforementioned issues, we propose a Prior Distribution Guided Gaussian Mixture Variational Autoencoder(PDGM-VAE). Specifically, we construct a Gaussian Mixture Prior Learner (GMPL) to capture complex features of the data distribution, enabling the model to learn and obtain a Gaussian mixture distribution that is reasonable and close to the real data distributions, which is then used as the prior distribution in the network. Furthermore, we build a Semantic-Aware Module with Embedded Prior Distribution (SAMEPD), integrating data and label information to learn the distribution parameters, enabling the network to learn and utilize the semantic knowledge contained in the labels. During training, by approximating the posterior distribution to the prior distribution, we enhance the model’s modeling and reconstruction capabilities, improving the quality of generated images. We evaluated the image generation task on five public datasets, and based on the FID metric, our proposed method outperformed other VAE methods.

The functional brain network (FBN) serves as an important tool for investigating neurological and mental disorders. Unlike many traditional networks whose structures are often known in advance, FBNs need to be estimated from neuroimaging or electrophysiological data, and their quality generally determines the performance of downstream tasks, particularly in disorder detection. Recent studies have shown that high-order FBNs tend to achieve better discriminative performance, while some other work indicates that increasing the order of FBN does not necessarily bring additional gains in discriminative performance and may even lead to a rapid decline in discriminability. To fully leverage information across different-order FBNs and identify optimal order for downstream tasks, we design an adaptive high-order FBN fusion learning framework (AHFL) with attention mechanism for brain disorder detection. Specifically, we first construct a series of FBNs with continuously increasing orders and propose a data-driven approach to evaluate each order's contribution to the classification performance. The self-attention mechanism is employed to capture contextual dependencies during the sequential generation of multi-order FBNs, thereby offering a natural fusion approach. Experimental evidence shows that the proposed method achieves superior performance compared to the baseline. In particular, we find that third-order FBN is achieved the highest weights, playing a crucial role for the detection of autism spectrum disorder (ASD), whereas second-order FBN is the most effective for identifying patients with major depressive disorder (MDD). Our findings advance the identification of discriminative high-order FBNs and establish a generalizable diagnostic framework for brain disorders.

Choroidal neovascularization (CNV) classification is a fine-grained classification task. Accurate classification of CNV in optical coherence tomography (OCT) images is crucial for clinical treatment. However, image acquisition noise degrades image quality and exacerbates confirmation bias from class imbalance in medical datasets. Moreover, significant inter-class ambiguity in fine-grained categories can misclassify informative samples (e.g., hard samples or minority class samples) when generating pseudo-labels, leading to sub-optimal classifiers. To address these challenges, we propose a difficulty-aware pseudo-label correction network (DPLC-Net). Specifically, we designed a robust feature mining module using feature similarity loss to maintain consistency between generated adversarial and original samples, enabling noise-resistant feature learning. A difficulty-aware pseudo-label correction module mines and corrects potential noisy pseudo-labels to improve classification performance. Finally, to alleviate data bias and leverage all unlabeled samples, we integrated a hybrid consistency and pseudo-labeling module comprising adaptive weighted consistency loss (AWCL) and class-aware dynamic threshold strategy (CDTS). AWCL adaptively learns weights for unlabeled samples, effectively utilizing all unlabeled data through weighted consistency loss. CDTS dynamically adjusts confidence thresholds based on class distribution and model learning status, improving pseudo-label quantity and quality. Experiments on private and public OCT datasets demonstrate that our method outperforms state-of-the-art methods.

Functional brain networks (FBNs) derived from resting-state functional Magnetic Resonance Imaging (rs-fMRI) have become pivotal tools for the auxiliary diagnosis of brain disorders, including Alzheimer's Disease (AD) and Major Depressive Disorder (MDD). However, most existing FBN analysis methods struggle to effectively capture both the temporal dynamics of rs-fMRI data and the hierarchical topological structures within FBNs, due to the inherent spatiotemporal complexity of brain activities. To address these challenges, we propose a novel framework for brain network analysis, called Crossattentioned Dynamic Hierarchical representation learning with Mamba fusion (CDHM). CDHM includes four principal phases: (1) dynamic FBNs construction via overlapping sliding windows, (2) cross-attentioned spatial encoding to capture local-to-global spatial interactions, (3) hierarchical graph pooling to distill multiscale FBN organisation, and (4) Mamba-based fusion modelling long-range temporal dependency and adaptive information flow regulation. Our framework pioneers synergistic integration of spatial cross-attention mechanisms with Mamba-based temporal fusion, enabling joint learning of transient neural dynamics and multi-scale hierarchical brain representations. We validate our approach through comprehensive experiments on two publicly available datasets, demonstrating superior performance compared to existing methods.

In clinical practice, obtaining a large amount of labeled CNV data is very difficult. Semi-supervised learning can effectively utilize a large amount of unlabeled CNV data. Since CNV has complex features such as blurred and unevenly distributed pixels on the edges, there are differences in the segmentation difficulty between pixels in the same image. Existing semi-supervised segmentation methods do not consider the segmentation difficulty of pixels, which will reduce the segmentation accuracy. To address this problem, we propose a dual difficulty-aware adaptive pseudo-label learning (D2APL) method for semi-supervised CNV segmentation. The proposed dual difficulty awareness includes segmentation difficulty perception of pixels in labeled and unlabeled data. For labeled data, we propose a classification confidence-guided difficulty perception method. For unlabeled data, we propose a model stability-guided difficulty perception method. Finally, we propose a difficulty-aware self-training method to dynamically adjust the threshold of pseudolabels according to the difficulty, thereby improving the utilization of difficult-to-segment pixels in unlabeled data. Experimental results show that our method outperforms the state-of-the-art method in CNV segmentation.

Learning to estimate and classify brain functional networks (BFNs) has become an increasingly important way of predicting neurological or mental disorders at their early stages. The traditional methods conduct BFN estimation and classification in two separate steps, thus preventing the interaction and joint optimization. In contrast, Transformer provides a natural architecture to learn BFNs with downstream tasks in an end-to-end manner. Despite their great potential, Transformer-based methods involve a large number of parameters that need to be learnt from Big Data and often lead to poor model interpretability. Considering the challenge in acquiring data and the high demand for model interpretability in medical scenarios, in this paper, we propose a minimalist Transformer architecture, referred to as Miniformer, by simplifying the projection matrices in the self-attention module into a single diagonal matrix, which greatly reduces the number of parameters, alleviates the risk of overfitting, and improves the interpretability. Additionally, the clear physical meaning of parameters in Miniformer makes the integration of domain knowledge or prior easier and more natural. Therefore, we further develop two variants of Miniformer by incorporating sparsity for removing potentially noisy time points from fMRI signals, and smoothness for capturing the temporal correlations in fMRI signals, respectively. To evaluate the effectiveness of the proposed methods, we perform brain disease diagnosis experiments on three public datasets. The results show that Miniformer and its variants tend to achieve higher classification performance than comparison methods with good interpretability.

Brain functional network (BFN) analysis has become a popular method for identifying neurological diseases at their early stages and revealing sensitive biomarkers related to these diseases. Due to the fact that BFN is a graph with complex structure, graph convolutional networks (GCNs) can be naturally used in the identification of BFN, and can generally achieve an encouraging performance if given large amounts of training data. In practice, however, it is very difficult to obtain sufficient brain functional data, especially from subjects with brain disorders. As a result, GCNs usually fail to learn a reliable feature representation from limited BFNs, leading to overfitting issues. In this paper, we propose an improved GCN method to classify brain diseases by introducing a self-supervised learning (SSL) module for assisting the graph feature representation. We conduct experiments to classify subjects with mild cognitive impairment (MCI) and autism spectrum disorder (ASD) respectively from normal controls (NCs). Experimental results on two benchmark databases demonstrate that our proposed scheme tends to obtain higher classification accuracy than the baseline methods.

Mild cognitive impairment (MCI) is an intermediate stage of brain cognitive decline, associated with increasing risk of developing Alzheimer's disease (AD). It is believed that early treatment of MCI could slow down the progression of AD, and functional brain network (FBN) could provide potential imaging biomarkers for MCI diagnosis and response to treatment. However, there are still some challenges to estimate a “good” FBN, particularly due to the poor quality and limited quantity of functional magnetic resonance imaging (fMRI) data from the target domain (i.e., MCI study). Inspired by the idea of transfer learning, we attempt to transfer information in high-quality data from source domain (e.g., human connectome project in this paper) into the target domain towards a better FBN estimation, and propose a novel method, namely NERTL (Network Estimation via Regularized Transfer Learning). Specifically, we first construct a high-quality network “template” based on the source data, and then use the template to guide or constrain the target of FBN estimation by a weighted l1-norm regularizer. Finally, we conduct experiments to identify subjects with MCI from normal controls (NCs) based on the estimated FBNs. Despite its simplicity, our proposed method is more effective than the baseline methods in modeling discriminative FBNs, as demonstrated by the superior MCI classification accuracy of 82.4% and the area under curve (AUC) of 0.910.

Functional brain network (FBN) is becoming an increasingly important measurement for exploring cerebral mechanisms and mining informative biomarkers that assist diagnosis of some neurodegenerative disorders. Despite its effectiveness to discover valuable hidden patterns in the human brain, the estimated FBNs are often heavily influenced by the quality of the observed data (e.g., blood oxygen level dependent signal series). In practice, a preprocessing pipeline is usually employed for improving data quality. With this in mind, some data points (volumes or time course in the time series) are still not clean enough, due to artifacts including spurious resting-state processes (head movement, mind-wandering). Therefore, not all volumes in the fMRI time series can contribute to the subsequent FBN estimation. To address this issue, we propose a novel FBN estimation method by introducing a latent variable as an indicator of the data quality, and develop an alternating optimization algorithm for jointly scrubbing the data and estimating FBN simultaneously. To further illustrate the effectiveness of the proposed method, we conduct experiments on two public datasets to identify subjects with mild cognitive impairment from normal controls based on the estimated FBNs, and achieve improved accuracies than the baseline methods.