Learnable Brain Connectivity Structures for Identifying Neurological Disorders.

Brain networks/graphs have been widely recognized as powerful and efficient tools for identifying neurological disorders. In recent years, various graph neural network models have been developed to automatically extract features from brain networks. However, a key limitation of these models is that the inputs, namely brain networks/graphs, are constructed using predefined statistical metrics (e.g., Pearson correlation) and are not learnable. The lack of learnability restricts the flexibility of these approaches. While statistically-specific brain networks can be highly effective in recognizing certain diseases, their performance may not exhibit robustness when applied to other types of brain disorders. To address this issue, we propose a novel module called Brain Structure Inference (termed BSI), which can be seamlessly integrated with multiple downstream tasks within a unified framework, enabling end-to-end training. It is highly flexible to learn the most beneficial underlying graph structures directly for specific downstream tasks. The proposed method achieves classification accuracies of 74.83% and 79.18% on two publicly available datasets, respectively. This suggests an improvement of at least 3% over the best-performing existing methods for both tasks. In addition to its excellent performance, the proposed method is highly interpretable, and the results are generally consistent with previous findings.

Exploring autism via the retina: Comparative insights in children with autism spectrum disorder and typical development.

Autism spectrum disorder (ASD) is a widely recognized neurodevelopmental disorder, yet the identification of reliable imaging biomarkers for its early diagnosis remains a challenge. Considering the specific manifestations of ASD in the eyes and the interconnectivity between the brain and the eyes, this study investigates ASD through the lens of retinal analysis. We specifically examined differences in the macular region of the retina using optical coherence tomography (OCT)/optical coherence tomography angiography (OCTA) images between children diagnosed with ASD and those with typical development (TD). Our findings present potential novel characteristics of ASD: the thickness of the ellipsoid zone (EZ) with cone photoreceptors was significantly increased in ASD; the large-caliber arteriovenous of the inner retina was significantly reduced in ASD; these changes in the EZ and arteriovenous were more significant in the left eye than in the right eye. These observations of photoreceptor alterations, vascular function changes, and lateralization phenomena in ASD warrant further investigation, and we hope that this work can advance interdisciplinary understanding of ASD.

Inferring brain causal and temporal-lag networks for recognizing abnormal patterns of dementia.

Brain functional network analysis has become a popular method to explore the laws of brain organization and identify biomarkers of neurological diseases. However, it is still a challenging task to construct an ideal brain network due to the limited understanding of the human brain. Existing methods often ignore the impact of temporal-lag on the results of brain network modeling, which may lead to some unreliable conclusions. To overcome this issue, we propose a novel brain functional network estimation method, which can simultaneously infer the causal mechanisms and temporal-lag values among brain regions. Specifically, our method converts the lag learning into an instantaneous effect estimation problem, and further embeds the search objectives into a deep neural network model as parameters to be learned. To verify the effectiveness of the proposed estimation method, we perform experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database by comparing the proposed model with several existing methods, including correlation-based and causality-based methods. The experimental results show that our brain networks constructed by the proposed estimation method can not only achieve promising classification performance, but also exhibit some characteristics of physiological mechanisms. Our approach provides a new perspective for understanding the pathogenesis of brain diseases. The source code is released at https://github.com/NJUSTxiazw/CTLN.

Deep Causality Variational Autoencoder Network for Identifying the Potential Biomarkers of Brain Disorders.

Identifying causality from observational time-series data is a key problem in dealing with complex dynamic systems. Inferring the direction of connection between brain regions (i.e., causality) has become the central topic in the domain of fMRI. The purpose of this study is to obtain causal graphs that characterize the causal relationship between brain regions based on time series data. To address this issue, we designed a novel model named deep causal variational autoencoder (CVAE) to estimate the causal relationship between brain regions. This network contains a causal layer that can estimate the causal relationship between different brain regions directly. Compared with previous approaches, our method relaxes many constraints on the structure of underlying causal graph. Our proposed method achieves excellent performance on both the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Autism Brain Imaging Data Exchange 1 (ABIDE1) databases. Moreover, the experimental results show that deep CVAE has promising applications in the field of brain disease identification.

A Structure-Guided Effective and Temporal-Lag Connectivity Network for Revealing Brain Disorder Mechanisms.

Brain network provides important insights for the diagnosis of many brain disorders, and how to effectively model the brain structure has become one of the core issues in the domain of brain imaging analysis. Recently, various computational methods have been proposed to estimate the causal relationship (i.e., effective connectivity) between brain regions. Compared with traditional correlation-based methods, effective connectivity can provide the direction of information flow, which may provide additional information for the diagnosis of brain diseases. However, existing methods either ignore the fact that there is a temporal-lag in the information transmission across brain regions, or simply set the temporal-lag value between all brain regions to a fixed value. To overcome these issues, we design an effective temporal-lag neural network (termed ETLN) to simultaneously infer the causal relationships and the temporal-lag values between brain regions, which can be trained in an end-to-end manner. In addition, we also introduce three mechanisms to better guide the modeling of brain networks. The evaluation results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrate the effectiveness of the proposed method.

Recognition of Dementia Biomarkers With Deep Finer-DBN.

The treatment of neurodegenerative diseases is expensive, and long-term treatment makes families bear a heavy burden. Accumulating evidence suggests that the high conversion rate can possibly be reduced if clinical interventions are applied at the early stage of brain diseases. Thus, a variety of deep learning methods are utilized to recognize the early stages of neurodegenerative diseases for clinical intervention and treatment. However, most existing methods have ignored the issue of sample imbalance, which often makes it difficult to train an effective model due to lack of a large number of negative samples. To address this problem, we propose a two-stage method, which is used to learn the compression and recover rules of normal subjects so that potential negative samples can be detected. The experimental results show that the proposed method can not only obtain a superb recognition result, but also give an explanation that conforms to the physiological mechanism. Most importantly, the deep learning model does not need to be retrained for each type of disease, which can be widely applied to the diagnosis of various brain diseases. Furthermore, this research could have great potential in understanding regional dysfunction of various brain diseases.