The identification of addiction-related circuits is critical for explaining
addiction processes and developing addiction treatments. And models of
functional addiction circuits developed from functional imaging are an
effective tool for discovering and verifying addiction circuits. However,
analyzing functional imaging data of addiction and detecting functional
addiction circuits still have challenges. We have developed a data-driven and
end-to-end generative artificial intelligence(AI) framework to address these
difficulties. The framework integrates dynamic brain network modeling and novel
network architecture networks architecture, including temporal graph
Transformer and contrastive learning modules. A complete workflow is formed by
our generative AI framework: the functional imaging data, from neurobiological
experiments, and computational modeling, to end-to-end neural networks, is
transformed into dynamic nicotine addiction-related circuits. It enables the
detection of addiction-related brain circuits with dynamic properties and
reveals the underlying mechanisms of addiction.

本研究采用生成人工智能框架，包括时间图转换器和对比学习模块等，对功能成像数据进行数据驱动和端到端建模，从而揭示尼古丁成瘾相关电路的动态特性及其机制。

基于生成人工智能的尼古丁相关电路动态检测

Generative artificial intelligence-enabled dynamic detection of nicotine-related circuits

Population imaging markedly increased the size of functional-imaging
datasets, shedding new light on the neural basis of inter-individual
differences. Analyzing these large data entails new scalability challenges,
computational and statistical. For this reason, brain images are typically
summarized in a few signals, for instance reducing voxel-level measures with
brain atlases or functional modes. A good choice of the corresponding brain
networks is important, as most data analyses start from these reduced signals.
We contribute finely-resolved atlases of functional modes, comprising from 64
to 1024 networks. These dictionaries of functional modes (DiFuMo) are trained
on millions of fMRI functional brain volumes of total size 2.4TB, spanned over
27 studies and many research groups. We demonstrate the benefits of extracting
reduced signals on our fine-grain atlases for many classic functional data
analysis pipelines: stimuli decoding from 12,334 brain responses, standard GLM
analysis of fMRI across sessions and individuals, extraction of resting-state
functional-connectomes biomarkers for 2,500 individuals, data compression and
meta-analysis over more than 15,000 statistical maps. In each of these analysis
scenarii, we compare the performance of our functional atlases with that of
other popular references, and to a simple voxel-level analysis. Results
highlight the importance of using high-dimensional "soft" functional atlases,
to represent and analyse brain activity while capturing its functional
gradients. Analyses on high-dimensional modes achieve similar statistical
performance as at the voxel level, but with much reduced computational cost and
higher interpretability. In addition to making them available, we provide
meaningful names for these modes, based on their anatomical location. It will
facilitate reporting of results.

我们提出了精细分辨率的功能模式图册 (DiFuMo)，由 64 到 1024 个网络组成，很好地提取了降维信号，以及对大量数据处理技术进行了比较和解释。