The characterisation of the brain as a "connectome", in which the connections
are represented by correlational values across timeseries and as summary
measures derived from graph theory analyses, has been very popular in the last
years. However, although this representation has advanced our understanding of
the brain function, it may represent an oversimplified model. This is because
the typical fMRI datasets are constituted by complex and highly heterogeneous
timeseries that vary across space (i.e., location of brain regions). We compare
various modelling techniques from deep learning and geometric deep learning to
pave the way for future research in effectively leveraging the rich spatial and
temporal domains of typical fMRI datasets, as well as of other similar
datasets. As a proof-of-concept, we compare our approaches in the homogeneous
and publicly available Human Connectome Project (HCP) dataset on a supervised
binary classification task. We hope that our methodological advances relative
to previous "connectomic" measures can ultimately be clinically and
computationally relevant by leading to a more nuanced understanding of the
brain dynamics in health and disease. Such understanding of the brain can
fundamentally reduce the constant specialised clinical expertise in order to
accurately understand brain variability.

通过比较深度学习和几何深度学习的各种建模技术来为未来的研究铺平道路，以有效利用典型的 fMRI 数据集以及其他类似数据集的丰富的时空域，从而为人们对健康和疾病中大脑动态的更加细致的理解、以及减少对专业临床专家的需求提供方法。

构建基于时空预测的脑数据表示模型

Towards a predictive spatio-temporal representation of brain data

What can we learn from a connectome? We constructed a simplified model of the
first two stages of the fly visual system, the lamina and medulla. The
resulting hexagonal lattice convolutional network was trained using
backpropagation through time to perform object tracking in natural scene
videos. Networks initialized with weights from connectome reconstructions
automatically discovered well-known orientation and direction selectivity
properties in T4 neurons and their inputs, while networks initialized at random
did not. Our work is the first demonstration, that knowledge of the connectome
can enable in silico predictions of the functional properties of individual
neurons in a circuit, leading to an understanding of circuit function from
structure alone.

本文利用回溯传播算法 (BPTT) 通过连接组重建构建蝇视觉系统模型（即光神经元和传导神经元），发现连接组信息可用于推测电路中单个神经元的功能特征，进而理解电路的功能和构成。

基于神经元连接的六边形晶格卷积网络模型 —— 以果蝇视觉系统为例

A Connectome Based Hexagonal Lattice Convolutional Network Model of the  Drosophila Visual System

We exploit flow propagation on the directed neuronal network of the nematode
Caenorhabditis elegans to reveal dynamically relevant features of its
connectome. We find flow-based groupings of neurons at different levels of
granularity, which we relate to functional and anatomical constituents of its
nervous system. A systematic in silico evaluation of the full set of single and
double neuron ablations is used to identify deletions that induce the most
severe disruptions of the multi-resolution flow structure. Such ablations are
linked to functionally relevant neurons, and suggest potential candidates for
further in vivo investigation. In addition, we use the directional patterns of
incoming and outgoing network flows at all scales to identify flow profiles for
the neurons in the connectome, without pre-imposing a priori categories. The
four flow roles identified are linked to signal propagation motivated by
biological input-response scenarios.

本文探讨了费城线虫的神经元有向网络的流传播，从而揭示了其连接组的动态相关特征。作者发现在不同的粒度级别上有基于流的神经元分组，并将其与其神经系统的功能和解剖组织相关联，并确定那些最严重破坏多重分辨率流结构的单个和双个神经元切除。此外，还使用所有尺度上的传入和传出网络流的定向模式，以识别连接组中神经元的流特征。所识别的四种流角色与应答于生物输入的传播信号相关。