Samanta Ananya, Sarma Monalisa, Samanta Debasis
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-4. doi: 10.1109/EMBC40787.2023.10340610.
In response to a stimulus, distinct areas of the human brain are activated. Also, it is known that the regions interact with one another. This functional connectivity is helpful to diagnose any neurological abnormality, such as autism spectrum disorder (ASD). This work proposes an approach to construct a functional connectivity network from fMRI image data. For obtaining a functional connectivity network, the time series component of fMRI data is used and from it correlation matrix is calculated showing the degree of interaction among the brain regions. To map the different regions of a brain, the brain atlas is considered. This essentially yields a low-rank tensor approximation of the functional connectivity matrix. A 2D convolutional deep neural network model is built to categorize topological similarity in the functional connectivity matrices related to ASD and typically developing control. The proposed approach has been tested with ABIDE dataset of fMRI data for autism spectrum disorder. Several brain atlases have been considered in the experiment. With a majority voting concept on the results from the atlases, the proposed technique reveals an ASD detection accuracy of 84.79%, which is significantly comparable to the state of the art techniques.Clinical Relevance- ASD is one of the least understood neurological disorders that has been recently recognized to have major sociological consequences on an affected individual's life. A symptom-based diagnosis is in practice. However, this requires prolonged behavioural examinations under the supervision of a highly skilled multidisciplinary team. An early and cost-effective detection using an fMRI image is considered an appropriate, comprehensive, and advanced treatment plan.
响应刺激时，人类大脑的不同区域会被激活。此外，已知这些区域会相互作用。这种功能连接有助于诊断任何神经学异常，例如自闭症谱系障碍（ASD）。这项工作提出了一种从功能磁共振成像（fMRI）图像数据构建功能连接网络的方法。为了获得功能连接网络，使用了fMRI数据的时间序列成分，并从中计算出相关矩阵，以显示大脑区域之间的相互作用程度。为了映射大脑的不同区域，考虑了脑图谱。这本质上产生了功能连接矩阵的低秩张量近似。构建了一个二维卷积深度神经网络模型，以对与ASD和典型发育对照相关的功能连接矩阵中的拓扑相似性进行分类。所提出的方法已使用ASD的fMRI数据的ABIDE数据集进行了测试。实验中考虑了几种脑图谱。通过对来自脑图谱的结果采用多数投票概念，所提出的技术显示出84.79%的ASD检测准确率，这与现有技术相比具有显著可比性。临床相关性——ASD是最不为人所理解的神经疾病之一，最近人们认识到它会对受影响个体的生活产生重大社会学后果。目前在实践中采用基于症状的诊断方法。然而，这需要在高技能多学科团队的监督下进行长时间的行为检查。使用fMRI图像进行早期且经济高效的检测被认为是一种合适、全面且先进的治疗方案。
