Aradhya Abhay M S, Sundaram Suresh, Pratama Mahardhika
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:2829-2832. doi: 10.1109/EMBC44109.2020.9176547.
Accurate detection of neuro-psychological disorders such as Attention Deficit Hyperactivity Disorder (ADHD) using resting state functional Magnetic Resonance Imaging (rs-fMRI) is challenging due to high dimensionality of input features, low inter-class separability, small sample size and high intra-class variability. For automatic diagnosis of ADHD and autism, spatial transformation methods have gained significance and have achieved improved classification performance. However, they are not reliable due to lack of generalization in dataset like ADHD with high variance and small sample size. Therefore, in this paper, we present a Metaheuristic Spatial Transformation (MST) approach to convert the spatial filter design problem into a constraint optimization problem, and obtain the solution using a hybrid genetic algorithm. Highly separable features obtained from the MST along with meta-cognitive radial basis function based classifier are utilized to accurately classify ADHD. The performance was evaluated using the ADHD200 consortium dataset using a ten fold cross validation. The results indicate that the MST based classifier produces state of the art classification accuracy of 72.10% (1.71% improvement over previous transformation based methods). Moreover, using MST based classifier the training and testing specificity increased significantly over previous methods in literature. These results clearly indicate that MST enables the determination of the highly discriminant transformation in dataset with high variability, small sample size and large number of features. Further, the performance on the ADHD200 dataset shows that MST based classifier can be reliably used for the accurate diagnosis of ADHD using rs-fMRI.Clinical relevance- Metaheuristic Spatial Transformation (MST) enables reliable and accurate detection of neuropsychological disorders like ADHD from rs-fMRI data characterized by high variability, small sample size and large number of features.
利用静息态功能磁共振成像（rs-fMRI）准确检测诸如注意力缺陷多动障碍（ADHD）等神经心理障碍具有挑战性，这是由于输入特征的高维度、类间可分离性低、样本量小以及类内变异性高。对于ADHD和自闭症的自动诊断，空间变换方法已变得很重要，并取得了改进的分类性能。然而，由于在像ADHD这样具有高方差和小样本量的数据集缺乏泛化能力，它们并不可靠。因此，在本文中，我们提出一种元启发式空间变换（MST）方法，将空间滤波器设计问题转化为一个约束优化问题，并使用混合遗传算法获得解决方案。从MST获得的高度可分离特征以及基于元认知径向基函数的分类器被用于准确分类ADHD。使用ADHD200联盟数据集通过十折交叉验证对性能进行评估。结果表明，基于MST的分类器产生了72.10%的当前最优分类准确率（比先前基于变换的方法提高了1.71%）。此外，与文献中的先前方法相比，使用基于MST的分类器训练和测试特异性显著提高。这些结果清楚地表明，MST能够在具有高变异性、小样本量和大量特征的数据集中确定高度判别性的变换。此外，在ADHD200数据集上的性能表明，基于MST的分类器可以可靠地用于使用rs-fMRI准确诊断ADHD。临床相关性——元启发式空间变换（MST）能够从具有高变异性、小样本量和大量特征的rs-fMRI数据中可靠且准确地检测出像ADHD这样的神经心理障碍。
