Purpose: Age biases have been identified as an essential factor in the diagnosis of ASD. The objective of this study was to compare the effect of different age groups in classifying ASD using morphological features (MF) and morphological connectivity features (MCF). Methods: The structural magnetic resonance imaging (sMRI) data for the study was obtained from the two publicly available databases, ABIDE-I and ABIDE-II. We considered three age groups, 6 to 11, 11 to 18, and 6 to 18, for our analysis. The sMRI data was pre-processed using a standard pipeline and was then parcellated into 148 different regions according to the Destrieux atlas. The area, thickness, volume, and mean curvature information was then extracted for each region which was used to create a total of 592 MF and 10,878 MCF for each subject. Significant features were identified using a statistical t-test (p<0.05) which was then used to train a random forest (RF) classifier. Results: The results of our study suggested that the performance of the 6 to 11 age group was the highest, followed by the 6 to 18 and 11 to 18 ages in both MF and MCF. Overall, the MCF with RF in the 6 to 11 age group performed better in the classification than the other groups and produced an accuracy, F1 score, recall, and precision of 75.8%, 83.1%, 86%, and 80.4%, respectively. Conclusion: Our study thus demonstrates that morphological connectivity and age-related diagnostic model could be an effective approach to discriminating ASD.

通过比较使用形态学特征和形态学连接特征在不同年龄组中对ASD进行分类的效果，研究发现6至11岁年龄组的性能最高，其次是6至18岁和11至18岁组，其中RF算法在6至11岁年龄组的MCF分类中表现最好，准确率、F1评分、召回率和精确率分别为75.8%、83.1%、86%和80.4%，这表明形态连接性和年龄相关诊断模型可以有效区分ASD。

自闭症中基于年龄分层的形态连接模式差异：基于sMRI和机器学习方法的研究