Hosseini Elahe, Hosseini Seyyed Ali, Servaes Stijn, Hall Brandon, Rosa-Neto Pedro, Moradi Ali-Reza, Kumar Ajay, Pedram Mir Mohsen, Chawla Sanjeev
Department of Electrical and Computer Engineering, Kharazmi University, Tehran 15719-14911, Iran.
Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC H4H 1R3, Canada.
Tomography. 2025 May 13;11(5):56. doi: 10.3390/tomography11050056.
According to the World Health Organization (WHO), approximately 5% of children and 2.5% of adults suffer from attention deficit hyperactivity disorder (ADHD). This disorder can have significant negative consequences on people's lives, particularly children. In recent years, methods based on artificial intelligence and neuroimaging techniques, such as MRI, have made significant progress, paving the way for development of more reliable diagnostic tools. In this proof of concept study, our aim was to investigate the potential utility of neuroimaging data and clinical information in combination with a deep learning-based analytical approach, more precisely, a novel feature extraction technique for the diagnosis of ADHD with high accuracy. Leveraging the ADHD200 dataset, which encompasses demographic information and anatomical MRI scans collected from a diverse ADHD population, our study focused on developing modern deep learning-based diagnostic models. The data preprocessing employed a pre-trained Visual Geometry Group16 (VGG16) network to extract two-dimensional (2D) feature maps from three-dimensional (3D) anatomical MRI data to reduce computational complexity and enhance diagnostic power. The inclusion of personal attributes, such as age, gender, intelligence quotient, and handedness, strengthens the diagnostic models. Four deep-learning architectures-convolutional neural network 2D (CNN2D), CNN1D, long short-term memory (LSTM), and gated recurrent units (GRU)-were employed for analysis of the MRI data, with and without the inclusion of clinical characteristics. A 10-fold cross-validation test revealed that the LSTM model, which incorporated both MRI data and personal attributes, had the best diagnostic performance among all tested models in the diagnosis of ADHD with an accuracy of 0.86 and area under the receiver operating characteristic (ROC) curve (AUC) score of 0.90. Our findings demonstrate that the proposed approach of extracting 2D features from 3D MRI images and integrating these features with clinical characteristics may be useful in the diagnosis of ADHD with high accuracy.
根据世界卫生组织（WHO）的数据，约5%的儿童和2.5%的成年人患有注意力缺陷多动障碍（ADHD）。这种疾病会对人们的生活产生重大负面影响，尤其是对儿童。近年来，基于人工智能和神经成像技术（如MRI）的方法取得了显著进展，为开发更可靠的诊断工具铺平了道路。在这项概念验证研究中，我们的目的是研究神经成像数据和临床信息与基于深度学习的分析方法（更确切地说是一种用于高精度诊断ADHD的新型特征提取技术）相结合的潜在效用。利用ADHD200数据集，该数据集包含从不同ADHD人群收集的人口统计学信息和解剖MRI扫描，我们的研究专注于开发基于现代深度学习的诊断模型。数据预处理采用预训练的视觉几何组16（VGG16）网络从三维（3D）解剖MRI数据中提取二维（2D）特征图，以降低计算复杂度并增强诊断能力。纳入年龄、性别、智商和利手等个人属性可增强诊断模型。使用了四种深度学习架构——二维卷积神经网络（CNN2D）、一维卷积神经网络（CNN1D）、长短期记忆网络（LSTM）和门控循环单元（GRU）——来分析MRI数据，分析时纳入和不纳入临床特征。一项10折交叉验证测试表明，结合了MRI数据和个人属性的LSTM模型在所有测试模型中对ADHD的诊断性能最佳，准确率为0.86，受试者操作特征（ROC）曲线下面积（AUC）得分为0.90。我们的研究结果表明，从3D MRI图像中提取2D特征并将这些特征与临床特征相结合的 proposed 方法可能有助于高精度诊断ADHD。
