基于ConvNeXt和注意力的多动症分类

doi:10.3969/j.issn.1006-2475.2025.07.003

摘要/Abstract

摘要： 摘要：注意缺陷与多动障碍（Attention Deficit and Hyperactivity Disorder， ADHD）俗称多动症，是一种常见的儿童行为异常性疾病。由于目前多动症尚无明确病因，且多动症患者与正常儿童的脑部结构仅存在细微差异，导致临床医生难以进行有效诊断。针对此类疾病，本文提出一种基于ConvNeXt和注意力机制的卷积神经网络，用于区分多动症患者和正常儿童。首先对结构磁共振图像进行预处理，其次加载预训练模型，通过包含多维协作注意力的ConvNeXt网络进行深层特征提取，重构ConvNeXt输出层并得到最终分类结果。在ADHD-200数据集上进行验证，实验结果表明，其分类准确性达到97.3%，优于目前的主流方法，并且模型的热力图提示了前额叶等与疾病相关的脑部区域，因此可以作为一种有效、便捷的多动症辅助诊断方法。

关键词: 关键词：多动症, ConvNeXt, 图像分类, 磁共振成像

Abstract:
Abstract: Attention Deficit and Hyperactivity Disorder （ADHD）， commonly known as ADHD， is a common behavioral disorder in children. Since there is no clear etiology for ADHD， and there are only subtle differences in the brain structure between ADHD patients and normal children， which makes it difficult for clinicians to make effective diagnosis. For such disorders， a convolutional neural network based on ConvNeXt and attentional mechanisms is proposed for distinguishing ADHD patients from normal children. Firstly， the sMRI is preprocessed， secondly， the pre-trained model is loaded， the deep feature extraction is performed by the ConvNeXt network containing multidimensional collaborative attention， the ConvNeXt output layer is reconstructed and the final classification results are obtained. Validated on the ADHD-200 dataset， the experimental results show that its classification accuracy reaches 97.3%， which is better than the current mainstream methods， and the heat map of the model suggests the prefrontal lobe and other brain regions related to the disease， so it can be used as an effective and convenient auxiliary diagnosis method for ADHD.

Key words: Key words: ADHD, ConvNeXt, image classification, magnetic resonance imaging

中图分类号:

TP389.1

汪涛1, 吴茜1, 2. 基于ConvNeXt和注意力的多动症分类[J]. 计算机与现代化, 2025, 0(07): 15-20.

WANG Tao1, WU Qian1, 2. ADHD Classification Based on ConvNeXt and Attention [J]. Computer and Modernization, 2025, 0(07): 15-20.

参考文献

［1］诸葛远莉. 正确认识儿童多动症［J］. 家庭医学（下半月）， 2023（12）: 22-24.
［2］张建昭. 儿童多动症:家庭和幼儿园如何早期发现［J］. 儿童与健康， 2023（11）: 4-5.
［3］ HAN D， FANG Y T， LUO H. A predictive model offor attention deficit hyperactivity disorder based on clinical assessment tools ［J］. Neuropsychiatr Dis Treat， 2020， 16: 1331-1337.
［4］ SRIDHAR C， BHAT S， ACHARYA U R， et al. Diagnosis of attention deficit hyperactivity disorder using imaging and signal processing techniques ［J］. Computers in Biology and Medicine， 2017，88:93-99.
［5］ WANG X K， WANG X Q， YANG X， et al. Gray matter network associated with attention in children with attention deficit hyperactivity disorder ［J］. Front Psychiatry， 2022，13:6-14.
［6］ ZOU L， ZHENG J N， MIAO C Y， et al. 3D CNN based automatic diagnosis of attention deficit hyperactivity disorder using functional and structural MRI ［J］. IEEE Access， 2017，5:23626-23636.
［7］ ZHANG J J， ZHOU L P， WANG L. Subject-adaptive integration of multiple SICE brain networks with different sparsity［J］. Pattern Recognition， 2017，63:642-652.
［8］ DOU C F， ZHANG S K， WANG H P， et al. ADHD fMRI short-time analysis method for edge computing based on multi-instance learning ［J］. Journal of Systems Architecture， 2020，111:92-100.
［9］ ZHANG J J， ZHOU L P， WANG L， et al. Diffusion kernel attention network for brain disorder classification［J］. IEEE Transactions on Medical Imaging， 2022，41（10）:2814-2827.
［10］ JANG J， HWANG D. M3T: Three-dimensional medical image classifier using Multi-plane and Multi-slice Transformer［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2022:20686-20697.
［11］ SHI C P， WU H Y， WANG L G. A feature complementary attention network based on adaptive knowledge filtering for hyperspectral image classification ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2023，61:1-19.
［12］ LIU Z， LIN Y T， CAO Y， et al. Swin Transformer: Hierarchical vision transformer using shifted windows ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision （ICCV）. IEEE， 2021: 9992-10002.
［13］ HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2016:770-778.
［14］ YU Y， ZHANG Y， CHENG Z Y， et al. MCA: Multidimensional collaborative attention in deep convolutional neural networks for image recognition ［J］. Engineering Applications of Artificial Intelligence， 2023，126:19-35.
［15］ DENG J， DONG W， SOCHER R， et al. ImageNet: A large-scale hierarchical image database［C］// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2009:248-255.
［16］马偲臆，刘晓薇，谢雪琴，等. 迁移学习在生物医学领域的应用［J］. 生物医学工程学进展， 2023，44（4）:347-356.
［17］ LIU Z， MAO H Z， WU C Y， et al. A ConvNet for the 2020s［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2022:11966-11976.
［18］ SRIVASTAVA V， BISWAS B. Manifold preserving CNN for pixel-based object labelling in images for high dimensional feature spaces ［J］. Neural Processing Letters， 2021，53（1）:607-635.
［19］ PATRO K K， ALLAM J P， SANAPALA U， et al. An effective correlation-based data modeling framework for automatic diabetes prediction using machine and deep learning techniques ［J］. BMC Bioinformatics， 2023，24（1）:26-46.
［20］ DEVIKA K， MAHAPATRA D， SUBRAMANIAN R， et al. Outlier-based autism detection using longitudinal structural MRI ［J］. IEEE Access， 2022，10: 27794-27808.
［21］ GUO P， DU G Q， WEI L S， et al. Multiscale face recognition in cluttered backgrounds based on visual attention ［J］. Neurocomputing， 2022，469:65-80.
［22］ HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018:7132-7141.
［23］ LIU M Q， PAN H Z， GE H M， et al. MS3Net: Multiscale stratified-split symmetric network with quadra-view attention for hyperspectral image classification ［J］. Signal Processing， 2023，212:69-79.
［24］ ZHOU P， XIE X Y， LIN Z C， et al. Towards understanding convergence and generalization of AdamW［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024，46（9）: 6486-6493.
［25］ BELLEC P， CHU C， CHOUINARD-DECORTE F， et al. The Neuro Bureau ADHD-200 preprocessed repository ［J］. NeuroImage， 2017，144:275-286.
［26］ ZHOU B L， KHOSLA A， LAPEDRIZA A， et al. Learning deep features for discriminative localization ［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2016:2921-2929.
［27］ HOOGMAN M， BRALTEN J， HIBAR D P， et al. Subcortical brain volume differences in participants with attention deficit hyperactivity disorder in children and adults: Across-sectional mega-analysis ［J］. The Lancet Psychiatry， 2017，4（4）:310-319.

[1]	侯梦晗, 韦昌法. 基于多特征融合的抑郁症识别模型构建[J]. 计算机与现代化, 2025, 0(03): 1-5.
[2]	黄庭培1, 马禄彪1, 李世宝2, 刘建航1. 基于WiFi和原型网络的手势识别方法[J]. 计算机与现代化, 2024, 0(12): 34-39.
[3]	赵小明, 潘婷, 刘伟锋. 基于图像分类的自动绘画心理分析方法[J]. 计算机与现代化, 2024, 0(08): 92-97.
[4]	许跃雯1, 李明1, 李莉2. 基于对比学习MocoV2的COVID-19图像分类#br#[J]. 计算机与现代化, 2024, 0(02): 81-87.
[5]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[6]	吴甜, 刘海华, 童顺延. 基于深度反馈的卷积神经网络的图像分类[J]. 计算机与现代化, 2023, 0(09): 82-86.
[7]	马国祥, 杨凌菲, 严传波, 张志豪, 孙彬, 王晓荣. 基于深度DenseNet网络的肝包虫病超声影像诊断方法[J]. 计算机与现代化, 2023, 0(09): 100-104.
[8]	秦竹媛, 吴浩忠, 谭代庆, 韩爱庆, 臧昊, 王选, 唐燕. 基于多尺度ResNet融合注意力机制的麦冬细粒度识别[J]. 计算机与现代化, 2023, 0(07): 105-111.
[9]	朱剑波, 葛明锋, 董文飞. 基于改进EfficientNet的阿尔兹海默症图像分类[J]. 计算机与现代化, 2023, 0(06): 56-61.
[10]	吴志平, 麻尧斌, 汤文超, 胡必伟, 胡毕炜, 刘明嘉. 基于上下文感知和超像素后处理的多光谱图像分类[J]. 计算机与现代化, 2022, 0(12): 67-73.
[11]	黄延辉, 兰海, 魏宪. 基于可分离结构变换的轻量级Vision Transformer[J]. 计算机与现代化, 2022, 0(10): 75-81.
[12]	杨贞, 单孟姣, 殷志坚, 杨凡, 李翠梅. 细粒度图像分类的通道自适应判别性学习方法[J]. 计算机与现代化, 2022, 0(10): 68-74.
[13]	王盼红, 朱昌明. 融合CNN与交互特征的多标签图像分类方法[J]. 计算机与现代化, 2022, 0(09): 85-92.
[14]	张林鹏, 汪西原, 李强. 基于双池化特征加权结构CNN的图像分类[J]. 计算机与现代化, 2021, 0(11): 67-71.
[15]	李晓双, 韩立新, 李景仙, 周经纬. 基于优化残差网络的多模态音乐情感分类[J]. 计算机与现代化, 2020, 0(12): 83-89.