Guo Xiang, Wang Jiehuan, Wang Xiaoqiang, Liu Wenjing, Yu Hao, Xu Li, Li Hengyan, Wu Jiangfen, Dong Mengxing, Tan Weixiong, Chen Weijian, Yang Yunjun, Chen Yueqin
Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China.
Children Rehabilitation Center, the Affiliated Hospital of Jining Medical University, Jining, China.
Eur Radiol. 2022 Feb;32(2):761-770. doi: 10.1007/s00330-021-08239-4. Epub 2021 Sep 4.
To develop and validate deep learning (DL) methods for diagnosing autism spectrum disorder (ASD) based on conventional MRI (cMRI) and apparent diffusion coefficient (ADC) images.
A total of 151 ASD children and 151 age-matched typically developing (TD) controls were included in this study. The data from these subjects were assigned to training and validation datasets. An additional 20 ASD children and 25 TD controls were acquired, whose data were utilized in an independent test set. All subjects underwent cMRI and diffusion-weighted imaging examination of the brain. We developed a series of DL models to separate ASD from TD based on the cMRI and ADC data. The seven models used include five single-sequence models (SSMs), one dominant-sequence model (DSM), and one all-sequence model (ASM). To enhance the feature detection of the models, we embed an attention mechanism module.
The highest AUC (0.824 ~ 0.850) was achieved when applying the SSM based on either FLAIR or ADC to the validation and independent test sets. A DSM using the combination of FLAIR and ADC showed an improved AUC in the validation (0.873) and independent test sets (0.876). The ASM also showed better diagnostic value in the validation (AUC = 0.838) and independent test sets (AUC = 0.836) compared to the SSMs. Among the models with attention mechanism, the DSM achieved the highest diagnostic performance with an AUC, accuracy, sensitivity, and specificity of 0.898, 84.4%, 85.0%, and 84.0% respectively.
This study established the potential of DL models to distinguish ASD cases from TD controls based on cMRI and ADC images.
• Deep learning models based on conventional MRI and ADC can be used to diagnose ASD. • The model (DSM) based on the FLAIR and ADC sequence achieved the best diagnostic performance with an AUC of 0.836 in the independent test sets. • The attention mechanism further improved the diagnostic performance of the models.
开发并验证基于传统磁共振成像（cMRI）和表观扩散系数（ADC）图像诊断自闭症谱系障碍（ASD）的深度学习（DL）方法。
本研究纳入了151名ASD儿童和151名年龄匹配的发育正常（TD）对照。这些受试者的数据被分配到训练和验证数据集。另外采集了20名ASD儿童和25名TD对照，其数据用于独立测试集。所有受试者均接受了脑部的cMRI和扩散加权成像检查。我们基于cMRI和ADC数据开发了一系列DL模型以区分ASD和TD。使用的七个模型包括五个单序列模型（SSM）、一个主导序列模型（DSM）和一个全序列模型（ASM）。为增强模型的特征检测能力，我们嵌入了一个注意力机制模块。
将基于FLAIR或ADC的SSM应用于验证集和独立测试集时，获得了最高的AUC（0.824 ~ 0.850）。使用FLAIR和ADC组合的DSM在验证集（0.873）和独立测试集（0.876）中显示出AUC有所提高。与SSM相比，ASM在验证集（AUC = 0.838）和独立测试集（AUC = 0.836）中也显示出更好的诊断价值。在具有注意力机制的模型中，DSM实现了最高的诊断性能，AUC、准确率、灵敏度和特异性分别为0.898、84.4%、85.0%和84.0%。
本研究确立了基于cMRI和ADC图像的DL模型区分ASD病例和TD对照的潜力。
• 基于传统MRI和ADC的深度学习模型可用于诊断ASD。• 基于FLAIR和ADC序列的模型（DSM）在独立测试集中实现了最佳诊断性能，AUC为0.836。• 注意力机制进一步提高了模型诊断性能。
