Long Zhuqing, Li Jie, Liao Haitao, Deng Li, Du Yukeng, Fan Jianghua, Li Xiaofeng, Miao Jichang, Qiu Shuang, Long Chaojie, Jing Bin
Medical Apparatus and Equipment Deployment, Hunan Children's Hospital, Changsha 410007, China.
School of Biomedical Engineering, Capital Medical University, Beijing 100069, China.
Brain Sci. 2022 Jun 8;12(6):751. doi: 10.3390/brainsci12060751.
Multi-modal neuroimaging with appropriate atlas is vital for effectively differentiating mild cognitive impairment (MCI) from healthy controls (HC).
The resting-state functional magnetic resonance imaging (rs-fMRI) and structural MRI (sMRI) of 69 MCI patients and 61 HC subjects were collected. Then, the gray matter volumes obtained from the sMRI and Hurst exponent (HE) values calculated from rs-fMRI data in the Automated Anatomical Labeling (AAL-90), Brainnetome (BN-246), Harvard-Oxford (HOA-112) and AAL3-170 atlases were extracted, respectively. Next, these characteristics were selected with a minimal redundancy maximal relevance algorithm and a sequential feature collection method in single or multi-modalities, and only the optimal features were retained after this procedure. Lastly, the retained characteristics were served as the input features for the support vector machine (SVM)-based method to classify MCI patients, and the performance was estimated with a leave-one-out cross-validation (LOOCV).
Our proposed method obtained the best 92.00% accuracy, 94.92% specificity and 89.39% sensitivity with the sMRI in AAL-90 and the fMRI in HOA-112 atlas, which was much better than using the single-modal or single-atlas features.
The results demonstrated that the multi-modal and multi-atlas integrated method could effectively recognize MCI patients, which could be extended into various neurological and neuropsychiatric diseases.
使用合适的图谱进行多模态神经成像对于有效区分轻度认知障碍（MCI）和健康对照（HC）至关重要。
收集了69例MCI患者和61例HC受试者的静息态功能磁共振成像（rs-fMRI）和结构磁共振成像（sMRI）数据。然后，分别提取了自动解剖标记（AAL-90）、脑网络组图谱（BN-246）、哈佛-牛津图谱（HOA-112）和AAL3-170图谱中从sMRI获得的灰质体积以及从rs-fMRI数据计算得到的赫斯特指数（HE）值。接下来，采用最小冗余最大相关算法和单模态或多模态的顺序特征收集方法选择这些特征，经过该过程后仅保留最优特征。最后，将保留的特征作为基于支持向量机（SVM）方法的输入特征来对MCI患者进行分类，并采用留一法交叉验证（LOOCV）评估性能。
我们提出的方法在AAL-90图谱的sMRI和HOA-112图谱的fMRI上取得了最佳结果，准确率为92.00%，特异性为94.92%，敏感性为89.39%，这比使用单模态或单图谱特征要好得多。
结果表明，多模态和多图谱综合方法能够有效识别MCI患者，该方法可扩展应用于各种神经和神经精神疾病。
