Eresen A, Alic L, Kornegay J, Ji J X
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:648-651. doi: 10.1109/EMBC.2018.8512303.
Duchenne muscular dystrophy (DMD) is a fatal Xlinked muscle disorder caused by mutations in the dystrophin gene with a consequence of progressive degeneration of skeletal and cardiac muscle. Golden retriever muscular dystrophy (GRMD) is a spontaneous X-linked canine model of DMD with similar effects. Due to high soft-tissue contrast images, MRI is preferred as a non-invasive method to extract information corresponding to biological characteristics. We propose and evaluate non-invasive MRI-based imaging biomarkers to assess the severity of golden retriever muscular dystrophy (GRMD) using 3T and 4.7T MRI data of nine animals. These imaging biomarkers use first order statistics and texture (assessed by wavelets) in quantitative MRI (qMRI). In a leave-one-sampleout cross-validation framework, we use SVM to differentiate between young and old GRMD animals. The preliminary results show good differentiation between young and old animals for different qMRI sequences and based on a different selection of features.
杜兴氏肌肉营养不良症（DMD）是一种致命的X连锁肌肉疾病，由肌营养不良蛋白基因突变引起，导致骨骼肌和心肌进行性退化。金毛寻回犬肌肉营养不良症（GRMD）是一种具有类似效应的自发性X连锁犬类DMD模型。由于MRI具有高软组织对比度图像，因此它作为一种非侵入性方法，更适合用于提取与生物学特征相关的信息。我们提出并评估基于非侵入性MRI的成像生物标志物，以使用9只动物的3T和4.7T MRI数据来评估金毛寻回犬肌肉营养不良症（GRMD）的严重程度。这些成像生物标志物在定量MRI（qMRI）中使用一阶统计量和纹理（通过小波评估）。在留一法交叉验证框架中，我们使用支持向量机（SVM）来区分年轻和年老的GRMD动物。初步结果表明，对于不同的qMRI序列以及基于不同特征选择，年轻和年老动物之间有良好的区分度。
