基于多尺度多模态磁共振图像的直方图特征在脑胶质瘤分级上的应用

Application of histogram features based on multiscale multimodal magnetic resonance images for brain glioma grading

目的提出一种基于多尺度多模态磁共振图像的直方图特征,并采用机器学习的方法进行脑胶质瘤的分级应用。方法收集临床60例脑胶质瘤病例,其中Ⅱ级胶质瘤弥漫型星形细胞瘤和少突胶质细胞瘤22例,Ⅲ级胶质瘤间变型少突星形细胞瘤和间变星形细胞瘤18例,Ⅳ级胶质瘤胶质母细胞瘤例20例。病例图像信息包含平扫T2加权序列、T2加权压水压脂序列以及增强后的T1序列。对3种序列图像做多尺度化处理,对多尺度化后的图像做纹理分析,以病灶核心区域为感兴趣区,计算纹理参数,探究纹理参数与脑胶质瘤的内在关联含义,行Ⅱ级与Ⅲ级间纹理参数的ROC曲线分析,以及Ⅲ级与Ⅳ级间纹理参数的ROC曲线分析。以支持向量机作为机器学习核心,核过交叉验证法,得出本文纹理分析方法在不同级别胶质瘤的分级上的准确度和整体分级准确度。结果多尺度多模态磁共振图像直方图特征结合支持向量机模型的鉴别系统在Ⅱ级和Ⅲ级脑胶质瘤间总体参数准确率为91.5%,在Ⅲ级和Ⅳ级脑胶质瘤间的总体参数准确率为97.9%。整体的三分类支持向量机模型在交叉验证法的分级准确率为91.67%。结论多尺度多模态磁共振图像的直方图特征结合支持向量机模型的鉴别系统,可以在脑胶质瘤肿瘤分级上为临床提供重要信息。

Objective To propose a histogram feature based on multi-scale multimodal magnetic resonance images and implementing a machine learning approach for the grading of gliomas.Methods sixty clinical cases of glioma were collected,including 22 cases of grade Ⅱ glioma(diffuse astrocytoma and oligodendroglioma),18 cases of grade Ⅲ glioma(anaplastic oligoastrocytoma and anaplastic astrocytoma)and 20 cases of grade Ⅳ glioma(glioblastoma).Case image information included T2-weighted sequence,T2-weighted sequence with water pressured and fat pressured,contrast-enhanced T1-weighted sequence.Multi-scale processing was performed on the three sequence images,and texture analysis was performed on the multi-scaled images.Taking the core area of the lesion as the area of interest,the texture parameters were calculated,and the intrinsic correlation between the texture parameters and glioma was explored,ROC was used to analyze the texture parameters between grade Ⅱ and grade Ⅲ,also between grade Ⅲ and grade Ⅳ.Using the support vector machine learning,the accuracy of the texture analysis method in this paper in the grading of different grades of gliomas were obtained through the cross-validation method.Results The identification system of multi-scale and multi-modal magnetic resonance image histogram features combined with support vector machine model had an accuracy rate of 91.5%between grade Ⅱ and grade Ⅲ gliomas,and an accuracy rate of 97.9%between grade Ⅲ and grade Ⅳ gliomas.The classification accuracy rate of the overall three-category support vector machine model in the cross-validation method was 91.67%.Conclusion The histogram features of multi-scale and multi-modal magnetic resonance images combined with the identification system of support vector machine model can provide important identification information for clinical glioma tumor grade.