双树复小波变换在基于磁共振成像的影像组学用于鉴别胶质母细胞瘤和孤立性脑转移瘤中的应用

The Application of DTCWT on MRI-Derived Radiomics for Differentiation of Glioblastoma and Solitary Brain Metastases.

作者信息

Wu Wen-Feng, Shen Chia-Wei, Lai Kuan-Ming, Chen Yi-Jen, Lin Eugene C, Chen Chien-Chin

机构信息

Department of Radiology, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi 600, Taiwan.

Department of Chemistry and Biochemistry, National Chung Cheng University, Chiayi 621, Taiwan.

出版信息

J Pers Med. 2022 Aug 3;12(8):1276. doi: 10.3390/jpm12081276.

DOI:10.3390/jpm12081276

PMID:36013225

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9409920/

Abstract

BACKGROUND

While magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of patients with brain tumors, it may still be challenging to differentiate glioblastoma multiforme (GBM) from solitary brain metastasis (SBM) due to their similar imaging features. This study aimed to evaluate the features extracted of dual-tree complex wavelet transform (DTCWT) from routine MRI protocol for preoperative differentiation of glioblastoma (GBM) and solitary brain metastasis (SBM).

METHODS

A total of 51 patients were recruited, including 27 GBM and 24 SBM patients. Their contrast-enhanced T1-weighted images (CET1WIs), T2 fluid-attenuated inversion recovery (T2FLAIR) images, diffusion-weighted images (DWIs), and apparent diffusion coefficient (ADC) images were employed in this study. The statistical features of the pre-transformed images and the decomposed images of the wavelet transform and DTCWT were utilized to distinguish between GBM and SBM.

RESULTS

The support vector machine (SVM) showed that DTCWT images have a better accuracy (82.35%), sensitivity (77.78%), specificity (87.50%), and the area under the curve of the receiver operating characteristic curve (AUC) (89.20%) than the pre-transformed and conventional wavelet transform images. By incorporating DTCWT and pre-transformed images, the accuracy (86.27%), sensitivity (81.48%), specificity (91.67%), and AUC (93.06%) were further improved.

CONCLUSIONS

Our studies suggest that the features extracted from the DTCWT images can potentially improve the differentiation between GBM and SBM.

摘要

背景

虽然磁共振成像（MRI）是评估脑肿瘤患者的首选成像方式，但由于多形性胶质母细胞瘤（GBM）和孤立性脑转移瘤（SBM）具有相似的成像特征，因此区分它们可能仍具有挑战性。本研究旨在评估从常规MRI协议中提取的双树复数小波变换（DTCWT）特征，用于术前鉴别胶质母细胞瘤（GBM）和孤立性脑转移瘤（SBM）。

方法

共招募了51例患者，其中包括27例GBM患者和24例SBM患者。本研究采用了他们的对比增强T1加权图像（CET1WI）、T2液体衰减反转恢复（T2FLAIR）图像、扩散加权图像（DWI）和表观扩散系数（ADC）图像。利用变换前图像以及小波变换和双树复数小波变换分解图像的统计特征来区分GBM和SBM。

结果

支持向量机（SVM）显示，与变换前图像和传统小波变换图像相比，双树复数小波变换图像具有更高的准确率（82.35%）、灵敏度（77.78%）、特异性（87.50%）以及受试者工作特征曲线（AUC）下的面积（89.20%）。通过结合双树复数小波变换和变换前图像，准确率（86.27%）、灵敏度（81.48%）、特异性（91.67%）和AUC（93.06%）进一步提高。