Computerized interpretation of breast MRI: Investigation of enhancement-variance dynamics
Computerized interpretation of breast MRI: Investigation of enhancement-variance dynamics
复制标题
DOI：
10.1118/1.1695652
复制
发表时间：
2004-05-01
期刊：
影响因子：
3.8
通讯作者：
Bick, U
中科院分区：
文献类型：
--
作者：
Chen, WJ;Giger, ML;Bick, U
使用对比剂Gd-DTPA的乳腺MRI在乳腺癌诊断中的优势已经得到了充分的证实。然而，解释标准的变化和解释指南的缺乏是MRI应用于乳腺成像常规临床实践的主要障碍。我们的研究旨在通过开发一种最终用于计算机辅助诊断的自动解释方法来增加乳腺MRI解释的客观性和重复性。这项研究中的数据库包含121例病例：77例恶性肿块和44例良性肿块，经活检证实。使用T1加权的3D破坏梯度回波序列获得图像。获取平扫序列后，静脉注射Gd-DTPA造影剂，剂量为0.2 mm o l/kg。取5个增强后序列，时间间隔为60 S，每个序列均为冠状位，层厚为128×256像素，面内分辨率为1.25×1.25 mm。根据乳房大小的不同，切片厚度从2到3 mm不等。病变由经验丰富的放射科医生描绘，并由计算机使用自动体积增长算法独立描绘。从病变中自动提取的14个特征可以根据(1)形态、(11)增强动力学和(111)病变上增强-变化的时间过程分为三类。采用逐步特征选择程序来选择有效的特征子集，然后通过线性判别分析(LDA)将其组合成与恶性可能性相关的判别分数。用受试者操作特征(ROC)分析来评价个体特征的分类性能和综合判别分数。根据放射科医生描绘的病变轮廓，逐步特征选择在留一法交叉验证测试中得到四个特征和LDA的A(Z)值0.80。使用计算机分割的病变体积，它产生了6个特征，在留一法测试中LDA的A值为0.86。(C)2004年美国医学物理学家协会。
The advantages of breast MRI using contrast agent Gd-DTPA in the diagnosis of breast cancer have been well established. The variation of interpretation criteria and absence of interpretation guidelines, however, is a major obstacle for applications of MRI in the routine clinical practice of breast imaging. Our study aims to increase the objectivity and reproducibility of breast MRI interpretation by developing an automated interpretation approach for ultimate use in computer-aided diagnosis. The database in this study contains 121 cases: 77 malignant and 44 benign masses as revealed by biopsy. Images were obtained using a T1-weighted 3D spoiled gradient echo sequence. After the acquisition of the precontrast series, Gd-DTPA contrast agent was injected intravenously by power injection with a dose of 0.2 mmol/kg. Five postcontrast series were then taken with a time interval of 60 s. Each series contained 64 coronal slices with a matrix of 128 X 256 pixels and an in-plane resolution of 1.25 X 1.25 mm. Slice thickness ranged from 2 to 3 mm depending on breast size. The lesions were delineated by an experienced radiologist as well as independently by computer using an automatic volume-growing algorithm. Fourteen features that were extracted automatically from the lesions could be grouped into three categories based on (1) morphology, (11) enhancement kinetics, and (111) time course of enhancement-variation over the lesion. A stepwise feature selection procedure was employed to select an effective subset of features, which were then combined by linear discriminant analysis (LDA) into a discriminant score, related to the likelihood of malignancy. The classification performances of individual features and the combined discriminant score were evaluated with receiver operating characteristic (ROC) analysis. With the radiologist-delineated lesion contours, stepwise feature selection yielded four features and an A(z) value of 0.80 for the LDA in leave-one-out cross-validation testing. With the computer-segmented lesion volumes, it yielded six features and an A, value of 0.86 for the LDA in the leave-one-out testing. (C) 2004 American Association of Physicists in Medicine.