Agner Shannon C, Rosen Mark A, Englander Sarah, Tomaszewski John E, Feldman Michael D, Zhang Paul, Mies Carolyn, Schnall Mitchell D, Madabhushi Anant
From the Department of Biomedical Engineering, Rutgers University, 599 Taylor Rd, Room 213, Piscataway, NJ 08854 (S.C.A.); Departments of Radiology (M.A.R., S.E., M.D.S.) and Pathology (M.D.F., P.Z., C.M.), University of Pennsylvania, Philadelphia, Pa; Department of Pathology and Anatomical Science, State University of New York at the University at Buffalo, Buffalo, NY (J.E.T.); and Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio (A.M.).
Radiology. 2014 Jul;272(1):91-9. doi: 10.1148/radiol.14121031. Epub 2014 Mar 10.
To determine the feasibility of using a computer-aided diagnosis (CAD) system to differentiate among triple-negative breast cancer, estrogen receptor (ER)-positive cancer, human epidermal growth factor receptor type 2 (HER2)-positive cancer, and benign fibroadenoma lesions on dynamic contrast material-enhanced (DCE) magnetic resonance (MR) images.
This is a retrospective study of prospectively acquired breast MR imaging data collected from an institutional review board-approved, HIPAA-compliant study between 2002 and 2007. Written informed consent was obtained from all patients. The authors collected DCE MR images from 65 women with 76 breast lesions who had been recruited into a larger study of breast MR imaging. The women had triple-negative (n = 21), ER-positive (n = 25), HER2-positive (n = 18), or fibroadenoma (n = 12) lesions. All lesions were classified as Breast Imaging Reporting and Data System category 4 or higher on the basis of previous imaging. Images were subject to quantitative feature extraction, feed-forward feature selection by means of linear discriminant analysis, and lesion classification by using a support vector machine classifier. The area under the receiver operating characteristic curve (Az) was calculated for each of five lesion classification tasks involving triple-negative breast cancers.
For each pair-wise lesion type comparison, linear discriminant analysis helped identify the most discriminatory features, which in conjunction with a support vector machine classifier yielded an Az of 0.73 (95% confidence interval [CI]: 0.59, 0.87) for triple-negative cancer versus all non-triple-negative lesions, 0.74 (95% CI: 0.60, 0.88) for triple-negative cancer versus ER- and HER2-positive cancer, 0.77 (95% CI: 0.63, 0.91) for triple-negative versus ER-positive cancer, 0.74 (95% CI: 0.58, 0.89) for triple-negative versus HER2-positive cancer, and 0.97 (95% CI: 0.91, 1.00) for triple-negative cancer versus fibroadenoma.
Triple-negative cancers possess certain characteristic features on DCE MR images that can be captured and quantified with CAD, enabling good discrimination of triple-negative cancers from non-triple-negative cancers, as well as between triple-negative cancers and benign fibroadenomas. Such CAD algorithms may provide added diagnostic benefit in identifying the highly aggressive triple-negative cancer phenotype with DCE MR imaging in high-risk women.
确定使用计算机辅助诊断（CAD）系统在动态对比剂增强（DCE）磁共振（MR）图像上鉴别三阴性乳腺癌、雌激素受体（ER）阳性癌、人表皮生长因子受体2（HER2）阳性癌和良性纤维腺瘤病变的可行性。
这是一项回顾性研究，对2002年至2007年间从一项经机构审查委员会批准、符合《健康保险流通与责任法案》（HIPAA）的前瞻性收集的乳腺MR成像数据进行分析。所有患者均获得书面知情同意。作者从65名患有76个乳腺病变的女性中收集了DCE MR图像，这些女性被纳入一项更大的乳腺MR成像研究。这些女性患有三阴性（n = 21）、ER阳性（n = 25）、HER2阳性（n = 18）或纤维腺瘤（n = 12）病变。根据之前的成像，所有病变均被分类为乳腺影像报告和数据系统（Breast Imaging Reporting and Data System）4类或更高类别。图像经过定量特征提取、通过线性判别分析进行前馈特征选择，并使用支持向量机分类器进行病变分类。针对涉及三阴性乳腺癌的五项病变分类任务中的每一项，计算受试者操作特征曲线下面积（Az）。
对于每对病变类型的比较，线性判别分析有助于识别最具鉴别力的特征，结合支持向量机分类器，三阴性癌与所有非三阴性病变的Az为0.73（95%置信区间[CI]：0.59，0.87），三阴性癌与ER和HER2阳性癌的Az为0.74（95% CI：0.60，0.88），三阴性与ER阳性癌的Az为0.77（95% CI：0.63，0.91），三阴性与HER2阳性癌的Az为0.74（95% CI：0.58，0.89），三阴性癌与纤维腺瘤的Az为0.97（95% CI：0.91，1.00）。
三阴性癌在DCE MR图像上具有某些特征性表现，可通过CAD进行捕捉和量化，从而能够很好地将三阴性癌与非三阴性癌以及三阴性癌与良性纤维腺瘤区分开来。这种CAD算法可能在高危女性的DCE MR成像中识别高度侵袭性的三阴性癌表型方面提供额外的诊断益处。
