Department of Radiology, University of Chicago, 5841 S Maryland Ave, MC2026, Chicago, IL 60637, USA.
Radiology. 2010 Mar;254(3):680-90. doi: 10.1148/radiol.09090838. Epub 2010 Feb 1.
To assess the performance of computer-extracted dynamic contrast material-enhanced (DCE) magnetic resonance (MR) imaging kinetic and morphologic features in the differentiation of invasive versus noninvasive breast lesions and metastatic versus nonmetastatic breast lesions.
In this institutional review board-approved HIPAA-compliant study, in which the requirement for informed patient consent was waived, breast MR images were retrospectively collected. The images had been obtained with a 1.5-T MR unit by using a gadodiamide-enhanced T1-weighted spoiled gradient-recalled acquisition in the steady state sequence. The breast MR imaging database contained 132 benign, 71 ductal carcinoma in situ (DCIS), and 150 invasive ductal carcinoma (IDC) lesions. Fifty-four IDC lesions were associated with metastasis-positive lymph nodes (LNs), and 64 IDC lesions were associated with negative LNs. Lesion segmentation and extraction of morphologic and kinetic features were automatically performed by a laboratory-developed computer workstation. Features were first selected by using stepwise linear discriminant analysis and then merged by using Bayesian neural networks. Lesion classification performance was assessed with receiver operating characteristic analysis.
Differentiation of DCIS from IDC lesions yielded an area under the receiver operating characteristic curve (AUC) of 0.83 +/- 0.03 (standard error). AUCs were 0.85 +/- 0.02 for differentiation between IDC and benign lesions and 0.79 +/- 0.03 for differentiation between DCIS and benign lesions. Differentiation between IDC lesions associated with positive LNs and IDC lesions associated with negative LNs yielded an AUC of 0.82 +/- 0.04. AUCs were 0.86 +/- 0.03 for differentiation between IDC lesions associated with positive LNs and benign lesions and 0.83 +/- 0.03 for differentiation between IDC lesions associated with negative LNs and benign lesions.
Computer-aided diagnosis of breast DCE MR imaging-depicted lesions was extended from the task of discriminating between malignant and benign lesions to the prognostic tasks of distinguishing between noninvasive and invasive lesions and discriminating between metastatic and nonmetastatic lesions, yielding MR imaging-based prognostic markers.
http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.09090838/-/DC1.
评估计算机提取的动态对比增强（DCE）磁共振（MR）成像的动力学和形态学特征在鉴别浸润性与非浸润性乳腺病变以及转移性与非转移性乳腺病变中的性能。
本研究经机构审查委员会批准，符合 HIPAA 规定，且豁免了患者知情同意的要求，回顾性地收集了乳腺 MR 图像。这些图像是使用 1.5-T MR 设备通过钆喷替酸葡甲胺增强的 T1 加权扰相梯度回波稳态序列获得的。乳腺 MR 成像数据库包含 132 例良性病变、71 例导管原位癌（DCIS）和 150 例浸润性导管癌（IDC）病变。54 例 IDC 病变与阳性淋巴结（LNs）相关，64 例 IDC 病变与阴性 LNs 相关。通过实验室开发的计算机工作站自动进行病变分割和形态学及动力学特征提取。首先使用逐步线性判别分析选择特征，然后使用贝叶斯神经网络进行合并。使用受试者工作特征（ROC）分析评估病变分类性能。
DCIS 与 IDC 病变的鉴别诊断得到的 ROC 曲线下面积（AUC）为 0.83±0.03（标准误差）。IDC 与良性病变的鉴别诊断 AUC 为 0.85±0.02，DCIS 与良性病变的鉴别诊断 AUC 为 0.79±0.03。IDC 病变与阳性 LNs 相关与 IDC 病变与阴性 LNs 相关的鉴别诊断 AUC 为 0.82±0.04。IDC 病变与阳性 LNs 相关与良性病变的鉴别诊断 AUC 为 0.86±0.03，IDC 病变与阴性 LNs 相关与良性病变的鉴别诊断 AUC 为 0.83±0.03。
从鉴别良恶性病变的任务扩展到鉴别非浸润性与浸润性病变以及鉴别转移性与非转移性病变的预后任务，计算机辅助诊断乳腺 DCE-MR 成像描绘的病变提供了基于 MR 成像的预后标志物。
http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.09090838/-/DC1.
