Tu & Yuen Centre for Functional Onco-Imaging (CFOI), University of California, Irvine, CA 92697-5020, USA.
Eur Radiol. 2010 Apr;20(4):771-81. doi: 10.1007/s00330-009-1616-y. Epub 2009 Sep 30.
To investigate methods developed for the characterisation of the morphology and enhancement kinetic features of both mass and non-mass lesions, and to determine their diagnostic performance to differentiate between malignant and benign lesions that present as mass versus non-mass types.
Quantitative analysis of morphological features and enhancement kinetic parameters of breast lesions were used to differentiate among four groups of lesions: 88 malignant (43 mass, 45 non-mass) and 28 benign (19 mass, 9 non-mass). The enhancement kinetics was measured and analysed to obtain transfer constant (K(trans)) and rate constant (k(ep)). For each mass eight shape/margin parameters and 10 enhancement texture features were obtained. For the lesions presenting as nonmass-like enhancement, only the texture parameters were obtained. An artificial neural network (ANN) was used to build the diagnostic model.
For lesions presenting as mass, the four selected morphological features could reach an area under the ROC curve (AUC) of 0.87 in differentiating between malignant and benign lesions. The kinetic parameter (k(ep)) analysed from the hot spot of the tumour reached a comparable AUC of 0.88. The combined morphological and kinetic features improved the AUC to 0.93, with a sensitivity of 0.97 and a specificity of 0.80. For lesions presenting as non-mass-like enhancement, four texture features were selected by the ANN and achieved an AUC of 0.76. The kinetic parameter k(ep) from the hot spot only achieved an AUC of 0.59, with a low added diagnostic value.
The results suggest that the quantitative diagnostic features can be used for developing automated breast CAD (computer-aided diagnosis) for mass lesions to achieve a high diagnostic performance, but more advanced algorithms are needed for diagnosis of lesions presenting as non-mass-like enhancement.
研究用于描述肿块和非肿块病变形态学和增强动力学特征的方法，并确定这些方法在鉴别良恶性病变方面的诊断性能，这些病变表现为肿块与非肿块类型。
使用定量分析乳腺病变的形态学特征和增强动力学参数，将 88 例恶性病变（43 例肿块，45 例非肿块）和 28 例良性病变（19 例肿块，9 例非肿块）分为四组。测量并分析增强动力学，以获得转移常数（K(trans)）和速率常数（k(ep)）。对于每个肿块，获得 8 个形状/边缘参数和 10 个增强纹理特征。对于表现为非肿块样增强的病变，仅获得纹理参数。使用人工神经网络（ANN）构建诊断模型。
对于表现为肿块的病变，四种选定的形态学特征在鉴别良恶性病变方面可达到 ROC 曲线下面积（AUC）为 0.87。从肿瘤热点分析得到的动力学参数（k(ep)）达到了相当的 AUC 为 0.88。形态学和动力学特征的组合将 AUC 提高到 0.93，灵敏度为 0.97，特异性为 0.80。对于表现为非肿块样增强的病变，ANN 选择了四个纹理特征，达到 AUC 为 0.76。从热点得到的动力学参数 k(ep)仅达到 AUC 为 0.59，诊断价值较低。
结果表明，定量诊断特征可用于开发用于肿块病变的自动乳腺 CAD（计算机辅助诊断），以实现高诊断性能，但需要更先进的算法来诊断表现为非肿块样增强的病变。
