Department of Imaging, Wujin Hospital Affiliated with Jiangsu University, Changzhou 213003, China.
Department of Imaging, The Wujin Clinical College of Xuzhou Medical University, Changzhou 213003, China.
Comput Math Methods Med. 2022 Jun 18;2022:2917844. doi: 10.1155/2022/2917844. eCollection 2022.
The application effect of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) based on the improved fuzzy C-mean clustering (GA-PFCM) algorithm in analyzing premenopausal and postmenopausal invasive breast carcinoma was discussed. 159 patients with breast carcinoma were selected and divided into the postmenopausal group (71 patients) and the premenopausal group (88 patients) according to their menstrual status. The magnetic resonance images of the two groups were processed and analyzed using GA-PFCM algorithm, and the imaging characteristics and relevant parameters of DCE-MRI examination of the two groups were analyzed. Besides, the sensitivity, specificity, and accuracy of the diagnosis of invasive breast carcinoma by DCE-MRI examination were investigated. The results showed that the percentage of patients with lobulated lumps, patients with burrs on lesion edge, and patients with uniformly enhanced tumors in the premenopausal group was larger than that in the postmenopausal group ( < 0.05). In the postmenopausal group, TCI of 33 patients was shown as platform curves, and that of 34 patients was shown as outflow curves. In the premenopausal group, TCI of 39 patients was shown as platform curves, and that of 41 patients was shown as outflow curves with a high proportion. The number of patients with peak height time ranging between 130 s and 260 s and of patients with early signal enhancement rate ranging between 100% and 200% was large. In contrast, the number of patients with ADC value higher than 1.2 × 10 was the least. In this research, there were 128 patients with positive invasive breast carcinoma and 31 with negative invasive breast carcinoma by pathological examination. Based on DCE-MRI examination, there were 121 patients with positive invasive breast carcinoma and 38 with negative invasive breast carcinoma. The sensitivity, specificity, and accuracy of invasive breast carcinoma by DCE-MRI were 91.41%, 87.1%, and 90.57%, respectively. In addition, the positive and negative predictive values reached 96.69% and 71.05%, respectively. In summary, GA-PFCM algorithm can be applied in the processing and segmentation of DCE-MRI images, and DCE-MRI could better diagnose invasive breast carcinoma with positive guiding value.
探讨基于改进的模糊 C-均值聚类（GA-PFCM）算法的动态对比增强磁共振成像（DCE-MRI）在分析绝经前和绝经后浸润性乳腺癌中的应用效果。选取 159 例乳腺癌患者，根据月经状态分为绝经后组（71 例）和绝经前组（88 例）。采用 GA-PFCM 算法对两组患者的磁共振图像进行处理和分析，分析两组患者 DCE-MRI 检查的影像学特征和相关参数，探讨 DCE-MRI 检查对浸润性乳腺癌的诊断敏感度、特异度和准确率。结果显示，绝经前组患者中存在分叶状肿块、病灶边缘呈毛刺状、肿瘤均匀强化的患者比例大于绝经后组（<0.05）。绝经后组中，33 例 TCI 表现为平台曲线，34 例表现为流出曲线；绝经前组中，39 例 TCI 表现为平台曲线，41 例表现为流出曲线，且以高比例为主。峰值时间在 130260 s 及早期信号增强率在 100%200%的患者例数较多，而 ADC 值高于 1.2×10 的患者例数最少。本研究中，经病理检查证实 128 例患者为阳性浸润性乳腺癌，31 例为阴性浸润性乳腺癌。基于 DCE-MRI 检查，有 121 例患者为阳性浸润性乳腺癌，38 例为阴性浸润性乳腺癌。DCE-MRI 对浸润性乳腺癌的敏感度、特异度和准确率分别为 91.41%、87.1%和 90.57%，阳性和阴性预测值分别为 96.69%和 71.05%。综上所述，GA-PFCM 算法可应用于 DCE-MRI 图像的处理和分割，DCE-MRI 对诊断浸润性乳腺癌有较好的应用价值。
