Objective To assess the clinical efficacy of neoadjuvant chemotherapy （NAC） for breast invasive ductal carcinoma with MR diffusion weighted imaging. Methods Thirty patients with breast invasive ductal carcinoma underwent conventional MRI scanning and diffusion weighted imaging examination before and after preoperative neoadj-uvant chemotherapy. Two experienced radiologists independently analyzed and measured the maximum lesion diameter and apparent diffusion coefficient （ADC） values before and after treatment，respectively. Statistical analysis was performed for testing the tumor maximum diameter and ADC values change by using the paired t-test. Results After NAC treatment，the maximum tumor diameter of invasive ductal breast carcinoma sharply reduced〔（4.33±0.83） cm vs. （2.04±0.64） cm，P＜0.001〕. When b value was 1 000，the mean ADC values of breast massess were significantly changed after NAC treatment〔（1.89±0.15） ×10-3mm2/s vs. （1.14±0.31） ×10-3mm2/s， P＜0.05〕. Conclusion MR diffusion weighted imaging can non-invasively and accurately assess the NAC efficacy， which are helpful for making surgical strategies.
目的 探讨磁共振扩散加权成像（DWI）、动脉自旋标记技术（ASL）、磁共振血管成像（MRA）联合应用在缺血性脑血管病诊断中的价值。 方法 对2010年3月－2012年5月经临床和影像学诊断的104例缺血性脑血管病患者，行常规MRI、液体衰减反转恢复序列、DWI及ASL、MRA序列检查，分析DWI、ASL、MRA多种技术显示病变的信号特征、面积大小及与血管关系。 结果 DWI对急性及亚急性脑梗死的检出率为100%，对大、小面积梗死病灶检出率无明显差异；ASL对大、小面积的急性及亚急性脑梗死的检出率有差异，对大面积梗死检出率为100%，对小面积梗死的检出率为70%；DWI和ASL对短暂性脑缺血发作的检出率分别为0%、70%，液体衰减反转恢复序列对短暂性脑缺血发作患者大脑皮层下斑状缺血灶检出最敏感。 结论 DWI和ASL均可用于急性脑梗死的早期诊断，ASL对大、小面积的急性及亚急性脑梗死的检出率有差异，DWI、ASL及MRA联合应用可准确评估缺血半暗区及侧支血管情况，在缺血性脑血管病诊断中有重要价值。
Among numerous medical imaging modalities, diffusion weighted imaging (DWI) is extremely sensitive to acute ischemic stroke lesions, especially small infarcts. However, magnetic resonance imaging is time-consuming and expensive, and it is also prone to interference from metal implants. Therefore, the aim of this study is to design a medical image synthesis method based on generative adversarial network, Stroke-p2pHD, for synthesizing DWI images from computed tomography (CT). Stroke-p2pHD consisted of a generator that effectively fused local image features and global context information (Global_to_Local) and a multi-scale discriminator (M2Dis). Specifically, in the Global_to_Local generator, a fully convolutional Transformer (FCT) and a local attention module (LAM) were integrated to achieve the synthesis of detailed information such as textures and lesions in DWI images. In the M2Dis discriminator, a multi-scale convolutional network was adopted to perform the discrimination function of the input images. Meanwhile, an optimization balance with the Global_to_Local generator was ensured and the consistency of features in each layer of the M2Dis discriminator was constrained. In this study, the public Acute Ischemic Stroke Dataset (AISD) and the acute cerebral infarction dataset from Yantaishan Hospital were used to verify the performance of the Stroke-p2pHD model in synthesizing DWI based on CT. Compared with other methods, the Stroke-p2pHD model showed excellent quantitative results (mean-square error = 0.008, peak signal-to-noise ratio = 23.766, structural similarity = 0.743). At the same time, relevant experimental analyses such as computational efficiency verify that the Stroke-p2pHD model has great potential for clinical applications.