Microwave-induced thermoacoustic imaging (MTI) has the advantages of high resolution, high contrast, non-ionization, and non-invasive. Recently, MTI was used in the field of breast cancer screening. In this paper, based on the finite element method (FEM) and COMSOL Multiphysics software, a three-dimensional breast cancer model suitable for exploring the MTI process is proposed to investigate the influence of Young’s modulus (YM) of breast cancer tissue on MTI. It is found that the process of electromagnetic heating and initial pressure generation of the entire breast tissue is earlier in time than the thermal expansion process. Besides, compared with normal breast tissue, tumor tissue has a greater temperature rise, displacement, and pressure rise. In particular, YM of the tumor is related to the speed of thermal expansion. In particular, the larger the YM of the tumor is, the higher the heating and contraction frequency is, and the greater the maximum pressure is. Different Young’s moduli correspond to different thermoacoustic signal spectra. In MTI, this study can be used to judge different degrees of breast cancer based on elastic imaging. In addition, this study is helpful in exploring the possibility of microwave-induced thermoacoustic elastic imaging (MTAE).

目前，病理专家通过肉眼识别显微镜视场下乳腺癌病理切片图像中的乳腺癌细胞具有很强的主观性。因此，设计了一款基于显微图像的乳腺癌细胞识别系统，该系统包括显微图像采集模块和乳腺癌细胞识别算法实现模块。通过USAF 1951分辨率测试板验证设计的乳腺癌细胞识别系统显微图像采集模块，最终的成像分辨率可以达到2.19 μm。通过多组乳腺癌病理图像验证所提乳腺癌细胞识别算法，结果表明设计的乳腺癌细胞识别系统识别乳腺癌细胞的平均准确率达到93.4%。

Photodynamic therapy (PDT) has limited effects in treating metastatic breast cancer. Immune checkpoints can deplete the function of immune cells; however, the expression of immune checkpoints after PDT is unclear. This study investigates whether the limited efficacy of PDT is due to upregulated immune checkpoints and tries to combine the PDT and immune checkpoint inhibitor to observe the efficacy. A metastatic breast cancer model was treated by PDT mediated by hematoporphyrin derivatives (HpD-PDT). The anti-tumor effect of HpD-PDT was observed, as well as CD4+T, CD8+T and calreticulin (CRT) by immunohistochemistry and immunofluorescence. Immune checkpoints on T cells were analyzed by flow cytometry after HpD-PDT. When combining PDT with immune checkpoint inhibitors, the antitumor effect and immune effect were assessed. For HpD-PDT at 100mW/cm² and 40, 60 and 80J/cm², primary tumors were suppressed and CD4+T, CD8+T and CRT were elevated; however, distant tumors couldn’t be inhibited and survival could not be prolonged. Immune checkpoints on T cells, especially PD1 and LAG-3 after HpD-PDT, were upregulated, which may explain the reason for the limited HpD-PDT effect. After PDT combined with anti-PD1 antibody, but not with anti-LAG-3 antibody, both the primary and distant tumors were significantly inhibited and the survival time was prolonged, additionally, CD4+T, CD8+T, IFN-γ+CD4+T and TNF-α+CD4+T cells were significantly increased compared with HpD-PDT. HpD-PDT could not combat metastatic breast cancer. PD1 and LAG-3 were upregulated after HpD-PDT. Anti-PD1 antibody, but not anti-LAG-3 antibody, could augment the antitumor effect of HpD-PDT for treating metastatic breast cancer.

人类表皮生长因子受体-2（HER2）的异常扩增会导致癌细胞的过度增殖和肿瘤恶化。在采用常规光学显微成像技术检测扩增水平较高的乳腺癌细胞HER2基因时，荧光原位杂交探针的荧光信号斑点呈簇状分布，难以精确计数。应用结构光照明超分辨成像技术对HER2基因荧光原位杂交的病理切片进行成像，从而分辨距离较近的荧光探针。通过大视场扫描成像和图像拼接，对数百个细胞进行成像和统计分析，提高了高扩增水平病理切片上HER2探针计数的准确性。

乳腺癌是全球女性发病率位居首位的恶性肿瘤，研究基于神经网络模型的乳腺癌诊断预测方法的目的是将临床与机器学习相结合，有助于医疗工作者更加快速准确地判断出患病与否，同时解决现有模型中存在的过拟合以及漏诊率和误诊率过高的问题，并提高预测模型的准确率。本文采用加州大学欧文分校(UCI)数据集，共 669个样本，其中包含 357个良性样本和 212个恶性肿瘤样本，共计 10个特征训练预测模型。将 10个神经网络模型采用 Adaboost方法相结合，即通过 Adaboost算法组合多个弱分类器从而形成一个强分类器，最终输出一个具有更高准确率、有较强的自学习能力、自适应能力且泛化性能优良的集成预测模型。结论表明，该模型的预测准确率达到 98.5507%，同时准确率(AUC)为 0.9966，说明所建模型区分度较好，可以反映模型的诊断价值，且非常稳定，具有非常好的验证效果，为临床应用提供进一步的技术支持和保障。

乳腺癌是世界上对于女性非常危险的疾病, 其患病率逐年增长, 是世界妇女死亡的主要原因。 在大样本情况下, 乳腺癌临床诊断受优质医疗资源相对短缺的限制, 诊断周期长、 检测费用高。 因此, 高效、 准确、 性价比高的乳腺癌诊断方法具有广阔的应用前景, 为临床诊断迫切需求。 荧光光谱检测是一种可以表征细胞中物理和化学综合变化的方法, 可用于表征正常和癌变细胞的特征。 机器学习擅长从大量数据中挖掘有用信息, 是进行分类和预测的有效手段。 以往机器学习多使用包含部分生化信息的数据库训练模型, 易导致信息缺失。 荧光光谱是细胞多种物质的叠加光谱, 使用荧光光谱特征峰诊断乳腺癌存在量化不确定性问题。 因此, 提出了机器学习结合乳腺癌样本荧光光谱的诊断方法。 使用405 nm波长的激光, 采集了正常和癌变乳腺组织(已做出病理诊断)的荧光光谱数据, 以此作为数据集, 比较了K-近邻(KNN)、 支持向量机(SVM)、 随机森林(RF)三种算法对正常和癌变乳腺组织荧光光谱的分类能力。 判别结果显示: 与SVM算法相比, KNN和RF算法的准确率更高、 平衡召回率和精度的能力更强, 对乳腺癌荧光光谱的分类能力更好, 其准确性、 召回率、 精度以及F1-score函数结果均在95%之上, 更利于乳腺癌的诊断。 进而探讨了权重KNN(WKNN)算法对正常和癌变乳腺组织荧光光谱的分类能力。 WKNN较KNN算法的分类评估结果有小幅度提升, 且具有更好的抗噪和适应能力, 算法简单。 综上所述, 本文提出的机器学习结合荧光光谱的乳腺癌诊断方法, 精度高、 速度快、 性价比高, 是未来乳腺癌诊断方法的发展方向, 具有重要的临床应用价值。

外泌体（Exosome）是直径大小为30～150 nm的膜性囊泡, 包裹DNA/RNA, miRNA, 蛋白质和脂质等多种物质并参与微环境中的生物信息传递, 是理想的癌症生物标志物, 在液体活检领域具有重要的应用潜力, 有望成为癌症快速检测的手段之一。 表面增强拉曼光谱（SERS）是分子振动光谱, 可从分子水平上探测物质的精细结构和信息变化, 具有“指纹图谱”的特征。 采用差速离心结合超速离心的方法获得乳腺癌细胞来源的外泌体, 以金溶胶为增强基底, 收集外泌体及其母细胞的SERS图谱, 结合多元统计分析, 进行乳腺癌细胞的快速鉴别与区分。 研究结果表明, 乳腺癌细胞及其外泌体在500～1 600 cm-1波段范围内有特征拉曼信号, 采用非标记检测所获得的图谱信息是样品“whole-organism fingerprint”整体信号的呈现。 根据外泌体的拉曼表型并结合OPLS-DA分析, 能够100%分辨3种不同类型的乳腺癌细胞。 单细胞SERS检测联合PCA-LDA分析, 区分乳腺癌细胞的准确率为83.7%。 通过比较乳腺癌细胞及其外泌体的拉曼特征图谱发现, 二者在拉曼谱图的波数高度表现一致, 但是外泌体在特征波数上显著增强。 具体体现为在506～569、 1 010～1 070 cm-1等波段二者存在相似性, 但外泌体在735、 963和1 318 cm-1等处的特征信号显著高于细胞。 分析认为外泌体结构比细胞更为简单, 核酸、 蛋白质等生物大分子信息更容易被表征。 同时也提示了通过SERS检测外泌体实现快速鉴定乳腺癌的可行性。 采用非标记、 直接检测, 建立了快速检测单细胞及外泌体的SERS分析技术, 结合多元统计分析能够快速鉴别不同类型的乳腺癌细胞, 并从拉曼组学角度探究了外泌体与母源细胞的关系。 该方法具有非标记、 快速、 灵敏、 准确、 简便的优势, 为乳腺癌的体外快速诊断与筛查提供有效的技术手段, 为临床应用奠定基础。

The tumor microenvironment (TME) is now recognized as an important participant of tumor progression. As the most abundant extracellular matrix component in TME, collagen plays an important role in tumor development. The imaging study of collagen morphological feature in TME is of great significance for understanding the state of tumor. Multiphoton microscopy (MPM), based on second harmonic generation (SHG) and two-photon excitation fluorescence (TPEF), can be used to monitor the morphological changes of biological tissues without labeling. In this study, we used MPM for large-scale imaging of early invasive breast cancer from the tumor center to normal tissues far from the tumor. We found that there were significant differences in collagen morphology between breast cancer tumor boundary, near tumor transition region and normal tissues far from the tumor. Furthermore, the morphological feature of eight collagen fibers was extracted to quantify the variation trend of collagen in three regions. These results may provide a new perspective for the optimal negative margin width of breast-conserving surgery and the understanding of tumor metastasis.

Because the breast cancer is an important factor that threatens women’s lives and health, early diagnosis is helpful for disease screening and a good prognosis. Exosomes are nanovesicles, secreted from cells and other body fluids, which can reflect the genetic and phenotypic status of parental cells. Compared with other methods for early diagnosis of cancer (such as circulating tumor cells (CTCs) and circulating tumor DNA), exosomes have a richer number and stronger biological stability, and have great potential in early diagnosis. Thus, it has been proposed as promising biomarkers for diagnosis of early-stage cancer. However, distinguishing different exosomes remain is a major biomedical challenge. In this paper, we used predictive Convolutional Neural model to detect and analyze exosomes of normal and cancer cells with surface-enhanced Raman scattering (SERS). As a result, it can be seen from the SERS spectra that the exosomes of MCF-7, MDA-MB-231 and MCF-10A cells have similar peaks (939, 1145 and 1380 cm−1). Based on this dataset, the predictive model can achieve 95% accuracy. Compared with principal component analysis (PCA), the trained CNN can classify exosomes from different breast cancer cells with a superior performance. The results indicate that using the sensitivity of Raman detection and exosomes stable presence in the incubation period of cancer cells, SERS detection combined with CNN screening may be used for the early diagnosis of breast cancer in the future.Because the breast cancer is an important factor that threatens women’s lives and health, early diagnosis is helpful for disease screening and a good prognosis. Exosomes are nanovesicles, secreted from cells and other body fluids, which can reflect the genetic and phenotypic status of parental cells. Compared with other methods for early diagnosis of cancer (such as circulating tumor cells (CTCs) and circulating tumor DNA), exosomes have a richer number and stronger biological stability, and have great potential in early diagnosis. Thus, it has been proposed as promising biomarkers for diagnosis of early-stage cancer. However, distinguishing different exosomes remain is a major biomedical challenge. In this paper, we used predictive Convolutional Neural model to detect and analyze exosomes of normal and cancer cells with surface-enhanced Raman scattering (SERS). As a result, it can be seen from the SERS spectra that the exosomes of MCF-7, MDA-MB-231 and MCF-10A cells have similar peaks (939, 1145 and 1380 cm−1). Based on this dataset, the predictive model can achieve 95% accuracy. Compared with principal component analysis (PCA), the trained CNN can classify exosomes from different breast cancer cells with a superior performance. The results indicate that using the sensitivity of Raman detection and exosomes stable presence in the incubation period of cancer cells, SERS detection combined with CNN screening may be used for the early diagnosis of breast cancer in the future.