Cervical cancer is 1 of the most common cancers in females worldwide. Understanding the most recent global patterns and temporal trends of cervical cancer burden might be helpful for its prevention and control.Data on cervical cancer (International Classification of Diseases, Tenth Revision, code C53) incidence and mortality in 2018 were extracted from the GLOBOCAN 2018 database and further analyzed for their correlations with the Human Development Index. Temporal trends were analyzed using the annual percent change with joinpoint analysis among 31 countries with highly qualified data from the Cancer Incidence in Five Continents Plus and World Health Organization mortality databases. Future trends for the next 15 years were predicted using an open-source age-period-cohort model.Cervical cancer incidence and mortality rates were both negatively correlated with the Human Development Index (r = -0.56 for incidence, r = -0.69 for mortality; P <.001) in cross-sectional analysis, and both remained stable in 12 countries or even decreased in 14 and 18 countries for incidence and mortality, respectively, during the most recent 10 data years. Similar findings were observed for the next 15 years.Cervical cancer burden was correlated with socioeconomic development. An overwhelming majority of countries had stable or decreasing trends in incidence and mortality rates, especially in those with effective cervical cancer screening programs and human papillomavirus vaccination.The authors investigated the most up-to-date data from official databases released by the International Agency for Research on Cancer and found that cervical cancer incidence and mortality were negatively correlated with socioeconomic development. Among the 31 countries analyzed, most (26 countries were analyzed for incidence, and 30 were analyzed for mortality) had stable or even decreasing temporal trends over the most recent 10 years, especially in those with effective cervical cancer screening programs. In addition, the predicted trends for the next 15 years were basically consistent with the observed trends among most of the analyzed countries (19 countries for incidence and 26 countries for mortality).© 2021 American Cancer Society.

Cervical cancer is one of the most common cancers worldwide, and immune function may impact disease progression. Serum markers may also be associated with diagnosis and progression. The aim of this study was to explore the clinical usefulness of determining the levels of peripheral blood immune cells and serum tumor markers in predicting diagnosis and prognosis of patients with cervical cancer.82 patients with cervical cancer (early stage group: IA-IB1 and IIA1; locally advanced group: IB2 and IIA2), 54 patients with cervical intra-epithelial neoplasia (CIN), and 54 healthy women (control group) were recruited. Inclusion criteria were: (1) patients whose cervical lesions were determined based on biopsy; and (2) patients who had not undergone immunotherapy, chemotherapy, or radiotherapy. The exclusion criteria were as follows: (1) patients with a history of other malignant tumors; (2) patients with heart, kidney, and other organ failure; (3) patients with immune diseases; and (4) pregnant or lactating women. The levels of immunocytes and tumor markers were assayed. The relationships among histopathologic factors were analyzed. The correlation between the levels of immunocytes and tumor markers in patients with different degrees of cervical lesions (pre-invasive or cancer) and healthy women was evaluated.The squamous cell carcinoma antigen and carcinoembryonic antigen levels in the control group and the CIN group were significantly lower than those in the cervical cancer groups (p<0.01). The incidence of lymph node metastasis in the early stage and locally advanced groups were 22.9% (11/48) and 46.2% (12/26), respectively, and 58.8% (20/34) and 7.5% (3/37) in the positive and negative lymphovascular invasion groups, respectively (p<0.05). The levels of CD8 and CD8 CD28 T cells in the early stage group were markedly lower than those in the CIN group and the control group (p=0.014, p=0.008, respectively). The ratio of CD4CD25/CD4 in the cervical cancer groups was significantly higher than in the control group (p<0.01). The increased serum squamous cell carcinoma and carcinoembryonic antigen levels and CD4CD25/CD4 ratio were risk factors for cervical cancer by logistic regression analysis (p<0.05).In patients with cervical cancer, immune function was impaired compared with that in healthy women and patients with CIN, while squamous cell carcinoma and carcinoembryonic antigen levels were increased. Combined detection of the levels of peripheral blood immune cells and serum tumor markers may be helpful for early detection, diagnosis, and prognosis evaluation of patients with cervical cancer.© IGCS and ESGO 2020. No commercial re-use. See rights and permissions. Published by BMJ.

准确可靠的乳腺肿瘤分割是乳腺癌诊断、治疗、预后评估的关键.针对现有的基于动态增强磁共振成像（DCE-MRI）的乳腺肿瘤分割方法易遗漏小目标肿瘤等不足，本文提出了一种基于全卷积网络的可靠高效的乳腺肿瘤DCE-MRI图像分割方法.首先，对乳腺DCE-MRI数据进行预处理后，截取128&#42;128大小的图像块，并以肿瘤区域像素数为依据将数据分为两个子数据集；其次，利用数据集训练CBP5-Net得到分类模型；然后，利用两个子数据集分别训练RAU-Net得到两个分割模型；最后，将测试集数据送到网络输入端，并对网络输出结果进行后处理，得到最终的乳腺肿瘤分割结果.利用本文提出的方法得到的Dice系数、敏感性、特异性和交并比（IoU）分别达到了0.938 8、0.952 3、0.998 5和0.876 8，说明利用本文方法能够有效、精确地分割乳腺肿瘤DCE-MRI图像.

In this report, we collected the Raman spectrum of cervical adenocarcinoma and cervical squamous cell carcinoma tissues by a micro-Raman spectroscopy system. We analysed, compared and summarized the characteristics and differences of the normalized mean Raman spectra of the two tissues and pointed out the major differences in the biochemical composition between the two tissues. The PCA-SVM model that was used to distinguish the two types of cervical cancer tissues was established. The accuracy of the model in differentiating cervical adenocarcinoma from cervical squamous cell carcinoma was 93.125%. The results of this study indicate that Raman spectroscopy of cervical adenocarcinoma and cervical squamous cell carcinoma tissue in combination with SVM (support vector analysis) and PCA (principal component analysis) can be useful for the classification of cervical adenocarcinoma and cervical squamous cell carcinoma tissues and for the exploration of the differences in biochemical compositions between the two types of cervical tissue. This study lays a foundation to further study Raman spectroscopy as a clinical diagnostic method for cervical cancer.Copyright © 2019 Elsevier B.V. All rights reserved.

Ovarian cancer is a hormone-related disease with a strong genetic basis. However, none of its high-penetrance susceptibility genes and GWAS-identified variants to date are known to be involved in hormonal pathways. Given the hypothesized etiologic role of gonadotropins, an assessment of how variability in genes involved in the gonadotropin signaling pathway impacts disease risk is warranted.Genetic data from 41 ovarian cancer study sites were pooled and unconditional logistic regression was used to evaluate whether any of the 2185 SNPs from 11 gonadotropin signaling pathway genes was associated with ovarian cancer risk. A burden test using the admixture likelihood (AML) method was also used to evaluate gene-level associations.We did not find any genome-wide significant associations between individual SNPs and ovarian cancer risk. However, there was some suggestion of gene-level associations for four gonadotropin signaling pathway genes: INHBB (p=0.045, mucinous), LHCGR (p=0.046, high-grade serous), GNRH (p=0.041, high-grade serous), and FSHB (p=0.036, overall invasive). There was also suggestive evidence for INHA (p=0.060, overall invasive).Ovarian cancer studies have limited sample numbers, thus fewer genome-wide susceptibility alleles, with only modest associations, have been identified relative to breast and prostate cancers. We have evaluated the majority of ovarian cancer studies with biological samples, to our knowledge, leaving no opportunity for replication. Using both our understanding of biology and powerful gene-level tests, we have identified four putative ovarian cancer loci near INHBB, LHCGR, GNRH, and FSHB that warrant a second look if larger sample sizes and denser genotype chips become available.Copyright © 2014 Elsevier Inc. All rights reserved.

为提高基于动态增强磁共振成像（DCE-MRI）的计算机辅助（CAD）方法对乳腺病变良恶性鉴别的精度，本文基于多模态特征融合，提出一种联合非对称卷积和超轻子空间注意模块的卷积神经网络AC_Ulsam_CNN.首先，采用迁移学习方法预训练模型，筛选出对乳腺病变良恶性鉴别最为有效的DCE-MRI扫描时序.而后，基于最优扫描时序图像，搭建基于AC_Ulsam_CNN网络的模型，以增强分类模型的特征表达能力和鲁棒性.最后，将影像特征与乳腺影像数据报告和数据系统（BI-RADS）分级、表观扩散系数（ADC）和时间-信号强度曲线（TIC）类型等多模态信息进行特征融合，以进一步提高模型对病灶的预测性能.采用五折交叉验证方法进行模型验证，本文方法获得了0.826的准确率（ACC）和0.877的受试者工作曲线下面积（AUC）.这表明该算法在小样本量数据下可较好区分乳腺病变的良恶性，而基于多模态数据的融合模型也进一步丰富了特征信息，从而提高病灶的检出精度，为乳腺病灶良恶性的自动鉴别诊断提供了新方法.

在乳腺动态增强磁共振（DCE-MR）图像中，乳房分割和腺体分割是进行乳腺癌风险评估的关键步骤.为实现在三维脂肪抑制乳腺DCE-MR图像中乳房和腺体的自动分割，本文提出一种基于nnU-Net的自动分割模型，利用U-Net分层学习图像特征的优势，融合深层特征与浅层特征，得到乳房分割和腺体分割结果.同时，基于nnU-Net策略，所使用的模型能根据图像参数自动进行预处理和数据扩增，并动态调整网络结构和参数配置.实验结果表明，在具有多样化参数的三维脂肪抑制乳腺DCE-MR图像数据集上，该模型能准确、有效地实现乳房和腺体分割，平均Dice相似系数分别达到0.969&#177;0.007和0.893&#177;0.054.

肝癌是最常见的恶性肿瘤之一，亚洲地区最为常见的肝癌演变过程为肝炎-肝硬化结节-异型增生结节-肝细胞性肝癌．判断肝脏结节在演变过程所处分期，并采取干预措施，对降低肝癌的发生率非常关键．本文针对影像组学提出了更精确的支持向量机（SVM）分类算法——LFOA-F-SVM，用于对120名患者的腹部动态增强磁共振图像的肝脏结节进行四分类．该算法利用了考虑半径与几何间距的F-SVM，并结合莱维飞行策略（LF）的果蝇优化算法（FOA）寻求超参．为了验证方法的有效性，本文另外添加了5个UCI分类数据集（心脏、帕金森疾病、虹膜、葡萄酒和动物园），并与SVM、PSO-SVM、FOA-SVM、F-SVM进行比较．结果表明，在6个分类数据集（包括肝脏结节数据集和5个UCI分类数据集）中，相对于其他分类算法，LFOA-F-SVM的分类准确率最高，在肝脏结节数据集中的四分类精确率和查全率也较高．