Automatic Detection and Classification of Mammograms Using Improved Extreme Learning Machine with Deep Learning

Background and objectiveBreast cancer, the most intrusive form of cancer affecting women globally. Next to lung cancer, breast cancer is the one that provides a greater number of cancer deaths among women. In recent times, several intelligent methodologies were come into existence for building an effective detection and classification of such noxious type of cancer. For further improving the rate of early diagnosis and for increasing the life span of victims, optimistic light of research is essential in breast cancer classification. Accordingly, a new customized method of integrating the concept of deep learning with the extreme learning machine (ELM), which is optimized using a simple crow-search algorithm (ICS-ELM). Thus, to enhance the state-of-the-art workings, an improved deep feature-based crow-search optimized extreme learning machine is proposed for addressing the health-care problem. The paper pours a light-of-research on detecting the input mammograms as either normal or abnormal. Subsequently, it focuses on further classifying the type of abnormal severities i.e., benign type or malignant.Materials and methodsThe digital mammograms for this work are taken from the Curated Breast Imaging Subset of DDSM (CBIS-DDSM), Mammographic Image Analysis Society (MIAS), and INbreast datasets. Herein, the work employs 570 digital mammograms (250 normal, 200 benign and 120 malignant cases) from CBIS-DDSM dataset, 322 digital mammograms (207 normal, 64 benign and 51 malignant cases) from MIAS database and 179 full-field digital mammograms (66 normal, 56 benign and 57 malignant cases) from INbreast dataset for its evaluation. The work utilizes ResNet-18 based deep extracted features with proposed Improved Crow-Search Optimized Extreme Learning Machine (ICS-ELM) algorithm.ResultsThe proposed work is finally compared with the existing Support Vector Machines (RBF kernel), ELM, particle swarm optimization (PSO) optimized ELM, and crow-search optimized ELM, where the maximum overall classification accuracy is obtained for the proposed method with 97.193% for DDSM, 98.137% for MIAS and 98.266% for INbreast datasets, respectively.ConclusionThe obtained results reveal that the proposed Computer-Aided-Diagnosis (CAD) tool is robust for the automatic detection and classification of breast cancer.     

A Hybrid Deep Learning Model for Predicting Molecular Subtypes of Human Breast Cancer Using Multimodal Data

BackgroundThe prediction of breast cancer subtypes plays a key role in the diagnosis and prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in the intelligent prediction of breast cancer subtypes. However, most of the traditional DL models use single modality data, which can just extract a few features, so it cannot establish a stable relationship between patient characteristics and breast cancer subtypes.DatasetWe used the TCGA-BRCA dataset as a sample set for molecular subtype prediction of breast cancer. It is a public dataset that can be obtained through the following link: https://portal.gdc.cancer.gov/projects/TCGA-BRCAMethodsIn this paper, a Hybrid DL model based on the multimodal data is proposed. We combine the patient's gene modality data with image modality data to construct a multimodal fusion framework. According to the different forms and states, we set up feature extraction networks respectively, and then we fuse the output of the two feature networks based on the idea of weighted linear aggregation. Finally, the fused features are used to predict breast cancer subtypes. In particular, we use the principal component analysis to reduce the dimensionality of high-dimensional data of gene modality and filter the data of image modality. Besides, we also improve the traditional feature extraction network to make it show better performance.ResultsThe results show that compared with the traditional DL model, the Hybrid DL model proposed in this paper is more accurate and efficient in predicting breast cancer subtypes. Our model achieved a prediction accuracy of 88.07% in 10 times of 10-fold cross-validation. We did a separate AUC test for each subtype, and the average AUC value obtained was 0.9427. In terms of subtype prediction accuracy, our model is about 7.45% higher than the previous average.     

乳腺癌新辅助化疗的研究进展

乳腺癌是一种女性最常见的恶性肿瘤,近年来我国乳腺癌的发病率呈逐年上升趋势。研究证实,新辅助化疗不仅可使不能手术的晚期乳腺癌患者获得手术机会,而且也增加了部分患者的保乳概率,但是约20%的乳腺癌患者不能从新辅助化疗中获益,并影响后续治疗效果。因此,制定合理的、个体化的新辅助化疗方案对于提高乳腺癌患者的生存质量和改善其预后尤为重要。目前,研究已发现的NCT相关的预测因子主要包块肿瘤类型、分子分型、ER、PR、Ki67等,而HER2、TOP2A、P53、PRAP单独作为预测因子的还存在争议。本文主要对乳腺癌新辅助化疗的现状、各种预测因子的作用及其不足之处进行了综述。     

乳腺癌患者预后的相关因素分析

目的:探讨影响乳腺癌患者预后的相关因素。方法:回顾性分析2008年1月~2009年2月我院收治的81例乳腺癌患者的临床、病理及随访资料。结果:所有患者均手术治疗并经病理证实,年龄45岁以上的乳腺癌患者的五年生存率为82.6%,显著高于45岁及其以下者(45.7%,P0.05);肿瘤直径为3 cm及其以下的乳腺癌患者的五年生存率为81.5%,显著高于肿瘤直径为3 cm以上者(40.7%,P0.05);无淋巴结转移的乳腺癌患者五年生存率明显高于有淋巴结转移的乳腺癌患者(P0.05);I期、II期、Ⅲ期、Ⅳ期的乳腺癌患者五年生存率分别为93.8%、73.0%、52.9%、0%,不同临床分期的乳腺癌患者的五年生存率比较差异均有统计学意义(P0.05)。结论:乳腺癌的治疗以手术为主,年龄、肿瘤大小、淋巴结转移、临床分期与患者的预后密切相关。     

丙戊酸协同顺铂抑制乳腺癌和结直肠癌细胞生长

摘要 目的：探究丙戊酸（Valproic acid, VPA）协同顺铂抑制乳腺癌和结直肠癌细胞增殖。方法：首先使用Western blot 检测 VPA 对Acetyl-Histone H3蛋白水平的影响,使用Cell Counting Kit-8（CCK-8）法检测 VPA 对乳腺癌和结直肠癌细胞的细胞活力的影响。其次单药顺铂、VPA 和联合用药处理乳腺癌细胞 MDA-MB-231 和结直肠癌细胞 HCT-15,使用 IncuCyte 动态检测细胞生长过程和生长终点。结果：发现VPA 可抑制组蛋白去乙酰化酶的功能,升高Acetyl-Histone H3的蛋白水平,VPA 可抑制乳腺癌细胞和结直肠癌细胞增殖,且对 VPA 的药物敏感性相似;顺铂和 VPA 连用后可显著抑制乳腺癌和结直肠癌细胞增殖和活力。结论：本文发现 VPA 抑制组蛋白去乙酰化酶发挥抑制乳腺癌和结直肠癌细胞生长的新机制,并可以与顺铂连用提高抗肿瘤效果和药物敏感性,为同时患有癫痫和肿瘤的人群提供新的治疗思路。     

纳米紫杉类药物在乳腺癌治疗中的研究现状

紫杉醇虽被证明在多种肿瘤治疗中均具有良好的效果,但其有一个严重的缺陷:水溶性低。临床使用中需使用聚氧乙烯蓖麻油(CremphorEL)或无水乙醇作为溶剂,但其在体内降解时能释放组胺,导致严重的过敏反应以及肾毒性和神经毒性等不良反应,此外还存在患者耐受性差、血药浓度低、靶向性差等不足。在乳腺癌的诊断和治疗中,纳米技术改变了紫杉醇制剂的特征参数而使药物表现出缓释、控释性及靶向性等优势,解决了传统紫杉醇制剂水溶性差的缺点,提高了药物的生物利用度,并明显降低了紫杉醇的毒性和副作用,给紫杉醇药物在体内运输提供了新途径。     

血清多肿瘤标志物蛋白芯片检测在乳腺癌诊断中的价值

目的:探讨血清多肿瘤标志物蛋白芯片检测系统在乳腺癌诊断中的临床价值。方法:临床确诊的乳腺癌患者307例为乳腺癌组,非乳腺癌的其他恶性肿瘤患者495例为对照组。应用多肿瘤标志物蛋白芯片检测系统检测12种肿瘤标志物水平,评价血清肿瘤标志物的在乳腺癌组与对照组之间的差异。结果:CA153,CEA,Free-PSA这三项指标为诊断乳腺癌的独立相关因素(P<0.05),比较三项指标ROC曲线下面积可见,CA153对于鉴别乳腺癌准确性更高,其敏感性、特异性分别为78.92和56.14,女性乳腺癌患者Free-PSA可见明显升高,对乳腺癌有特殊提示意义,手术前后标志物CA199、CA242、Ferrin、CA125水平差异有统计学意义。结论:在临床常用的肿瘤标记物中,CA153,CEA,Free_PSA水平的升高与乳腺癌发生独立相关,其中CA153具有更高的诊断准确性,Free_PSA水平升高对乳腺癌的诊断有特别提示意义。     

指长比与乳腺癌的相关性研究

本文研究了宁夏汉族女性256例(正常对照:128例,乳腺癌患者:128例)左右手指长比(2D∶3D、2D∶4D、2D∶5D、3D∶4D、3D∶5D、4D∶5D),比较其均值的差异性;分析了指长比与年龄间的关系。结果表明:1)宁夏汉族正常女性与乳腺癌患者组指长比均值呈现2D∶3D<2D∶4D<3D∶4D<2D∶5D<4D∶5D<3D∶5D的趋势;2)乳腺癌患者组指长比均值均高于正常对照组,2D∶3D(P<0.05)、2D∶4D(P<0.01)、2D∶5D(左手P4D的比例高于对照组;3)乳腺癌患者组指长比均值与发病年龄呈高度负相关(P<0.001)。     

乳腺癌中α- 晶状体B 链蛋白表达的临床病理研究

目的:探讨α-晶状体蛋白B链(Alpha-crystallin B chain,CRYAB)在乳腺癌中表达的临床病理学意义。方法:收集乳腺癌病例及相应的临床资料包括随访资料,应用IHC染色方法检测CRYAB在乳腺良性病变(BBD)、无淋巴结转移乳腺癌(NMBC)、有淋巴结转移乳腺癌(MBC)及配对淋巴结转移灶(PMLN)中的表达,分析CRYAB表达与乳腺癌临床病理指标(患者年龄、肿块大小、淋巴结转移情况、临床分期、组织学分型和分级、雌孕激素受体和c-cerb B2表达情况、绝经情况)间及生存状态的关系。结果:CRYAB在对照组BBD组、NMBC组、MBC组、PMLN组的阳性表达率分别为97.9%(46/47)、44.6%(37/83)、13.1%(14/107)、10.8%(11/107),其中BBD组和NMBC组,BBD组、NMBC组分别与MBC组、PMLN组均存在显著性差异。CRYAB表达与淋巴结转移(P0.001)、临床分期(P=0.001)、组织学分级(P=0.037)和雌孕激素受体表达情况(P0.001)有显著相关,无淋巴结转移组的阳性表达率显著高于有淋巴结转移组,临床晚期的阳性表达率低于临床早期,雌孕激素受体阳性病例的阳性表达率显著低于雌孕激素受体阴性病例。生存分析结果显示CRYAB阳性表达的患者生存期比CRYAB阴性表达的患者生存期更长(p=0.037)。结论:CRYAB与乳腺癌的转移、临床分期、生存状态、雌孕激素受体表达有关。     

吉西他滨联合化疗方案治疗复发转移性乳腺癌的临床疗效观察

目的:观察吉西他滨与顺铂联合以及吉西他滨与紫杉醇联合治疗复发转移性乳腺癌的疗效和不良反应。方法:本研究收集65例女性乳腺癌术后复发转移的患者作为研究对象。随机分成两组,分别应用吉西他滨与顺铂(GP方案组)、吉西他滨与紫杉醇(GT方案组)联合进行治疗。GP方案组患者有30例,第1天、第8天用吉西他滨800mg~1000mg/m2溶于0.9%的100mL生理盐水中静脉滴注;第1天~第3天,21天重复用顺铂30mg/m2溶于0.9%的250mL生理盐水中静脉滴注;GT方案组患者有35例,吉西他滨的使用方法与GP方案组相同,第2天,21重复用紫杉醇135mg/m2溶于0.9%的500mL生理盐水中静脉滴注。对化疗时产生的不良反应进行对症处理。结果 :GP方案组化疗有效率为46.67%,疾病控制率为70.00%;GT方案组化疗有效率为42.86%,疾病控制率为68.57%,两组比较差异均无统计学意义(P0.05)。GT组脱发的发生率为62.86%,明显高于GP组的10.00%(P0.001),其他不良反应在两组之间差异无统计学意义(P0.05)。结论:GP方案和GT方案在治疗复发转移性乳腺癌有较好的疗效,不良反应较轻,可作为复方转移性乳腺的一种化疗方案。     

新辅助化疗配合手术治疗中晚期乳腺癌的临床效果分析

目的:观察新辅助化疗配合手术治疗中晚期乳腺癌的临床效果,为临床研究提供参考。方法:选取我院2009年5月-2011年4月收治的中晚期乳腺癌患者107例,根据治疗方法的不同,将患者分为新辅助化疗组和对照组。新辅助化疗组采取术前辅助化疗,而对照组术前不接受化疗。观察新辅助化疗组患者的近期临床疗效、毒副反应发生率;比较两组患者的手术时间、术中出血量等;术后随访三年,记录两组患者的肿瘤局部复发率及远处转移率。结果:新辅助化疗组患者治疗的总有效率为79.66%,毒副反应的发生率为33.89%;新辅助化疗组的平均手术时间、术中出血量均低于对照组,差异具有统计学意义(P0.05)。新辅助化疗组患者的局部复发率为5.08%,远处转移率为6.78%;对照组患者局部复发率为12.50%,远处转移率为18.75%。新辅助化疗组患者的肿瘤复发转移率低于对照组,差异具有统计学意义(P0.05)。结论:在中晚期乳腺癌的临床治疗中,术前对患者实施新辅助化疗具有明显的效果,患者近期疗效良好,毒副反应可耐受,且手术后的复发转移率相对较低,值得推广应用。     

糖尿病对乳腺癌患者预后影响的Meta 分析

目的：评价中国地区糖尿病对乳腺癌患者预后的影响,为临床工作提供依据。方法：检索万方、中国知网、维普、Medline、Pubmed、Embase数据库有关糖尿病对乳腺癌患者预后影响的文章,收集数据,进行meta 分析,以合并OR 值作为效应指标。结果：meta 分析共纳入11 篇文献,总共有28589 个病例;合并糖尿病对乳腺癌患者5 年无病生存率有影响[OR=2.48,95%CI（1.81~3.40）;I2=0%,P(Q)=0.42];合并糖尿病对乳腺癌患者5 年总生存率有影响[OR=2.40,95%CI（1.75~3.29）;I2=81.67%,P(Q)<0.01]。结论：糖尿病对乳腺癌患者预后有影响,造成生存率降低。     

整合素与EGFR 受体家族相互作用在乳腺癌中的作用研究进展

整合素与表皮生长因子受体（epithelial growth factor receptor,EGFR）在乳腺癌的发生、进展、侵袭与转移过程中发挥着重要的作用。在乳腺癌中,多种整合素的功能都与细胞的粘附相关,而EGFR 与细胞增殖、转移密切相关,过表达的整合素和EGFR 受体家族预示着预后不良。通过与受体结合,形成同源或异源二聚体,被活化的受体激活下游的信号蛋白,调节由细胞外至细胞内的信号途径,由此将刺激信号传入细胞内,从而控制细胞的增殖、转移等细胞生命事件,实现促进肿瘤进展与转移的作用。本文就整合素与EGFR 之间的相互作用在乳腺癌中的作用、对乳腺癌治疗策略及新药研发方向的影响进行综述。     

年轻乳腺癌患者的病理特点分析

目的:探讨年轻乳腺癌患者的病理特点,为其临床诊断和治疗提供参考依据。方法:选取2012年~2015年经病理组织学确诊的≤35岁年轻乳腺癌患者86例以及35岁的中老年乳腺癌患者313例作为研究对象,对其临床病理资料进行对比分析。结果:年轻乳腺癌组患者就诊时分期较晚者(III期)比例、腋窝淋巴结转移率及人类表皮生长因子受体2(HER-2)阳性率明显高于老年乳腺癌患者,而年轻乳腺癌患者雌激素受体(ER)、孕激素受体(PR)阳性率明显低于老年乳腺癌患者(P0.05)。结论:与中老年乳腺癌患者相比,年轻乳腺癌进展更快且侵袭性、转移能力更强,内分泌治疗的效果差,预后也较差。     

Fatty Acid Synthase Mediates the Epithelial-Mesenchymal Transition of Breast Cancer Cells

This study aimed to investigate the role of fatty acid synthase (FASN) in the epithelial-mesenchymal transition (EMT) of breast cancer cells. MCF-7 cells and MCF-7 cells overexpressing mitogen-activated protein kinase 5 (MCF-7-MEK5) were used in this study. MCF-7-MEK5 cells showed stable EMT characterized by increased vimentin and decreased E-cadherin expression. An In vivo animal model was established using the orthotopic injection of MCF-7 or MCF-7-MEK5 cells. Real-time quantitative PCR and western blotting were used to detect the expression levels of FASN and its downstream proteins liver fatty acid-binding protein (L-FABP) and VEGF/VEGFR-2 in both in vitro and in vivo models (nude mouse tumor tissues). In MCF-7-MEK5 cells, significantly increased expression of FASN was associated with increased levels of L-FABP and VEGF/VEGFR-2. Cerulenin inhibited MCF-7-MEK5 cell migration and EMT, and reduced FASN expression and down-stream proteins L-FABP, VEGF, and VEGFR-2. MCF-7-MEK5 cells showed higher sensitivity to Cerulenin than MCF-7 cells. Immunofluorescence revealed an increase of co-localization of FASN with VEGF on the cell membrane and with L-FABP within MCF-7-MEK5 cells. Immunohistochemistry further showed that increased percentage of FASN-positive cells in the tumor tissue was associated with increased percentages of L-FABP- and VEGF-positive cells and the Cerulenin treatment could reverse the effect. Altogether, our results suggest that FASN is essential to EMT possibly through regulating L-FABP, VEGF and VEGFR-2. This study provides a theoretical basis and potential strategy for effective suppression of malignant cells with EMT.     

Fas 相关死亡结构域蛋白在乳腺癌中表达的临床病理研究

目的:探讨Fas相关死亡结构域蛋白(Fas-associated death domain protein,FADD)在乳腺癌中表达的临床病理学意义。方法:收集乳腺癌病例及相应的临床资料包括随访资料,应用免疫组织化学技术检测乳腺良性病变,有/无淋巴结转移的乳腺癌及配对淋巴结转移灶中FADD的表达,观察分析FADD表达与乳腺癌患者年龄、肿块大小、临床分期、组织学类型和分级、雌孕激素受体水平等临床病理指标间的关系。结果:免疫组化检测结果显示良性乳腺病变组中FADD的阳性表达率(85.1%,40/47)与无淋巴结转移的乳腺癌组(45.8%,38/83),伴有淋巴结转移的乳腺癌组(67.3%72/107)和淋巴结转移灶(45.8%,49/107)组织中FADD阳性表率均有显著性差异(P值分别0.001,=0.022和0.001);此外,伴有淋巴结转移的乳腺癌组中FADD阳性表达率也均与其它三组中FADD阳性表达率之间具有显著性差异(P值分别为0.003,0.001和0.022)。FADD与患者的确诊年龄(P=0.049)和淋巴结转移有显著性相关(P=0.003),与肿瘤大小、临床分期、组织学类型、组织学分级、雌孕激素受体及cerb B-2的表达情况和月经史无明显相关性(P0.05)。生存分析显示FADD阳性表达的患者较FADD阴性患者的生存期更短。结论:FADD与乳腺癌淋巴结转移和预后有关。     

PRRX1蛋白在乳腺癌中的表达及其临床意义

目的:探讨配对相关同源框1(PRRX1)在乳腺癌中的表达及其临床病理学意义,为乳腺癌的诊断和治疗提供参考依据。方法:收集2002~2003年湖南省肿瘤医院收治的临床资料及随访资料完整的80例乳腺癌组织标本,应用免疫组织化学技术检测乳腺癌和癌旁正常乳腺组织中PRRX1的表达,并分析PRRX1表达与乳腺癌患者临床病理特征间的关系。结果:PRRX1在80例乳腺癌中的阳性表达率是45%(36/80),在癌旁组织中的阳性表达率为12.5%(5/40),二者比较有显著性差异(P0.05)。PRRX1的阳性表达率与乳腺癌患者的年龄、组织学类型、肿瘤分化程度均无显著性相关(P0.05),而与淋巴结转移、临床分期显著相关(P0.05),淋巴结转移及Ⅲ~Ⅳ期乳腺癌患者PRRX1的阳性表达率显著高于无淋巴结转移及Ⅰ~Ⅱ期的乳腺癌患者(P0.05)。PRRX1表达阴性的乳腺癌患者5年生存率显著高于PRRX1表达阳性的乳腺癌患者(P0.05)。结论:乳腺癌中PRRX1的表达上调与其发生和恶性演进密切相关,可能作为乳腺癌诊断和预后预测的候选标志物。     

Backpropagation Neural Network for Processing of Missing Data in Breast Cancer Detection

BackgroundA complete dataset is essential for biomedical implementation. Due to the limitation of objective or subjective factors, missing data often occurs, which exerts uncertainty in the subsequent data processing. Commonly used methods of interpolation are interpolating substitute values that keep minimum error. Some applications of statistics are usually used for handling this problem.MethodsWe are trying to find a higher performance interpolation method compared with the usual statistic methods, by using artificial intelligence which is in full swing today. The prediction and classification of backpropagation neural network are used in this paper, describes a missing data interpolation method to propose the interpolation model that mines association rules in the data. In the experiment, depending on a multi-layer network structure, the model is trained and tested by sample data, constantly revises network weights and thresholds. The error function decreases along the negative gradient direction and approaches the expected real output. The model is validated on the breast cancer dataset, and we select real samples from the data set for validation, moreover, add four traditional methods as a control group.ResultsThe proposed method has great performance improvement in the interpolation of missing data. Experimental results show that the interpolation accuracy of our proposed method (84%) is higher than four traditional methods (1.33%, 74.67%, 73.33%, 77.33%) as mentioned in this paper, BPNN stays low in MSE evaluation. Finally, we analyze the performance of various methods in processing missing data.ConclusionsThe study in this paper has estimated missing data with high accuracy as much as possible to reduce the negative impact in the diagnosis of real life. At the same time, it can also assist in missing data processing in the biomedical field.     

紫归长皮膏联合银离子藻酸盐治疗乳腺癌术后伤口不愈疗效观察及初步机制探讨

目的：观察紫归长皮膏联合银离子藻酸盐敷料治疗乳腺癌术后伤口不愈的临床疗效,初步探讨作用机制。方法：将80例乳腺癌术后伤口不愈患者随机分为2组,对照组40例采用银离子藻酸盐外敷,治疗组40例用紫归长皮膏联合银离子藻酸盐外敷;2组疗程均为6周,治疗6周后评价疗效;6周未愈者重新评估伤口,更改方案治疗直至创面愈合;比较2组临床疗效、创面愈合率、创面肉芽组织中血管内皮生长因子表达。结果：对照组痊愈率为68．42％,总有效率为81．58％;治疗组分别为86．49％、94．59％;组间比较,P＜0．05;治疗组VEGF面积（1447．64±240．18）μm2,对照组为（1117．95±373．54）μm2,治疗组明显优于对照组（P＜0．01）。结论：紫归长皮膏联合银离子藻酸盐敷料治疗乳腺癌术后伤口不愈,能提高创面愈合率、临床疗效;促进创面血管内皮生长因子表达,从而促进创面愈合;治疗期间未出现不良反应,值得临床推广。