Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators...Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.展开更多
Objective: To find an effective, sensitive, specific and noninvasive diagnostic method of breast cancer. Methods: 109 masses of 102 patients with breast lesions smaller than 2 cm in diameter were divided into three gr...Objective: To find an effective, sensitive, specific and noninvasive diagnostic method of breast cancer. Methods: 109 masses of 102 patients with breast lesions smaller than 2 cm in diameter were divided into three groups to undergo 99mTc-MIBI imaging and compared with the results of pathology examination. 20 cases without breast lesions were selected as control. Abnormal condensation of 99mTc-MIBI in the breast reaching 10% higher than that in the counterpart of the healthy breast was regarded as positive. Results: Of 32 breast cancers, positive imaging appeared in 25. Negative imaging were found in 31 of 38 benign breast lesions. Of 39 occult breast lesions, positive imaging appeared in 6 and 3 of them were breast cancer, 2 of 3 patients with slightly increased 99mTc-MIBI imaging threshold were breast cancer also. No positive imaging was found in the control group. The diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value of 99mTc-MIBI was 88.4%, 89.2%, 88.0%, 75.0% and 95.3%, respectively. Conclusion: 99mTc-MIBI imaging had higher sensitivity and accuracy in the diagnosis of breast cancer and differentiation between benign and malignant breast lesions. It could provide useful information for the diagnosis of clinically suspected breast cancer.展开更多
目的:探讨新版(2013年更新版)超声(ultrasound,US)乳腺影像报告数据系统(breast imaging report and data system,BI-RADS)中罗列的指标结合相关临床资料在诊断乳腺癌中的应用情况,评估新版超声BI-RADS(BI-RADS-US)在乳腺癌诊断中的临...目的:探讨新版(2013年更新版)超声(ultrasound,US)乳腺影像报告数据系统(breast imaging report and data system,BI-RADS)中罗列的指标结合相关临床资料在诊断乳腺癌中的应用情况,评估新版超声BI-RADS(BI-RADS-US)在乳腺癌诊断中的临床应用价值。方法:3名超声医师结合收集的临床资料共同对2 860个肿块的声像图进行回顾性分析,按照新版BIRADS超声影像学词典记录、分类。以病理结果为金标准,运用ROC曲线计算新版BI-RADS-US分类的诊断效能。并对记录的超声指标及收集的临床资料先行单因素分析,具有统计学意义的指标再运用多因素logistic回归分析进行分析。结果:新版BIRADS-US诊断乳腺癌BI-RADS 2类的恶性率为0.66%,3类的恶性率0.99%,4a类的恶性率为9.57%,4b类的恶性率为32.31%,4c类的恶性率为88.36%,5类的恶性率为94.19%。以4a类为截断点,新版BI-RADS-US诊断乳腺癌的敏感性为88.55%,特异性为92.17%,准确性为91.75%,AUC为0.948,Youden指数为0.81。结论:新版BI-RADS-US诊断乳腺癌风险分层的准确率高。以4a类作为截断点,新版BI-RADS-US诊断乳腺癌具有较高的诊断效能。肿块形态、边缘、钙化、血流是重要的超声变量,结合患者年龄和腋窝淋巴结转移情况可指导临床进行明确的诊断和精确的治疗。展开更多
目的调查乳腺疾病患者营养状况的现状,探讨患者体质量与乳腺癌发生的关系,为预防和筛选乳腺癌提供循证依据。方法便利抽样法选取2012年6-11月在上海交通大学医学院附属瑞金医院乳腺疾病诊治中心住院治疗的1187例患者为研究对象,采用营...目的调查乳腺疾病患者营养状况的现状,探讨患者体质量与乳腺癌发生的关系,为预防和筛选乳腺癌提供循证依据。方法便利抽样法选取2012年6-11月在上海交通大学医学院附属瑞金医院乳腺疾病诊治中心住院治疗的1187例患者为研究对象,采用营养风险筛查工具(nutritional risk screening-2002,NRS-2002)对患者的营养状况进行调查,记录其实验室检查指标,并计算体质量指数(body mass index,BMI);随访记录患者住院天数、住院费用及乳腺癌患者的临床分期。结果1187例乳腺疾病患者中有乳腺癌676例(56.95%)和乳腺良性疾病511例(43.05%)。乳腺良性疾病患者中有营养风险患者的比例要高于乳腺癌患者,差异有统计学意义(P<0.05)。乳腺癌者中体质量超过正常者的比例要高于乳腺良性疾病患者,差异有统计学意义(P<0.05)。乳腺癌患者的白蛋白水平、淋巴细胞计数明显低于乳腺良性疾病患者,而乳腺癌患者的前白蛋白水平却高于乳腺良性疾病患者,差异均有统计学意义(均P<0.05)。乳腺癌患者中以临床Ⅰ期(33.38%)和Ⅱ期(53.06%)患者占多数;不同BMI组患者在其临床分期上的差异有统计学意义(P<0.05)。结论乳腺癌患者中体质量高于正常者占多数,且超重或肥胖与乳腺癌的发生有一定联系。展开更多
文摘Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.
文摘Objective: To find an effective, sensitive, specific and noninvasive diagnostic method of breast cancer. Methods: 109 masses of 102 patients with breast lesions smaller than 2 cm in diameter were divided into three groups to undergo 99mTc-MIBI imaging and compared with the results of pathology examination. 20 cases without breast lesions were selected as control. Abnormal condensation of 99mTc-MIBI in the breast reaching 10% higher than that in the counterpart of the healthy breast was regarded as positive. Results: Of 32 breast cancers, positive imaging appeared in 25. Negative imaging were found in 31 of 38 benign breast lesions. Of 39 occult breast lesions, positive imaging appeared in 6 and 3 of them were breast cancer, 2 of 3 patients with slightly increased 99mTc-MIBI imaging threshold were breast cancer also. No positive imaging was found in the control group. The diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value of 99mTc-MIBI was 88.4%, 89.2%, 88.0%, 75.0% and 95.3%, respectively. Conclusion: 99mTc-MIBI imaging had higher sensitivity and accuracy in the diagnosis of breast cancer and differentiation between benign and malignant breast lesions. It could provide useful information for the diagnosis of clinically suspected breast cancer.
文摘目的:探讨新版(2013年更新版)超声(ultrasound,US)乳腺影像报告数据系统(breast imaging report and data system,BI-RADS)中罗列的指标结合相关临床资料在诊断乳腺癌中的应用情况,评估新版超声BI-RADS(BI-RADS-US)在乳腺癌诊断中的临床应用价值。方法:3名超声医师结合收集的临床资料共同对2 860个肿块的声像图进行回顾性分析,按照新版BIRADS超声影像学词典记录、分类。以病理结果为金标准,运用ROC曲线计算新版BI-RADS-US分类的诊断效能。并对记录的超声指标及收集的临床资料先行单因素分析,具有统计学意义的指标再运用多因素logistic回归分析进行分析。结果:新版BIRADS-US诊断乳腺癌BI-RADS 2类的恶性率为0.66%,3类的恶性率0.99%,4a类的恶性率为9.57%,4b类的恶性率为32.31%,4c类的恶性率为88.36%,5类的恶性率为94.19%。以4a类为截断点,新版BI-RADS-US诊断乳腺癌的敏感性为88.55%,特异性为92.17%,准确性为91.75%,AUC为0.948,Youden指数为0.81。结论:新版BI-RADS-US诊断乳腺癌风险分层的准确率高。以4a类作为截断点,新版BI-RADS-US诊断乳腺癌具有较高的诊断效能。肿块形态、边缘、钙化、血流是重要的超声变量,结合患者年龄和腋窝淋巴结转移情况可指导临床进行明确的诊断和精确的治疗。
文摘目的调查乳腺疾病患者营养状况的现状,探讨患者体质量与乳腺癌发生的关系,为预防和筛选乳腺癌提供循证依据。方法便利抽样法选取2012年6-11月在上海交通大学医学院附属瑞金医院乳腺疾病诊治中心住院治疗的1187例患者为研究对象,采用营养风险筛查工具(nutritional risk screening-2002,NRS-2002)对患者的营养状况进行调查,记录其实验室检查指标,并计算体质量指数(body mass index,BMI);随访记录患者住院天数、住院费用及乳腺癌患者的临床分期。结果1187例乳腺疾病患者中有乳腺癌676例(56.95%)和乳腺良性疾病511例(43.05%)。乳腺良性疾病患者中有营养风险患者的比例要高于乳腺癌患者,差异有统计学意义(P<0.05)。乳腺癌者中体质量超过正常者的比例要高于乳腺良性疾病患者,差异有统计学意义(P<0.05)。乳腺癌患者的白蛋白水平、淋巴细胞计数明显低于乳腺良性疾病患者,而乳腺癌患者的前白蛋白水平却高于乳腺良性疾病患者,差异均有统计学意义(均P<0.05)。乳腺癌患者中以临床Ⅰ期(33.38%)和Ⅱ期(53.06%)患者占多数;不同BMI组患者在其临床分期上的差异有统计学意义(P<0.05)。结论乳腺癌患者中体质量高于正常者占多数,且超重或肥胖与乳腺癌的发生有一定联系。
