Computer-aided diagnosis of breast cancer using cytological images: A systematic review

Cytological evaluation by microscopic image-based characterization [imprint cytology (IC) and fine needle aspiration cytology (FNAC)] plays an integral role in primary screening/detection of breast cancer. The sensitivity of IC and FNAC as a screening tool is dependent on the image quality and the pathologist’s level of expertise. Computer-aided diagnosis (CAD) is used to assists the pathologists by developing various machine learning and image processing algorithms. This study reviews the various manual and computer-aided techniques used so far in breast cytology. Diagnostic applications were studied to estimate the role of CAD in breast cancer diagnosis. This paper presents an overview of image processing and pattern recognition techniques that have been used to address several issues in breast cytology-based CAD including slide preparation, staining, microscopic imaging, pre-processing, segmentation, feature extraction and diagnostic classification. This review provides better insights to readers regarding the state of the art the knowledge on CAD-based breast cancer diagnosis to date.     

Machine Learning Based Computer Aided Diagnosis of Breast Cancer Utilizing Anthropometric and Clinical Features

Breast cancer is one of the most prevalent types of cancers in females, which has become rampant all over the world in recent years. The survival rate of breast cancer patients degrades considerably for patients diagnosed at an advanced stage compared to those diagnosed at an early stage. The objective of this study is two folds. The first one is to find the most relevant biomarkers of breast cancer, which can be attained from regular blood analysis and anthropometric measurements. The other one is to improve the performance of current computer-aided diagnosis (CAD) system of early breast cancer detection. This study utilized a recent data set containing nine anthropometric and clinical attributes. In our methodology, first, we performed multicollinearity analysis and ranked the features based on the weighted average score obtained from four filter-based feature evaluation methods such as F-score, information gain, chi-square statistic, and Minimum Redundancy Maximum Relevance. Next, to improve the separability of the target classes, we scaled and weighted the dataset using min-max normalization and similarity-based attribute weighting by the k-means clustering algorithm, respectively. Finally, we trained standard machine learning (ML) models and evaluated the performance metrics by 10-fold cross-validation method. Our support vector machine (SVM) model with radial basis function (RBF) kernel appeared to be the most successful classifier by utilizing six features, namely, Body Mass Index (BMI), Age, Glucose, MCP-1, Resistin, and Insulin. The obtained classification accuracy, sensitivity, and specificity are 93.9% (95% CI: 93.2–94.6%), 95.1% (95% CI: 94.4–95.8%), and 94.0% (95% CI: 93.3–94.7%), respectively; these performance metrics outperformed state-of-the-art methods reported in the literature. The developed model could potentially assist the medical experts for the early diagnosis of breast cancer by employing a set of attributes that can be easily obtained from regular blood analysis and anthropometric measurements.     

乳腺肿块X线检查常见漏、误诊原因的病例分析

目的:分析乳腺X线检查的误漏诊原因,提高诊断准确性。方法:选择2011年3月至2013年12月来我院就诊的135例经乳腺X线摄影和病理检查证实的乳腺肿瘤患者为研究对象,将X线摄影结果与病理检查结果对比,进行回顾性的分析。结果:病理诊断72例良性肿瘤而X线误诊为恶性7例(误诊率9.72%);63例恶性肿瘤而X线误诊为良性5例(漏诊率7.93%)。结论:乳腺X线误诊与乳腺致密程度、患者年龄以及肿瘤形态相关。掌握拍片技术减少技术性误差,提高影像质量,诊断时仔细阅片并熟知各类型乳腺疾病的特征性X影像表象,并与临床相结合,增强责任心,可减少乳腺X线检查的误漏诊。     

NBI及AFE在喉癌早期诊断中的应用

研究表明,喉癌的早期诊断、及时治疗不仅可以提高治愈率,而且也减少了患者的手术创伤和经济负担。积极开展喉癌的早期诊断研究具有重要的临床和社会意义。发现早期喉癌常规方法主要有电子喉镜、纤维喉镜、颈部CT及MRI检查,但并不能明显有效提高早期诊断率。而窄带成像(narrow band imaging,NBI)及自体荧光内镜(autofluorescence endoscopy AFE)是近几年用于喉癌早期诊断的两种新颖的内镜技术。NBI是一种通过变窄光波的波长,使粘膜上皮内乳头样毛细血管袢及粘膜下静脉的结构形成鲜明的对比,从而提高组织表面细微结构的对比度,便于发现病灶。而AFE技术是一种利用自发荧光聚集于病变组织的某个区域产生的差异强度,来区别正常组织与肿瘤性病变,从而用于肿瘤的早期诊断及识别癌前病变。因此,对NBI及AFE的进一步研究及认识对喉癌早期诊断提供非常重要的临床应用价值。     

Diagnosis delay in Libyan female breast cancer

ABSTRACT: BACKGROUND: To study the diagnosis delay and its impact on stage of disease among women with breast cancer on Libya METHODS: 200 women, aged 22 to 75 years with breast cancer diagnosed during 2008--2009 were interviewed about the period from the first symptoms to the final histological diagnosis of breast cancer. This period (diagnosis time) was categorized into 3 periods: <3 months, 3--6 months, and >6 months. If diagnosis time was longer than 3 months, the diagnosis was considered delayed (diagnosis delay). Consultation time was the time taken to visit the general practitioner after the first symptoms. Retrospective preclinical and clinical data were collected on a form (questionnaire) during an interview with each patient and from medical records. RESULTS: The median of diagnosis time was 7.5 months. Only 30.0% of patients were diagnosed within 3 months after symptoms. 14% of patients were diagnosed within 3--6 months and 56% within a period longer than 6 months. A number of factors predicted diagnosis delay: Symptoms were not considered serious in 27% of patients. Alternative therapy (therapy not associated with cancer) was applied in 13.0% of the patients. Fear and shame prevented the visit to the doctor in 10% and 4.5% of patients, respectively. Inappropriate reassurance that the lump was benign was an important reason for prolongation of the diagnosis time. Diagnosis delay was associated with initial breast symptom(s) that did not include a lump (p < 0.0001), with women who did not report monthly self examination (p < 0.0001), with old age (p = 0.004), with illiteracy (p = 0.009), with history of benign fibrocystic disease (p = 0.029) and with women who had used oral contraceptive pills longer than 5 years (p = 0.043). At the time of diagnosis, the clinical stage distribution was as follows: 9.0% stage I, 25.5% stage II, 54.0% stage III and 11.5% stage IV.Diagnosis delay was associated with bigger tumour size (p <0.0001), with positive lymph nodes (N2, N3; p < 0.0001), with high incidence of late clinical stages (p < 0.0001), and with metastatic disease (p < 0.0001). CONCLUSIONS: Diagnosis delay is very serious problem in Libya. Diagnosis delay was associated with complex interactions between several factors and with advanced stages. There is a need for improving breast cancer awareness and training of general practitioners to reduce breast cancer mortality by promoting early detection. The treatment guidelines should pay more attention to the early phases of breast cancer. Especially, guidelines for good practices in managing detectable of tumors are necessary.     

全数字化X线摄影联合MR 动态增强检查诊断早期乳腺癌的 临床价值研究

摘要目的：分析早期乳腺癌的全数字X 线摄影与MRI影像学表现,评价全数字X 线摄影联合MRI 检查在早期乳腺癌诊断中的 临床价值。方法：回顾性分析2009 年10 月至2012 年5月在我院经穿刺或手术病理证实为早期乳腺癌的42例患者的临床资料, 术前均行数字X线及动态增强MR 检查,比较两种方法单独使用和联合使用的诊断乳腺癌的准确率。结果：全数字化X 线摄片 诊断早期乳腺癌的准确率为69.0%(29/42),动态增强MR 检查为95.2%(40/42),两者比较差异有统计学意义(P<0.05);两者联合使 用诊断早期乳腺癌的准确率为97.6%(41/42)。结论：动态增强MR 检查对早期乳腺癌的诊断价值明显优于全数字X线摄影,但后 者对微小钙化显示较好,两者联合可提高诊断正确率,尤其对多腺体型和致密型乳腺的早期乳腺癌的检出具有重要的价值。     

Reliability of bioimpedance spectroscopy and tonometry after breast conserving cancer treatment

BACKGROUND: Measuring the female breast, especially after breast cancer treatment, is problematic due to breast size, texture, and patient positioning. However, being able to accurately measure changes in the breast is important, as it may help in the earlier diagnosis and treatment of early breast edema and later lymphedema. METHODS: 14 women who had undergone breast conserving surgery for breast cancer (> 12 months ago) were recruited to assess the between subject reproducibility of tonometry and bioimpedance spectroscopy (BIS). With the participant supine, two repeat measurements of the resistance of the tissues to compression (tonometry) and fluid levels (BIS) of the treated and normal breast were taken for each of the four quadrants of the breast. RESULTS: The between subject reproducibility for both measurement techniques was high, with covariance ranging from 1.29% to 3.25% for tonometry and 0.20-0.86% for BIS. CONCLUSIONS: The reliability of these two measurement techniques provides an opportunity for researchers and clinicians to easily quantify breast tissue and fluid changes which in turn may lead to the earlier diagnosis and targeted treatment of breast edema and lymphedema.     

超声弹性成像技术在前列腺癌诊断中的应用

超声弹性成像技术是一项新兴的超声成像方法,可通过分析不同组织间机械组织差异区分组织软硬度,早期主要应用于乳腺、甲状腺结节的区分和定性。随着科技的进步和医疗水平的提高,目前弹性成像技术可在二维声像图的基础上,对感兴趣区域进行定性诊断和定量分析,已逐步应用于医学各领域相关研究和临床疾病的鉴别诊断。本文介绍了弹性成像的基本原理和目前弹性成像技术在医学领域中的相关应用,叙述了前列腺癌的发展趋势和目前常用的筛查、诊断方法,详细阐述了弹性成像技术在前列腺癌诊断中的应用方法和现状,分析总结了弹性成像技术在前列腺癌诊断中的应用价值。运用弹性成像技术无创、经济便捷、实时动态、可重复性好等优点,联合前列腺癌相关筛查、诊断检查,可有效帮助早期诊断前列腺癌,减少前列腺穿刺术的针数,提高前列腺癌的检出率。     

Computer aided diagnosis of Coronary Artery Disease,Myocardial Infarction and carotid atherosclerosis using ultrasound images: A review

The diagnosis of Coronary Artery Disease (CAD), Myocardial Infarction (MI) and carotid atherosclerosis is of paramount importance, as these cardiovascular diseases may cause medical complications and large number of death. Ultrasound (US) is a widely used imaging modality, as it captures moving images and image features correlate well with results obtained from other imaging methods. Furthermore, US does not use ionizing radiation and it is economical when compared to other imaging modalities. However, reading US images takes time and the relationship between image and tissue composition is complex. Therefore, the diagnostic accuracy depends on both time taken to read the images and experience of the screening practitioner. Computer support tools can reduce the inter-operator variability with lower subject specific expertise, when appropriate processing methods are used. In the current review, we analysed automatic detection methods for the diagnosis of CAD, MI and carotid atherosclerosis based on thoracic and Intravascular Ultrasound (IVUS). We found that IVUS is more often used than thoracic US for CAD. But for MI and carotid atherosclerosis IVUS is still in the experimental stage. Furthermore, thoracic US is more often used than IVUS for computer aided diagnosis systems.     

Approaches to improving breast cancer diagnosis using a high resolution,breast specific gamma camera

Mammography remains the gold standard in breast cancer detection, although there remains a challenge for improvement in sensitivity of breast cancer detection and diagnosis. Although mammography is the most frequently utilized examination to screen for breast cancer, which has resulted in a reduction of breast cancer mortality, still some cancers are unable to be visualized on mammographic images. Mammography films are interpreted using an anatomic approach. A new approach to breast cancer diagnosis utilizes a breast specific gamma camera to measure radiotracer uptake of abnormal tissue in the breast in patients with an abnormal mammogram or palpble mass using technetium sestamibi. Images are taken using the same positioning techniques as mammography for comparison of both types of images. Multi-Institutional trials using a traditional gamma camera demonstrated potential for this approach. However, the inability of traditional gamma camera intrinsic resolution and non-optinuized breast imaging limited scintimammography. Therefore, a breast specific, high resolution gamma camera was developed to overcome these limitations.Results of clinical studies evaluating BSGI are promising and are increasingly being used. Additionally, means for minimally invasive imaging-guided acquisition of tissue are being developed so that biopsies will be avaibles for areas of interest based on radiotracer uptake.Breast specific gamma camera nuclear imaging of the breast is a developing and increasingly utilized approach to improving breast cancer detection and diagnosis.     

Comparison of female breast cancer between Russia and Germany: A population-based study on time trends and stage at diagnosis

ObjectivesWhile a mammography-screening program (MSP) is being offered systematically in Germany since 2009, the dispanserizatsiya has been implemented in Russia since 2013. This study examined trends of stage at breast cancer diagnosis in two Russian regions and compared the results with the development in Germany. In addition, we aimed to gain further insights into the early detection of breast cancer in Russia.MethodsIncidence data from two cancer registries in Russia and 12 population-based cancer registries in Germany were used to analyse breast cancer incidence rates among women above age 30 over time. Further, we calculated rate ratios to compare the age group-specific incidence rates after the implementation of MSP in Germany (2010–2014) with the period before implementation (2003–2005) separately for each tumour stage and all stages combined.ResultsDuring the study period from 2003 to 2014, age-standardised rates for breast cancer were 54.6 and 116.7 per 100,000 for Russia and Germany, respectively. The proportion of the T1 stage at diagnosis among Russian women aged 50 + is half than that in Germany. Nevertheless, we observed an increasing trend of early-stage alongside the reduction of advanced-stage incidence rates of breast cancer in Russia.ConclusionsThe observed trend in Russia may reflect overall positive changes in early detection of breast cancer, with actual proportion of T1 stage still far behind Germany. Advances in breast cancer screening efforts through the dispanserizatsiya may help to further reduce the breast cancer burden.     

Mouse models for breast cancer metastasis

Metastasis of cancer cells is the main cause of death in most breast cancer patients. Although markers for early diagnosis and drugs that limit the spread of cancer to other organs have been developed, it is difficult to prevent the relapse of breast cancer. Recent research has highlighted the importance of tumor environment in which communication between tumor cells and the body system occurs. Emerging data have suggested that animal models are a good system to investigate this communication. Therefore, studies with mouse models have been developed as a reasonable method for a systemic approach to understand breast cancer metastasis. In this review, we summarize mouse models of breast cancer and their applications to the study of human breast cancers, and discuss limitation of model system and advanced techniques to overcome it.     

全数字化X线摄影联合MR动态增强检查诊断早期乳腺癌的临床价值研究

目的：分析早期乳腺癌的全数字X线摄影与MRI影像学表现,评价全数字X线摄影联合MRI检查在早期乳腺癌诊断中的临床价值。方法：回顾性分析2009年10月至2012年5月在我院经穿刺或手术病理证实为早期乳腺癌的42例患者的临床资料,术前均行数字X线及动态增强MR检查,比较两种方法单独使用和联合使用的诊断乳腺癌的准确率。结果：全数字化X线摄片诊断早期乳腺癌的准确率为69．0％（29／42）,动态增强MR检查为95．2％（40／42）,两者比较差异有统计学意义（P〈0．05）;两者联合使用诊断早期乳腺癌的准确率为97．6％（41／42）。结论：动态增强MR检查对早期乳腺癌的诊断价值明显优于全数字X线摄影,但后者对微小钙化显示较好,两者联合可提高诊断正确率,尤其对多腺体型和致密型乳腺的早期乳腺癌的检出具有重要的价值。     

乳腺内不可触及病灶的定位活检应用价值

目的:探讨乳腺内不可触及病灶(NPBL)的定位活检技术及其在乳腺癌早期诊断中的临床应用价值。方法:对彩超发现的4459个和钼靶发现的25个NPBL分别行麦默通旋切和钩丝定位活检,确定病灶的病理类型。结果:4459个NPBL中3196个病灶为乳腺腺病或伴纤维腺瘤样结节(71.7%),1198个为纤维腺瘤(26.9%),11个为分叶状肿瘤(0.2%),17个为导管内乳头状瘤(0.4%),9个为乳腺导管原位癌,5个为导管原位癌伴微浸润,23个为浸润性癌(恶性占0.8%)。25个钼靶发现的NPBL中乳腺腺病13例(52%),导管原位癌7例,导管原位癌伴微浸润2例,浸润性癌3例(恶性占48%)。结论:超声引导下麦默通和钼靶引导下钩丝定位切除可以对NPBL做出定性诊断,具备创伤小、手术时间短和定位精准等特点,对提高乳腺癌的早期诊断率、降低死亡率具有一定的临床应用价值。     

核酸适配体在三阴性乳腺癌诊疗中的研究进展*

乳腺癌是女性高发恶性肿瘤,三阴性乳腺癌(triple-negative breast cancer, TNBC)恶性程度极高,且发病机制复杂,是乳腺癌分型中预后最差的类型,但目前其早期筛查和诊断的敏感度仍处在较低水平。因此,亟须通过应用具有高度特异性的肿瘤标志物分子探针,实现其早期诊断和治疗。核酸适配体是在人工合成的随机单链核酸序列文库中,通过指数富集的配体系统进化技术(systematic evolution of ligands by exponential enrichment, SELEX)筛选获得的寡核苷酸序列。高效的分子识别能力使其成为最具潜力的生物靶向分子,在肿瘤诊断及治疗中具有广阔的应用前景。目前,通过筛选已获得了多种靶向TNBC细胞的核酸适配体。重点综述基于SELEX及其衍生技术筛选TNBC相关核酸适配体的新进展,以及核酸适配体在TNBC诊断和治疗中的应用,为相关研究提供参考。     

The Diagnosis of Breast Pre-Cancer By the Chronobra- II. The Breast Pre-Cancer Test

Contemporary screening programmes for early breast cancer based on X-rays (mammography) are very expensive and have two serious limitations in their potential to control the disease. First, soft-tissue radiology imaging is poor at resolving a tumour in the youngest third of cancer patients because of breast density; second, by the time size of a tumour enables a diagnosis to be made, there are already hundreds of thousands of malignant cells; depending on the particular biology of the tumour they may have disseminated.

For effective control of the disease there must be some understanding of breast cancer biology so that appropriate pre-cancer therapeutic strategies can be implemented. There is persuasive evidence from the growth kinetics of excised tumours; the prognosis of the breast cancer process; the protection afforded by an early first pregnancy; the age-related sensitivity to diagnostic X-rays; and, the age-correlated presence of oestrogen receptors in tumours, that the genesis of cancer is usually in the pre-menopause (the second or third decade). Breast cancer prevention programmes have to take this early genesis into their reckoning. Also, to see any progenitor or pre-cancerous lesions the histopathologist must look in the cancer mastectomy specimens of the younger patient. When this is done, such mastectomies reveal multiple benign focal hyperplasias and cysts very much more numerous than in age-matched consecutive autopsy breasts. These abnormalities may represent a failure of acinisation and an abnormal maturation pathway with a large number of uncommitted epithelial cells vulnerable to mutation since they are not fully differentiated.     

Breast lesion characterization using Quantitative Ultrasound (QUS) and derivative texture methods

PurposeAccurate and timely diagnosis of breast cancer is extremely important because of its high incidence and high morbidity. Early diagnosis of breast cancer through screening can improve overall prognosis. Currently, biopsy remains as the gold standard for tumor pathological confirmation. Development of diagnostic imaging techniques for rapid and accurate characterization of breast lesions is required. We aim to evaluate the usefulness of texture-derivate features of QUS spectral parametric images for non-invasive characterization of breast lesions.MethodsQUS Spectroscopy was used to determine parametric images of mid-band fit (MBF), spectral slope (SS), spectral intercept (SI), average scatterer diameter (ASD), and average acoustic concentration (AAC) in 204 patients with suspicious breast lesions. Subsequently, texture analysis techniques were used to generate texture maps from parametric images to quantify heterogeneities of QUS parametric images. Further, a second-pass texture analysis was applied to obtain texture-derivate features. QUS parameters, texture-parameters and texture-derivate parameters were determined from both tumor core and a 5-mm tumor margin and were used in comparison to histopathological analysis in order to develop a diagnostic model for classifying breast lesions as either benign or malignant. Both leave-one-out and hold-out cross-validations were used to evaluate the performance of the diagnostic model. Three standard classification algorithms including a linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines-radial basis function (SVM-RBF) were evaluated.ResultsCore and margin information using the SVM-RBF attained the best classification performance of 90% sensitivity, 92% specificity, 91% accuracy, and 0.93 AUC utilizing QUS parameters and their texture derivatives, evaluated using leave-one-out cross-validation. Implementation of hold-out cross-validation using combination of both core and margin information and SVM-RBF achieved average accuracy and AUC of 88% and 0.92, respectively.ConclusionsQUS-based framework and derivative texture methods enable accurate classification of breast lesions. Evaluation of the proposed technique on a large cohort using hold-out cross-validation demonstrates its robustness and its generalization.     

乳腺癌发生的特征基因筛选及模式识别

本文选取癌症基因组图谱数据库的乳腺癌样本作为数据集,在全基因组的水平上研究乳腺癌病人从正常到发病Ⅰ期基因表达的变化,寻找与乳腺癌发病密切相关的特征基因,建立乳腺癌发生的模式识别分类方法,为乳腺癌预防及早期诊断提供理论支持.研究中,综合利用相关性、t检验、置信区间等统计学方法,建立乳腺癌发生特征基因筛选方法,获得与乳腺癌发生具有显著性差异的特征基因336个.通过机器学习方法建模,得到的分类准确率能达到98%以上,与之前乳腺癌相关的研究相比,准确率更高.同时采用KEGG(kyoto encyclopedia of genes and genomes)通路分析得到与基因显著相关(P0.05)的通路有8个,GO(gene ontology)基因功能富集分析显示与基因显著相关(P0.05)的功能有18个.最后对映射在8个通路中的一部分基因进行简要功能分析,说明了其在调控水平上的密切关系,表明识别的特征基因在乳腺癌的发生过程中有重要的作用,这对了解乳腺癌发病机理以及乳腺癌的早期诊断非常重要.     

Directional features for automatic tumor classification of mammogram images

One way for breast cancer diagnosis is provided by taking radiographic (X-ray) images (termed mammograms) for suspect patients, images further used by physicians to identify potential abnormal areas thorough visual inspection. When digital mammograms are available, computer-aided based diagnostic may help the physician in having a more accurate decision. This implies automatic abnormal areas detection using segmentation, followed by tumor classification. This work aims at describing an approach to deal with the classification of digital mammograms. Patches around tumors are manually extracted to segment the abnormal areas from the remaining of the image, considered as background. The mammogram images are filtered using Gabor wavelets and directional features are extracted at different orientation and frequencies. Principal Component Analysis is employed to reduce the dimension of filtered and unfiltered high-dimensional data. Proximal Support Vector Machines are used to final classify the data. Superior mammogram image classification performance is attained when Gabor features are extracted instead of using original mammogram images. The robustness of Gabor features for digital mammogram images distorted by Poisson noise with different intensity levels is also addressed.     

拉曼光谱技术在肿瘤检测中的应用

癌症是威胁人类健康和生命的严重疾病之一,早期诊断与及时治疗是提高癌症患者生存率的最有效途径。激光拉曼光谱技术作为一种非侵入性的检测技术,可以无损伤地提供丰富的分子结构特征和物质成分信息,从分子水平上反映癌变组织与正常组织之间的结构差异,从而可用于癌症的早期诊断。综述了激光拉曼光谱技术在皮肤癌、鼻咽癌、肺癌、胃癌、结肠癌、乳腺癌及前列腺癌诊断中的研究进展,并对拉曼光谱技术在癌症诊断中的发展方向和应用前景作了进一步的展望,为癌症的早期检测和诊断技术的应用研究提供参考依据。