Impact of the Introduction of Digital Mammography in an Organized Screening Program on the Recall and Detection Rate

In 2012, the Reggio Emilia Breast Cancer Screening Program introduced digital mammography in all its facilities at the same time. The aim of this work is to analyze the impact of digital mammography introduction on the recall rate, detection rate, and positive predictive value. The program actively invites women aged 45–74 years. We included women screened in 2011, all of whom underwent film-screen mammography, and all women screened in 2012, all of whom underwent digital mammography. Double reading was used for all mammograms, with arbitration in the event of disagreement. A total of 42,240 women underwent screen-film mammography and 45,196 underwent digital mammography. The recall rate increased from 3.3 to 4.4 % in the first year of digital mammography (relative recall adjusted by age and round 1.46, 95 % CI = 1.37–1.56); the positivity rate for each individual reading, before arbitration, rose from 3 to 5.7 %. The digital mammography recall rate decreased during 2012: after 12 months, it was similar to the recall rate with screen-film mammography. The detection rate was similar: 5.9/1000 and 5.2/1000 with screen-film and digital mammography, respectively (adjusted relative detection rate 0.95, 95 % CI = 0.79–1.13). The relative detection rate for ductal carcinoma in situ remained the same. The introduction of digital mammography to our organized screening program had a negative impact on specificity, thereby increasing the recall rate. The effect was limited to the first 12 months after introduction and was attenuated by the double reading with arbitration. We did not observe any relevant effects on the detection rate.     

Screening Ultrasound in Women with Negative Mammography: Outcome Analysis

Purpose

To show the results of an audit of screening breast ultrasound (US) in women with negative mammography in a single institution and to analyze US-detected cancers within a year and interval cancers.

Materials and Methods

During the year of 2006, 1974 women with negative mammography were screened with US in our screening center, and 1727 among them had pathologic results or any follow up breast examinations more than a year. We analyzed the distribution of Breast Imaging Reporting and Data System (BI-RADS) category and the performance outcome through follow up.

Results

Among 1727 women (age, 30-76 years, median 49.5 years), 1349 women (78.1%) showed dense breasts on mammography, 762 (44.1%) had previous breast US, and 25 women (1.4%) had a personal history of breast cancers. Test negatives were 94.2% (1.627/1727) [BI-RADS category 1 in 885 (51.2%), 2 in 742 (43.0%)]. The recall rate (=BI-RADS category 3, 4, 5) was 5.8%. Eight cancers were additionally detected with US (yield, 4.6 per 1000). The sensitivity, specificity, and positive predictive value (PPV1, PPV2) were 88.9%, 94.6%, 8.0%, and 28.0%, respectively. Eight of nine true positive cancers were stage I or in-situ cancers. One interval cancer was stage I cancer from BI-RADS category 2.

Conclusion

Screening US detected 4.6 additional cancers among 1000. The recall rate was 5.8%, which is in lower bound of acceptable range of mammography (5-12%), according to American College of Radiology standard.     

钼靶X线联合高频彩超在乳腺癌早期筛查中的应用价值

目的 探讨钼靶X线联合高频彩超在乳腺癌早期筛查中的应用价值。方法 选取2016年1月~2018年12月于什邡市人民医院就诊的126例早期乳腺癌患者（直径＜2 cm）作为研究对象。所有患者均被序贯予以钼靶X线和高频彩超检查,比较钼靶X线、高频彩超及联合检测早期乳腺癌筛查的血流信号检出率、微钙化灶检出率及诊断准确率。结果 高频彩超血流信号检出率为80.16%,高于钼靶X线的21.43%;高频彩超微细钙化检出率为33.33%,低于钼靶X线的59.52%,差异有统计学意义(P＜0.05)。高频超声诊断准确率为82.54%,高于钼靶X线的80.16%,差异无统计学意义(P＞0.05);而联合检查诊断准确率为96.83%,高于单用高频超声和单用钼靶X线,差异有统计学意义(P＜0.05)。结论 钼靶X线、高频彩超应用于乳腺癌的早期筛查各有优劣,联合应用能提高诊断乳腺癌的准确率,具有较高的临床价值。     

False Positive Marks on Unsuspicious Screening Mammography with Computer-Aided Detection

The contribution of computer-aided detection (CAD) systems as an interpretive aid in screening mammography can be hampered by a high rate of false positive detections. Specificity, false positive rate, and ease of dismissing false positive marks from two CAD systems are retrospectively evaluated. One hundred screening mammographic studies with a BI-RADS assessment code of 1 or 2 and at least 2-year normal mammographic follow-up were retrospectively reviewed using two CAD systems. Breast density, CAD marks, and radiologist's ease of dismissing false positive marks were recorded. Specificities from the two CAD versions considering all marks were 23% and 15% (p value = 0.07); mass marks, 35% and 17% (p value < 0.01); and calcification marks 62% and 75% (p value = 0.01). The two CAD versions did not differ regarding mean and median marks per case for all marks (2.3, 2.0 and 2.3, 2.0, p value = 0.65) or mass marks (1.6, 1.0 and 1.8, 2.0, p value = 0.15), but differed for calcification marks (0.8, 0 and 0.5, 0, p value < 0.01). Slightly higher specificity and fewer marks per case observed in dense breasts did not reach statistical significance. The reviewing radiologist classified most marks from both CAD systems (84% and 88%) as very easy/easy to dismiss. The two CAD versions had small differences in specificity and false positive marks. Differences, although not statistically significant, in specificities and false positive rates between dense and non-dense breasts warrant further research. Most false positive marks are easily dismissed and should not affect clinical performance.     

EMAS position statement: Individualized breast cancer screening versus population-based mammography screening programmes

Introduction

Breast cancer is the most prevalent cancer in women, with slightly more than ten percent developing the disease in Western countries. Mammography screening is a well established method to detect breast cancer.

Aims

The aim of the position statement is to review critically the advantages and shortcomings of population based mammography screening.

Materials and methods

Literature review and consensus of expert opinion.

Results and conclusion

Mammography screening programmes vary worldwide. Thus there are differences in the age at which screening is started and stopped and in the screening interval. Furthermore differences in screening quality (such as equipment, technique, resolution, single or double reading, recall rates) result in a sensitivity varying from 70% to 94% between studies. Reporting results of screening is subject to different types of bias such as overdiagnosis. Thus because of the limitations of population-based mammography screening programmes an algorithm for individualized screening is proposed.     

EMAS position statement: Individualized breast cancer screening versus population-based mammography screening programmes

IntroductionBreast cancer is the most prevalent cancer in women, with slightly more than ten percent developing the disease in Western countries. Mammography screening is a well established method to detect breast cancer.AimsThe aim of the position statement is to review critically the advantages and shortcomings of population based mammography screening.Materials and methodsLiterature review and consensus of expert opinion.Results and conclusionMammography screening programmes vary worldwide. Thus there are differences in the age at which screening is started and stopped and in the screening interval. Furthermore differences in screening quality (such as equipment, technique, resolution, single or double reading, recall rates) result in a sensitivity varying from 70% to 94% between studies. Reporting results of screening is subject to different types of bias such as overdiagnosis. Thus because of the limitations of population-based mammography screening programmes an algorithm for individualized screening is proposed.     

血清肿瘤标志物和乳腺钼靶在乳腺癌诊断中的应用价值

目的 探讨乳腺钼靶和血清肿瘤标志物在乳腺癌诊断中的应用价值.方法 回顾性分析2013年1月至2014年10月在我院明确诊断的104例乳腺癌患者的临床资料,按照乳腺肿块大小分别统计乳腺钼靶和血清肿瘤标志物CEA、CA153和CA125检测结果,对两种检查方法阳性符合率进行比较,探讨其在乳腺癌诊断中的意义.结果 乳腺肿瘤直径＜2cm组、2～ 5cm组、＞5cm组,钼靶结果阳性率分别为76.7％,87.5％,94.4％;肿瘤标志物联合诊断阳性率分别为33.3％,62.2％,100％.结论 在乳腺癌诊断中,钼靶诊断是乳腺癌诊断的重要方法,其诊断阳性率明显高于血清肿瘤标志物诊断;血清肿瘤标志物在晚期肿瘤中阳性率明显高于早期肿瘤,其在癌症复发监测、肿瘤疗效评价中的有较高价值.     

Auxiliary Diagnosis for COVID-19 with Deep Transfer Learning

To assist physicians identify COVID-19 and its manifestations through the automatic COVID-19 recognition and classification in chest CT images with deep transfer learning. In this retrospective study, the used chest CT image dataset covered 422 subjects, including 72 confirmed COVID-19 subjects (260 studies, 30,171 images), 252 other pneumonia subjects (252 studies, 26,534 images) that contained 158 viral pneumonia subjects and 94 pulmonary tuberculosis subjects, and 98 normal subjects (98 studies, 29,838 images). In the experiment, subjects were split into training (70%), validation (15%) and testing (15%) sets. We utilized the convolutional blocks of ResNets pretrained on the public social image collections and modified the top fully connected layer to suit our task (the COVID-19 recognition). In addition, we tested the proposed method on a finegrained classification task; that is, the images of COVID-19 were further split into 3 main manifestations (ground-glass opacity with 12,924 images, consolidation with 7418 images and fibrotic streaks with 7338 images). Similarly, the data partitioning strategy of 70%-15%-15% was adopted. The best performance obtained by the pretrained ResNet50 model is 94.87% sensitivity, 88.46% specificity, 91.21% accuracy for COVID-19 versus all other groups, and an overall accuracy of 89.01% for the three-category classification in the testing set. Consistent performance was observed from the COVID-19 manifestation classification task on images basis, where the best overall accuracy of 94.08% and AUC of 0.993 were obtained by the pretrained ResNet18 (P < 0.05). All the proposed models have achieved much satisfying performance and were thus very promising in both the practical application and statistics. Transfer learning is worth for exploring to be applied in recognition and classification of COVID-19 on CT images with limited training data. It not only achieved higher sensitivity (COVID-19 vs the rest) but also took far less time than radiologists, which is expected to give the auxiliary diagnosis and reduce the workload for the radiologists.     

Mammographic breast cancer screening —a randomized trial in Malmö, Sweden

A randomized trial is presented on the effect of repeated invitation to breast cancer screening with mammography on mortality from breast cancer. The invited group and the control group each consisted of approximately 21,000 women aged 45-69 yr at the start of the screening. The attendance rate was 74% at the first screening and 70% at the two subsequent screening rounds. The cancer detection rate was 7.5 per 1000 women examined in the first screening round and 2.2 and 2.0 per 1000 woman-years in the second and third screenings with an incidence of 0.9 in the intervals. The incidence in the control group was 2.7 per 1000 woman-years. The proportion of positive biopsies was 61% in the first screening round, 33% in the second, and 58% in the third. After the prevalence screening, the stage distribution was more favourable in the invited group (including non-attenders) than in the control group. In the two most recent periods of the programme, 62 out of 160 women with cancer (39%) in the invited group were in stage II-IV compared with 91 out of 159 (57%) in the control group. More than 60% of cancers detected at screening were either non-invasive or invasive with a diameter of 1 cm. The corresponding percentage in the control group was 27%. The importance of sampling bias is discussed. Although data on mortality still have to be awaited, the results so far clearly indicate a positive effect of screening.     

From facts to arguments: A study of the 2014 Swiss controversy over systematic mammography screening

Objective

The Swiss Medical Board (SMB) has recently revived the controversy over mammography screening by recommending to stop the introduction of new systematic mammography screening programs. This study aimed to examine the Swiss media coverage of the release of the SMB report.

人工智能在创伤骨科中的应用

新形势、新环境下,创伤骨科医师面临伤情更加复杂、人口老龄化加剧的严峻挑战。随着数据处理能力的飞速发展、医工交叉的深入,人工智能的应用正逐步延伸至医学各相关领域,同样也是未来创伤骨科的发展重要方向,将为创伤骨科面临的问题提出新的解决途径。人工智能将在诊断、处理、教育与研究、系统分析等领域促进创伤骨科的发展。然而,人工智能在创伤骨科的应用离不开数据安全性、稳定性的影响,仍然面临一些问题。本文就人工智能的概念及在创伤骨科中的应用与挑战做一综述,旨在汲取国内外先进的人工智能理念及先进技术,以期提升其在创伤骨科的应用,为患者提供精准化、个性化的诊疗服务。     

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses on Breast DCE-MRI Images Using Deep Convolutional Neural Network with Bayesian Optimization

Although magnetic resonance imaging (MRI) has a higher sensitivity of early breast cancer than mammography, the specificity is lower. The purpose of this study was to develop a computer-aided diagnosis (CAD) scheme for distinguishing between benign and malignant breast masses on dynamic contrast material-enhanced MRI (DCE-MRI) by using a deep convolutional neural network (DCNN) with Bayesian optimization. Our database consisted of 56 DCE-MRI examinations for 56 patients, each of which contained five sequential phase images. It included 26 benign and 30 malignant masses. In this study, we first determined a baseline DCNN model from well-known DCNN models in terms of classification performance. The optimum architecture of the DCNN model was determined by changing the hyperparameters of the baseline DCNN model such as the number of layers, the filter size, and the number of filters using Bayesian optimization. As the input of the proposed DCNN model, rectangular regions of interest which include an entire mass were selected from each of DCE-MRI images by an experienced radiologist. Three-fold cross validation method was used for training and testing of the proposed DCNN model. The classification accuracy, the sensitivity, the specificity, the positive predictive value, and the negative predictive value were 92.9% (52/56), 93.3% (28/30), 92.3% (24/26), 93.3% (28/30), and 92.3% (24/26), respectively. These results were substantially greater than those with the conventional method based on handcrafted features and a classifier. The proposed DCNN model achieved high classification performance and would be useful in differential diagnoses of masses in breast DCE-MRI images as a diagnostic aid.     

MuDeRN: Multi-category classification of breast histopathological image using deep residual networks

MotivationIdentifying carcinoma subtype can help to select appropriate treatment options and determining the subtype of benign lesions can be beneficial to estimate the patients’ risk of developing cancer in the future. Pathologists’ assessment of lesion subtypes is considered as the gold standard, however, sometimes strong disagreements among pathologists for distinction among lesion subtypes have been previously reported in the literature.ObjectiveTo propose a framework for classifying hematoxylin-eosin stained breast digital slides either as benign or cancer, and then categorizing cancer and benign cases into four different subtypes each.Materials and methodsWe used data from a publicly available database (BreakHis) of 81 patients where each patient had images at four magnification factors (×40, ×100, ×200, and ×400) available, for a total of 7786 images. The proposed framework, called MuDeRN (MUlti-category classification of breast histopathological image using DEep Residual Networks) consisted of two stages. In the first stage, for each magnification factor, a deep residual network (ResNet) with 152 layers has been trained for classifying patches from the images as benign or malignant. In the next stage, the images classified as malignant were subdivided into four cancer subcategories and those categorized as benign were classified into four subtypes. Finally, the diagnosis for each patient was made by combining outputs of ResNets’ processed images in different magnification factors using a meta-decision tree.ResultsFor the malignant/benign classification of images, MuDeRN’s first stage achieved correct classification rates (CCR) of 98.52%, 97.90%, 98.33%, and 97.66% in ×40, ×100, ×200, and ×400 magnification factors respectively. For eight-class categorization of images based on the output of MuDeRN’s both stages, CCRs in four magnification factors were 95.40%, 94.90%, 95.70%, and 94.60%. Finally, for making patient-level diagnosis, MuDeRN achieved a CCR of 96.25% for eight-class categorization.ConclusionsMuDeRN can be helpful in the categorization of breast lesions.     

Semi-Automatic Region-of-Interest Segmentation Based Computer-Aided Diagnosis of Mass Lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Breast Cancer Screening

Cancer screening with magnetic resonance imaging (MRI) is currently recommended for very high risk women. The high variability in the diagnostic accuracy of radiologists analyzing screening MRI examinations of the breast is due, at least in part, to the large amounts of data acquired. This has motivated substantial research towards the development of computer-aided diagnosis (CAD) systems for breast MRI which can assist in the diagnostic process by acting as a second reader of the examinations. This retrospective study was performed on 184 benign and 49 malignant lesions detected in a prospective MRI screening study of high risk women at Sunnybrook Health Sciences Centre. A method for performing semi-automatic lesion segmentation based on a supervised learning formulation was compared with the enhancement threshold based segmentation method in the context of a computer-aided diagnostic system. The results demonstrate that the proposed method can assist in providing increased separation between malignant and radiologically suspicious benign lesions. Separation between malignant and benign lesions based on margin measures improved from a receiver operating characteristic (ROC) curve area of 0.63 to 0.73 when the proposed segmentation method was compared with the enhancement threshold, representing a statistically significant improvement. Separation between malignant and benign lesions based on dynamic measures improved from a ROC curve area of 0.75 to 0.79 when the proposed segmentation method was compared to the enhancement threshold, also representing a statistically significant improvement. The proposed method has potential as a component of a computer-aided diagnostic system.     

1109例乳腺癌X线影像病理学分型研究

目的 提高对乳腺癌X线征象的认识。方法 分析1109例经病理证实的乳腺癌X线特征。结果 1109例病例中，非浸润性癌66例（6．0％），早期浸润性癌74例（6．7％），浸润性特殊型癌96例（8．6％），浸润性非特殊型癌851例（76.7％），其他罕见癌22例（2％）。结论 乳腺X线检查对于乳腺癌，尤其是早期乳腺癌和隐性乳癌的诊断有重大价值。     

Breast cancer screening programmes: Challenging the coexistence with opportunistic mammography

Objective

This study investigated predictive factors of women's participation in organized mammography screening (OrgMS) and/or opportunistic mammography screening (OppMS) when the two screening modes coexist.

Methods

Questionnaires were sent to 6,000 women aged 51–74 years old invited to attend an OrgMS session between 2010 and 2011 in France. Data collected concerned the women's healthcare behaviour and their socioeconomic characteristics. Women without a personal or family history of breast cancer that could explain their participation in OppMS were retained in the generalized logits analysis.

Results

The data of 1,202 women were analysed. Of these, 555 (46.2%) had attended OrgMS only, 105 (8.7%) OppMS only and 542 (45.1%) had performed both OrgMS and OppMS. Multivariable analyses showed that women who had regular gynaecological check-ups were more likely to perform OppMS only or both OrgMS and OppMS, OR 95% CI were 2.1 [1.1–3.9], 1.9 [1.4–2.6], respectively. Being employed also increased participation in OppMS only [OR: 2.1 (1.2–3.7)] or both OrgMS and OppMS [OR: 1.5 (1.1–2.05)].

Conclusion and practice implications

In countries where OrgMS and OppMS coexist, strategies involving gynaecologists, referring doctors or company doctors and the organization of healthcare services to promote adequate screening round may help to reduce the overuse of mammography.     

The effect of motivational interviewing on the change of breast cancer screening behaviors among rural Iranian women

ObjectiveThe study aimed to determine the effect of motivational interviewing on the change of breast cancer screening behaviors among rural Iranian women.MethodsThis Randomized controlled trial (RCT) was performed on 120 Iranian rural women selected through cluster random sampling method. Out of all 20 rural health centers of Abish Ahmad District, in the northwest of Iran, about one third (six clusters) were randomly selected; out of which three were randomly assigned to the control group and three to the intervention group. A list of women aged 40–69 years in the selective health centers was prepared and 60 participants were selected for each group through the convenience sampling method based on the inclusion and exclusion criteria. Then, six group sessions (two educational and four motivational interviewing sessions) were held for the intervention group. The data were collected using demographic and obstetric questionnaire, paper-based health records, and the stages of change checklist and analyzed in SPSS 24. The groups were compared through the chi square test, homogeneity test, and the sequential logistic regression with generalized estimating equations.ResultsTwo months after the intervention, a significant difference was found between the two groups in terms of the stages of change for clinical breast examination and mammography by taking into account the pre-intervention stages (p = 0.001).ConclusionMI-based counseling increased the Iranian rural women’s motivation for displaying breast cancer screening behaviors.Practice implicationsThe application of MI for enhancing cancer screening programs among Iranian women is suggested.     

Scoping review and classification of deep learning in medical genetics

Deep learning (DL) is applied in many biomedical areas. We performed a scoping review on DL in medical genetics. We first assessed 14,002 articles, of which 133 involved DL in medical genetics. DL in medical genetics increased rapidly during the studied period. In medical genetics, DL has largely been applied to small data sets of affected individuals (mean = 95, median = 29) with genetic conditions (71 different genetic conditions were studied; 24 articles studied multiple conditions). A variety of data types have been used in medical genetics, including radiologic (20%), ophthalmologic (14%), microscopy (8%), and text-based data (4%); the most common data type was patient facial photographs (46%). DL authors and research subjects overrepresent certain geographic areas (United States, Asia, and Europe). Convolutional neural networks (89%) were the most common method. Results were compared with human performance in 31% of studies. In total, 51% of articles provided data access; 16% released source code. To further explore DL in genomics, we conducted an additional analysis, the results of which highlight future opportunities for DL in medical genetics. Finally, we expect DL applications to increase in the future. To aid data curation, we evaluated a DL, random forest, and rule-based classifier at categorizing article abstracts.     

Detection of Breast Cancer with a Computer-Aided Detection Applied to Full-Field Digital Mammography

A study was conducted to evaluate the sensitivity of computer-aided detection (CAD) with full-field digital mammography in detection of breast cancer, based on mammographic appearance and histopathology. Retrospectively, CAD sensitivity was assessed in total group of 152 cases for subgroups based on breast density, mammographic presentation, lesion size, and results of histopathological examination. The overall sensitivity of CAD was 91 % (139 of 152 cases). CAD detected 100 % (47/47) of cancers manifested as microcalcifications; 98 % (62/63) of those manifested as non-calcified masses; 100 % (15/15) of those manifested as mixed masses and microcalcifications; 75 % (12/16) of those manifested as architectural distortions, and 69 % (18/26) of those manifested as focal asymmetry. CAD sensitivity was 83 % (10/12) for cancers measuring 1–10 mm, 92 % (37/40) for those measuring 11–20 mm, and 92 % (92/100) for those measuring >20 mm. There was no significant difference in CAD detection efficiency between cancers in dense breasts (88 %; 69/78) and those in non-dense breasts (95 %; 70/74). CAD showed a high sensitivity of 91 % (139/152) for the mammographic appearance of cancer and 100 % sensitivity for identifying cancers manifested as microcalcifications. Sensitivity was not influenced by breast density or lesion size. CAD should be effective for helping radiologists detect breast cancer at an earlier stage.