Showing papers on "Mammography published in 2020"

International evaluation of an AI system for breast cancer screening.

Abstract: Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening. An artificial intelligence (AI) system performs as well as or better than radiologists at detecting breast cancer from mammograms, and using a combination of AI and human inputs could help to improve screening efficiency.

Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study

Abstract: Summary Background Mammography is the current standard for breast cancer screening. This study aimed to develop an artificial intelligence (AI) algorithm for diagnosis of breast cancer in mammography, and explore whether it could benefit radiologists by improving accuracy of diagnosis. Methods In this retrospective study, an AI algorithm was developed and validated with 170 230 mammography examinations collected from five institutions in South Korea, the USA, and the UK, including 36 468 cancer positive confirmed by biopsy, 59 544 benign confirmed by biopsy (8827 mammograms) or follow-up imaging (50 717 mammograms), and 74 218 normal. For the multicentre, observer-blinded, reader study, 320 mammograms (160 cancer positive, 64 benign, 96 normal) were independently obtained from two institutions. 14 radiologists participated as readers and assessed each mammogram in terms of likelihood of malignancy (LOM), location of malignancy, and necessity to recall the patient, first without and then with assistance of the AI algorithm. The performance of AI and radiologists was evaluated in terms of LOM-based area under the receiver operating characteristic curve (AUROC) and recall-based sensitivity and specificity. Findings The AI standalone performance was AUROC 0·959 (95% CI 0·952–0·966) overall, and 0·970 (0·963–0·978) in the South Korea dataset, 0·953 (0·938–0·968) in the USA dataset, and 0·938 (0·918–0·958) in the UK dataset. In the reader study, the performance level of AI was 0·940 (0·915–0·965), significantly higher than that of the radiologists without AI assistance (0·810, 95% CI 0·770–0·850; p Interpretation The AI algorithm developed with large-scale mammography data showed better diagnostic performance in breast cancer detection compared with radiologists. The significant improvement in radiologists' performance when aided by AI supports application of AI to mammograms as a diagnostic support tool. Funding Lunit.

Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms

Abstract: Importance Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. Design, Setting, and Participants In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Main Outcomes and Measurements Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists’ specificity with radiologists’ sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists’ recall assessment was developed and evaluated. Results Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists’ sensitivity, lower than community-practice radiologists’ specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. Conclusions and Relevance While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.

Mammography screening reduces rates of advanced and fatal breast cancers: Results in 549,091 women.

Abstract: Background It is of paramount importance to evaluate the impact of participation in organized mammography service screening independently from changes in breast cancer treatment. This can be done b ...

Breast Cancer Screening and Diagnosis: A Synopsis of the European Breast Guidelines

Abstract: Description The European Commission Initiative for Breast Cancer Screening and Diagnosis guidelines (European Breast Guidelines) are coordinated by the European Commission's Joint Research Centre. The target audience for the guidelines includes women, health professionals, and policymakers. Methods An international guideline panel of 28 multidisciplinary members, including patients, developed questions and corresponding recommendations that were informed by systematic reviews of the evidence conducted between March 2016 and December 2018. GRADE (Grading of Recommendations Assessment, Development and Evaluation) Evidence to Decision frameworks were used to structure the process and minimize the influence of competing interests by enhancing transparency. Questions and recommendations, expressed as strong or conditional, focused on outcomes that matter to women and provided a rating of the certainty of evidence. Recommendations This synopsis of the European Breast Guidelines provides recommendations regarding organized screening programs for women aged 40 to 75 years who are at average risk. The recommendations address digital mammography screening and the addition of hand-held ultrasonography, automated breast ultrasonography, or magnetic resonance imaging compared with mammography alone. The recommendations also discuss the frequency of screening and inform decision making for women at average risk who are recalled for suspicious lesions or who have high breast density.

External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms

Abstract: Importance A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening. Objective To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. Design, Setting, and Participants This retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). Main Outcomes and Measures Positive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). Results The median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. Conclusions and Relevance To our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers.

Deep Learning Assisted Efficient AdaBoost Algorithm for Breast Cancer Detection and Early Diagnosis

Abstract: Breast cancer is one of the most dangerous diseases and the second largest cause of female cancer death. Breast cancer starts when malignant, cancerous lumps start to grow from the breast cells. Self-tests and Periodic clinical checks help to early diagnosis and thereby improve the survival chances significantly. The breast cancer classification is a medical method that provides researchers and scientists with a great challenge. Neural networks have recently become a popular tool in cancer data classification. In this paper, Deep Learning assisted Efficient Adaboost Algorithm (DLA-EABA) for breast cancer detection has been mathematically proposed with advanced computational techniques. In addition to traditional computer vision approaches, tumor classification methods using transfers are being actively developed through the use of deep convolutional neural networks (CNNs). This study starts with examining the CNN-based transfer learning to characterize breast masses for different diagnostic, predictive tasks or prognostic or in several imaging modalities, such as Magnetic Resonance Imaging (MRI), Ultrasound (US), digital breast tomosynthesis and mammography. The deep learning framework contains several convolutional layers, LSTM, Max-pooling layers. The classification and error estimation that has been included in a fully connected layer and a softmax layer. This paper focuses on combining these machine learning approaches with the methods of selecting features and extracting them through evaluating their output using classification and segmentation techniques to find the most appropriate approach. The experimental results show that the high accuracy level of 97.2%, Sensitivity 98.3%, and Specificity 96.5% has been compared to other existing systems.

Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study.

Abstract: Summary Background We examined the potential change in cancer detection when using an artificial intelligence (AI) cancer-detection software to triage certain screening examinations into a no radiologist work stream, and then after regular radiologist assessment of the remainder, triage certain screening examinations into an enhanced assessment work stream. The purpose of enhanced assessment was to simulate selection of women for more sensitive screening promoting early detection of cancers that would otherwise be diagnosed as interval cancers or as next-round screen-detected cancers. The aim of the study was to examine how AI could reduce radiologist workload and increase cancer detection. Methods In this retrospective simulation study, all women diagnosed with breast cancer who attended two consecutive screening rounds were included. Healthy women were randomly sampled from the same cohort; their observations were given elevated weight to mimic a frequency of 0·7% incident cancer per screening interval. Based on the prediction score from a commercially available AI cancer detector, various cutoff points for the decision to channel women to the two new work streams were examined in terms of missed and additionally detected cancer. Findings 7364 women were included in the study sample: 547 were diagnosed with breast cancer and 6817 were healthy controls. When including 60%, 70%, or 80% of women with the lowest AI scores in the no radiologist stream, the proportion of screen-detected cancers that would have been missed were 0, 0·3% (95% CI 0·0–4·3), or 2·6% (1·1–5·4), respectively. When including 1% or 5% of women with the highest AI scores in the enhanced assessment stream, the potential additional cancer detection was 24 (12%) or 53 (27%) of 200 subsequent interval cancers, respectively, and 48 (14%) or 121 (35%) of 347 next-round screen-detected cancers, respectively. Interpretation Using a commercial AI cancer detector to triage mammograms into no radiologist assessment and enhanced assessment could potentially reduce radiologist workload by more than half, and pre-emptively detect a substantial proportion of cancers otherwise diagnosed later. Funding Stockholm City Council.

Review of Microwaves Techniques for Breast Cancer Detection

Abstract: Conventional breast cancer detection techniques including X-ray mammography, magnetic resonance imaging, and ultrasound scanning suffer from shortcomings such as excessive cost, harmful radiation, and inconveniences to the patients. These challenges motivated researchers to investigate alternative methods including the use of microwaves. This article focuses on reviewing the background of microwave techniques for breast tumour detection. In particular, this study reviews the recent advancements in active microwave imaging, namely microwave tomography and radar-based techniques. The main objective of this paper is to provide researchers and physicians with an overview of the principles, techniques, and fundamental challenges associated with microwave imaging for breast cancer detection. Furthermore, this study aims to shed light on the fact that until today, there are very few commercially available and cost-effective microwave-based systems for breast cancer imaging or detection. This conclusion is not intended to imply the inefficacy of microwaves for breast cancer detection, but rather to encourage a healthy debate on why a commercially available system has yet to be made available despite almost 30 years of intensive research.

Image-guided breast biopsy and localisation: recommendations for information to women and referring physicians by the European Society of Breast Imaging

Abstract: We summarise here the information to be provided to women and referring physicians about percutaneous breast biopsy and lesion localisation under imaging guidance. After explaining why a preoperative diagnosis with a percutaneous biopsy is preferred to surgical biopsy, we illustrate the criteria used by radiologists for choosing the most appropriate combination of device type for sampling and imaging technique for guidance. Then, we describe the commonly used devices, from fine-needle sampling to tissue biopsy with larger needles, namely core needle biopsy and vacuum-assisted biopsy, and how mammography, digital breast tomosynthesis, ultrasound, or magnetic resonance imaging work for targeting the lesion for sampling or localisation. The differences among the techniques available for localisation (carbon marking, metallic wire, radiotracer injection, radioactive seed, and magnetic seed localisation) are illustrated. Type and rate of possible complications are described and the issue of concomitant antiplatelet or anticoagulant therapy is also addressed. The importance of pathological-radiological correlation is highlighted: when evaluating the results of any needle sampling, the radiologist must check the concordance between the cytology/pathology report of the sample and the radiological appearance of the biopsied lesion. We recommend that special attention is paid to a proper and tactful approach when communicating to the woman the need for tissue sampling as well as the possibility of cancer diagnosis, repeat tissue sampling, and or even surgery when tissue sampling shows a lesion with uncertain malignant potential (also referred to as “high-risk” or B3 lesions). Finally, seven frequently asked questions are answered.

Non-invasive Biomarkers for Early Detection of Breast Cancer

Abstract: Breast cancer is the most common cancer in women worldwide. Accurate early diagnosis of breast cancer is critical in the management of the disease. Although mammogram screening has been widely used for breast cancer screening, high false-positive and false-negative rates and radiation from mammography have always been a concern. Over the last 20 years, the emergence of "omics" strategies has resulted in significant advances in the search for non-invasive biomarkers for breast cancer diagnosis at an early stage. Circulating carcinoma antigens, circulating tumor cells, circulating cell-free tumor nucleic acids (DNA or RNA), circulating microRNAs, and circulating extracellular vesicles in the peripheral blood, nipple aspirate fluid, sweat, urine, and tears, as well as volatile organic compounds in the breath, have emerged as potential non-invasive diagnostic biomarkers to supplement current clinical approaches to earlier detection of breast cancer. In this review, we summarize the current progress of research in these areas.

A review of various modalities in breast imaging: technical aspects and clinical outcomes

Abstract: Nowadays, breast cancer is the second cause of death after cardiovascular diseases. In general, about one out of eight women (about 12%) suffer from this disease during their life in the USA and European countries. If breast cancer is detected at an early stage, its survival rate will be very high. Several methods have been introduced to diagnose breast cancer with their clinical advantages and disadvantages. In this review, various methods of breast imaging have been introduced. Furthermore, the sensitivity and specificity of each of these methods have been investigated. For each of the imaging methods, articles that were relevant to the past 10 years were selected through electronic search engines, and then the most relevant papers were selected. Finally, about 40 articles were studied and their results were categorized and presented in the form of a report as follows. Various breast cancer imaging techniques were extracted as follows: mammography, contrast-enhanced mammography, digital tomosynthesis, sonography, sonoelastography, magnetic resonance imaging, magnetic elastography, diffusion-weighted imaging, magnetic spectroscopy, nuclear medicine, optical imaging, and microwave imaging. The choice of these methods depends on the patient’s state and stage, the age of the individual and the density of the breast tissue. Hybrid imaging techniques appear to be an acceptable way to improve detection of breast cancer. This review article can be useful in choosing the right method for imaging in people suspected of breast cancer.

Diagnosis of Breast Cancer Based on Modern Mammography using Hybrid Transfer Learning

Abstract: Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning process to detect breast cancer. Modified VGG (MVGG), residual network, mobile network is proposed and implemented in this paper. DDSM dataset is used in this paper. Experimental results show that our proposed hybrid transfers learning model (Fusion of MVGG16 and ImageNet) provides an accuracy of 88.3% where the number of epoch is 15. On the other hand, only modified VGG 16 architecture (MVGG 16) provides an accuracy 80.8% and MobileNet provides an accuracy of 77.2%. So, it is clearly stated that the proposed hybrid pre-trained network outperforms well compared to single architecture. This architecture can be considered as an effective tool for the radiologists in order to reduce the false negative and false positive rate. Therefore, the efficiency of mammography analysis will be improved.

Worldwide Review and Meta-Analysis of Cohort Studies Measuring the Effect of Mammography Screening Programmes on Incidence-Based Breast Cancer Mortality.

Abstract: In 2012, the Euroscreen project published a review of incidence-based mortality evaluations of breast cancer screening programmes. In this paper, we update this review to October 2019 and expand its scope from Europe to worldwide. We carried out a systematic review of incidence-based mortality studies of breast cancer screening programmes, and a meta-analysis of the estimated effects of both invitation to screening and attendance at screening, with adjustment for self-selection bias, on incidence-based mortality from breast cancer. We found 27 valid studies. The results of the meta-analysis showed a significant 22% reduction in breast cancer mortality with invitation to screening, with a relative risk of 0.78 (95% CI 0.75-0.82), and a significant 33% reduction with actual attendance at screening (RR 0.67, 95% CI 0.61-0.75). Breast cancer screening in the routine healthcare setting continues to confer a substantial reduction in mortality from breast cancer.

Multiple microRNAs as biomarkers for early breast cancer diagnosis

Abstract: MicroRNA (miRNA or miR) is stably present in plasma. It has been reported that miRNA could be used for detecting cancer. Circulating miRNAs are being increasingly recognized as powerful biomarkers in a number of different pathologies, including in breast cancer. The aim of the current study was to establish and validate miRNA sets that are useful for the early diagnosis of breast cancer. Specifically, the current study intended to determine whether miRNA biomarkers were tumor-specific and to statistically verify whether circulating miRNA analysis could be used for breast cancer diagnosis. In the present study, a total of nine candidate miRNA biomarkers were selected by examining reference miRNAs associated with the generation and progression of breast cancer to identify novel miRNAs that could be used to detect early breast cancer. A total of 226 plasma samples from patients with breast cancer were used. In addition, 146 plasma healthy samples were used as non-cancer controls. These samples were divided into training and validation cohorts. The training cohort was used to identify a combination of miRNA that could detect breast cancer. The validation cohort was used to validate this combination of miRNA. Total RNAs were isolated from collected samples. A total of 9 miRNAs were quantified using reverse-transcription quantitative PCR. A total of nine candidate miRNA expression levels were compared between patients with breast cancer and healthy controls. It was indicated that combinations of two or more of the nine miRNAs could detect breast cancer with higher accuracy than the use of a single biomarker. As a representative example, combinations of four miRNAs (miR-1246+miR-206+miR-24+miR-373) of the nine miRNAs had a sensitivity of 98%, a specificity of 96% and an accuracy of 97% for breast cancer detection in the validation cohort. The results of the present study suggest that multiple miRNAs could be used as potential biomarkers for early diagnosis of breast cancer. These biomarkers are expected to overcome limitations of mammography when used as an auxiliary diagnosis of mammography.

Hybridized neural network and decision tree based classifier for prognostic decision making in breast cancers

Abstract: Artificial intelligence techniques and algorithms are applied at various fields such as face recognition, self-driving cars, industrial robots and health care. These real-world conundrums are solved employing artificial intelligence since it focuses on narrow tasks, and AI-driven tasks are very reliable and efficient because of its automated problem-solving techniques. Breast cancer is considered as the most common type of cancer among women. The well-known technique for detection of breast cancer is mammography which can diagnosis anomalies and determine cancerous cells. However, in the present breast cancer screenings, the retrospective studies reveal that approximately 20–40% of breast cancer cases are missed by radiologists. The main objective of the proposed algorithm is to exactly forecast the misclassified malignant cancers employing radial basis function network and decision tree. In order to obtain the effective classification algorithm, this work is compared with three widely employed algorithms, namely K-nearest neighbors, support vector machine and Naive Bayes algorithm, and the proposed algorithm achieves a high accuracy.

Performance of Breast Cancer Risk-Assessment Models in a Large Mammography Cohort.

Abstract: Background Several breast cancer risk-assessment models exist. Few studies have evaluated predictive accuracy of multiple models in large screening populations. Methods We evaluated the performance of the BRCAPRO, Gail, Claus, Breast Cancer Surveillance Consortium (BCSC), and Tyrer-Cuzick models in predicting risk of breast cancer over 6 years among 35 921 women aged 40-84 years who underwent mammography screening at Newton-Wellesley Hospital from 2007 to 2009. We assessed model discrimination using the area under the receiver operating characteristic curve (AUC) and assessed calibration by comparing the ratio of observed-to-expected (O/E) cases. We calculated the square root of the Brier score and positive and negative predictive values of each model. Results Our results confirmed the good calibration and comparable moderate discrimination of the BRCAPRO, Gail, Tyrer-Cuzick, and BCSC models. The Gail model had slightly better O/E ratio and AUC (O/E = 0.98, 95% confidence interval [CI] = 0.91 to 1.06, AUC = 0.64, 95% CI = 0.61 to 0.65) compared with BRCAPRO (O/E = 0.94, 95% CI = 0.88 to 1.02, AUC = 0.61, 95% CI = 0.59 to 0.63) and Tyrer-Cuzick (version 8, O/E = 0.84, 95% CI = 0.79 to 0.91, AUC = 0.62, 95% 0.60 to 0.64) in the full study population, and the BCSC model had the highest AUC among women with available breast density information (O/E = 0.97, 95% CI = 0.89 to 1.05, AUC = 0.64, 95% CI = 0.62 to 0.66). All models had poorer predictive accuracy for human epidermal growth factor receptor 2 positive and triple-negative breast cancers than hormone receptor positive human epidermal growth factor receptor 2 negative breast cancers. Conclusions In a large cohort of patients undergoing mammography screening, existing risk prediction models had similar, moderate predictive accuracy and good calibration overall. Models that incorporate additional genetic and nongenetic risk factors and estimate risk of tumor subtypes may further improve breast cancer risk prediction.

Computer-Aided Histopathological Image Analysis Techniques for Automated Nuclear Atypia Scoring of Breast Cancer: a Review

Abstract: Breast cancer is the most common type of malignancy diagnosed in women. Through early detection and diagnosis, there is a great chance of recovery and thereby reduce the mortality rate. Many preliminary tests like non-invasive radiological diagnosis using ultrasound, mammography, and MRI are widely used for the diagnosis of breast cancer. However, histopathological analysis of breast biopsy specimen is inevitable and is considered to be the golden standard for the affirmation of cancer. With the advancements in the digital computing capabilities, memory capacity, and imaging modalities, the development of computer-aided powerful analytical techniques for histopathological data has increased dramatically. These automated techniques help to alleviate the laborious work of the pathologist and to improve the reproducibility and reliability of the interpretation. This paper reviews and summarizes digital image computational algorithms applied on histopathological breast cancer images for nuclear atypia scoring and explores the future possibilities. The algorithms for nuclear pleomorphism scoring of breast cancer can be widely grouped into two categories: handcrafted feature-based and learned feature-based. Handcrafted feature-based algorithms mainly include the computational steps like pre-processing the images, segmenting the nuclei, extracting unique features, feature selection, and machine learning–based classification. However, most of the recent algorithms are based on learned features, that extract high-level abstractions directly from the histopathological images utilizing deep learning techniques. In this paper, we discuss the various algorithms applied for the nuclear pleomorphism scoring of breast cancer, discourse the challenges to be dealt with, and outline the importance of benchmark datasets. A comparative analysis of some prominent works on breast cancer nuclear atypia scoring is done using a benchmark dataset which enables to quantitatively measure and compare the different features and algorithms used for breast cancer grading. Results show that improvements are still required, to have an automated cancer grading system suitable for clinical applications.

Current Status of Circulating Tumor Cells, Circulating Tumor DNA, and Exosomes in Breast Cancer Liquid Biopsies.

Abstract: Breast cancer is the most common cancer among women worldwide. Although the five-, ten- and fifteen-year survival rates are good for breast cancer patients diagnosed with early-stage disease, some cancers recur many years after completion of primary therapy. Tumor heterogeneity and clonal evolution may lead to distant metastasis and therapy resistance, which are the main causes of breast cancer-associated deaths. In the clinic today, imaging techniques like mammography and tissue biopsies are used to diagnose breast cancer. Even though these methods are important in primary diagnosis, they have limitations when it comes to longitudinal monitoring of residual disease after treatment, disease progression, therapy responses, and disease recurrence. Over the last few years, there has been an increasing interest in the diagnostic, prognostic, and predictive potential of circulating cancer-derived material acquired through liquid biopsies in breast cancer. Thanks to the development of sensitive devices and platforms, a variety of tumor-derived material, including circulating cancer cells (CTCs), circulating DNA (ctDNA), and biomolecules encapsulated in extracellular vesicles, can now be extracted and analyzed from body fluids. Here we will review the most recent studies on breast cancer, demonstrating the clinical potential and utility of CTCs and ctDNA. We will also review literature illustrating the potential of circulating exosomal RNA and proteins as future biomarkers in breast cancer. Finally, we will discuss some of the advantages and limitations of liquid biopsies and the future perspectives of this field in breast cancer management.

Improving Breast Cancer Detection Accuracy of Mammography with the Concurrent Use of an Artificial Intelligence Tool

Abstract: A multireader, multicase retrospective study demonstrated that the use of an artificial intelligence–based tool significantly improved the average area under the receiving operating characteristic ...

Comparison of Breast MRI Tumor Classification Using Human-Engineered Radiomics, Transfer Learning From Deep Convolutional Neural Networks, and Fusion Method

Abstract: Digital image-based signatures of breast tumors may ultimately contribute to the design of patient-specific breast cancer diagnostics and treatments. Beyond traditional human-engineered computer vision methods, tumor classification methods using transfer learning from deep convolutional neural networks (CNNs) are actively under development. This article will first discuss our progress in using CNN-based transfer learning to characterize breast tumors for various diagnostic, prognostic, or predictive image-based tasks across multiple imaging modalities, including mammography, digital breast tomosynthesis, ultrasound (US), and magnetic resonance imaging (MRI), compared to both human-engineered feature-based radiomics and fusion classifiers created through combination of such features. Second, a new study is presented that reports on a comprehensive comparison of the classification performances of features derived from human-engineered radiomic features, CNN transfer learning, and fusion classifiers for breast lesions imaged with MRI. These studies demonstrate the utility of transfer learning for computer-aided diagnosis and highlight the synergistic improvement in classification performance using fusion classifiers.

Lockdown of Breast Cancer Screening for COVID-19: Possible Scenario.

Abstract: Background/aim Coronavirus disease is spreading worldwide. Due to fast transmission and high fatality rate drastic emergency restrictions were issued. During the lockdown, only urgent medical services are guaranteed. All non-urgent services, as breast cancer (BC) screening, are temporarily suspended. The potential of breast cancer screening programs in increasing the survival rate and decreasing the mortality rate has been widely confirmed. Suspension could lead to worse outcomes for breast cancer patients. Our study aimed to analyse the data and provide estimates regarding the temporary BC screening suspension. Patients and methods Data regarding breast cancer and respective screening programs were achieved through literature research and analysis. Results Considering three different scenarios with respect to the lockdown's impact on breast cancer screening, we estimate that approximately 10,000 patients could have a missed diagnosis during these 3 months. Considering a 6-month period, as suggested by the Imperial college model, the number of patients who will not receive a diagnosis will rise to 16,000. Conclusion Breast cancer screening should be resumed as soon as possible in order to avoid further breast cancer missed diagnosis and reduce the impact of delayed diagnosis.

Automated Breast Cancer Detection in Digital Mammograms of Various Densities via Deep Learning.

Abstract: Mammography plays an important role in screening breast cancer among females, and artificial intelligence has enabled the automated detection of diseases on medical images. This study aimed to develop a deep learning model detecting breast cancer in digital mammograms of various densities and to evaluate the model performance compared to previous studies. From 1501 subjects who underwent digital mammography between February 2007 and May 2015, craniocaudal and mediolateral view mammograms were included and concatenated for each breast, ultimately producing 3002 merged images. Two convolutional neural networks were trained to detect any malignant lesion on the merged images. The performances were tested using 301 merged images from 284 subjects and compared to a meta-analysis including 12 previous deep learning studies. The mean area under the receiver-operating characteristic curve (AUC) for detecting breast cancer in each merged mammogram was 0.952 ± 0.005 by DenseNet-169 and 0.954 ± 0.020 by EfficientNet-B5, respectively. The performance for malignancy detection decreased as breast density increased (density A, mean AUC = 0.984 vs. density D, mean AUC = 0.902 by DenseNet-169). When patients’ age was used as a covariate for malignancy detection, the performance showed little change (mean AUC, 0.953 ± 0.005). The mean sensitivity and specificity of the DenseNet-169 (87 and 88%, respectively) surpassed the mean values (81 and 82%, respectively) obtained in a meta-analysis. Deep learning would work efficiently in screening breast cancer in digital mammograms of various densities, which could be maximized in breasts with lower parenchyma density.

Cancer Yield and Patterns of Follow-up for BI-RADS Category 3 after Screening Mammography Recall in the National Mammography Database.

Abstract: Of 43 628 women, 810 (1.86%) given Breast Imaging Reporting and Data System category 3 assessment after screening mammography recall were diagnosed with malignancy, with 468 of 810 malignancies (57...

A Multi-million Mammography Image Dataset and Population-Based Screening Cohort for the Training and Evaluation of Deep Neural Networks—the Cohort of Screen-Aged Women (CSAW)

Abstract: For AI researchers, access to a large and well-curated dataset is crucial. Working in the field of breast radiology, our aim was to develop a high-quality platform that can be used for evaluation of networks aiming to predict breast cancer risk, estimate mammographic sensitivity, and detect tumors. Our dataset, Cohort of Screen-Aged Women (CSAW), is a population-based cohort of all women 40 to 74 years of age invited to screening in the Stockholm region, Sweden, between 2008 and 2015. All women were invited to mammography screening every 18 to 24 months free of charge. Images were collected from the PACS of the three breast centers that completely cover the region. DICOM metadata were collected together with the images. Screening decisions and clinical outcome data were collected by linkage to the regional cancer center registers. Incident cancer cases, from one center, were pixel-level annotated by a radiologist. A separate subset for efficient evaluation of external networks was defined for the uptake area of one center. The collection and use of the dataset for the purpose of AI research has been approved by the Ethical Review Board. CSAW included 499,807 women invited to screening between 2008 and 2015 with a total of 1,182,733 completed screening examinations. Around 2 million mammography images have currently been collected, including all images for women who developed breast cancer. There were 10,582 women diagnosed with breast cancer; for 8463, it was their first breast cancer. Clinical data include biopsy-verified breast cancer diagnoses, histological origin, tumor size, lymph node status, Elston grade, and receptor status. One thousand eight hundred ninety-one images of 898 women had tumors pixel level annotated including any tumor signs in the prior negative screening mammogram. Our dataset has already been used for evaluation by several research groups. We have defined a high-volume platform for training and evaluation of deep neural networks in the domain of mammographic imaging.

Interval and Consecutive Round Breast Cancer after Digital Breast Tomosynthesis and Synthetic 2D Mammography versus Standard 2D Digital Mammography in BreastScreen Norway

Abstract: Background Screening that includes digital breast tomosynthesis (DBT) with two-dimensional (2D) synthetic mammography (SM) or standard 2D digital mammography (DM) results in detection of more breast cancers than does screening with DM alone. A decrease in interval breast cancer rates is anticipated but is not reported. Purpose To compare rates and characteristics of (a) interval breast cancer in women screened with DBT and SM versus those screened with DM alone and (b) screen-detected breast cancer at consecutive screenings with DM. Materials and Methods This prospective cohort study from BreastScreen Norway included women screened with DBT and SM (study group) or DM alone (control group) between February 2014 and December 2015 (baseline). All women, except nonattendees, women with breast cancer, and those who exceeded the upper age limit, were consecutively screened with DM after 2 years. Interval breast cancer, sensitivity, and specificity were estimated for women screened at baseline. Recall, screen-detected breast cancer, and positive predictive value were analyzed for consecutively screened women. A χ2 test, t test (P < .001 after Bonferroni correction indicated a significant difference), and binomial regression model were used to analyze differences across groups. Results A total of 92 404 women who underwent baseline screening (mean age, 59 years ± 6 [standard deviation]) were evaluated; 34 641 women in the study group (mean age, 59 years ± 6) were screened with DBT and SM and 57 763 women in the control group (mean age, 59 years ± 6) were screened with DM. A total of 26 474 women in the study group (mean age, 60 years ± 5) and 45 543 women in the control group (mean age, 60 years ± 5) were consecutively screened with DM. Rates of interval breast cancer were 2.0 per 1000 screened women in the study group and 1.5 per 1000 screened women in the control group (P = .12). No differences in histopathologic characteristics of interval breast cancer were observed. In the consecutive screening round, rates of screen-detected breast cancer were 3.9 per 1000 screened women (study group) and 5.6 per 1000 screened women (control group) (P = .001). Rates of histologic grade 1 invasive cancer were 0.5 per 1000 screened women (study group) and 1.3 per 1000 screened women (control group) (P = .001). Conclusion No differences in interval breast cancer rates or tumor characteristics were observed in women screened with DBT and SM compared with women screened with DM. Higher rates of low-grade screen-detected tumors were observed in the control group at consecutive screening. © RSNA, 2019 Online supplemental material is available for this article.