-
Life (Basel, Switzerland) Jun 2024Breast cancer is the most common malignancy diagnosed in the female population worldwide and the leading cause of death among perimenopausal women. Screening is... (Review)
Review
Breast cancer is the most common malignancy diagnosed in the female population worldwide and the leading cause of death among perimenopausal women. Screening is essential, since earlier detection in combination with improvements in breast cancer treatment can reduce the associated mortality. The aim of this study was to review and compare the recommendations from published guidelines on breast cancer screening. A total of 14 guidelines on breast cancer screening issued between 2014 and 2022 were identified. A descriptive review of relevant guidelines by the World Health Organization (WHO), the U.S. Preventive Services Task Force (USPSTF), the American Cancer Society (ACS), the National Comprehensive Cancer Network (NCCN), the American College of Obstetricians and Gynecologists (ACOG), the American Society of Breast Surgeons (ASBrS), the American College of Radiology (ACR), the Task Force on Preventive Health Care (CTFPHC), the European Commission Initiative on Breast Cancer (ECIBC), the European Society for Medical Oncology (ESMO), the Royal Australian College of General Practitioners (RACGP) and the Japanese Journal of Clinical Oncology (JJCO) for women both at average and high-risk was carried out. There is a consensus among all the reviewed guidelines that mammography is the gold standard screening modality for average-risk women. For this risk group, most of the guidelines suggest annual or biennial mammographic screening at 40-74 years, while screening should particularly focus at 50-69 years. Most of the guidelines suggest that the age limit to stop screening should be determined based on the women's health status and life expectancy. For women at high-risk, most guidelines recommend the use of annual mammography or magnetic resonance imaging, while the starting age should be earlier than the average-risk group, depending on the risk factor. There is discrepancy among the recommendations regarding the age at onset of screening in the various high-risk categories. The development of consistent international practice protocols for the most appropriate breast cancer screening programs seems of major importance to reduce mortality rates and safely guide everyday clinical practice.
PubMed: 38929759
DOI: 10.3390/life14060777 -
Diagnostics (Basel, Switzerland) Jun 2024The purposes of this study were to develop an artificial intelligence (AI) model for future breast cancer risk prediction based on mammographic images, investigate the...
The purposes of this study were to develop an artificial intelligence (AI) model for future breast cancer risk prediction based on mammographic images, investigate the feasibility of the AI model, and compare the AI model, clinical statistical risk models, and Mirai, a state of-the art deep learning algorithm based on screening mammograms for 1-5-year breast cancer risk prediction. We trained and developed a deep learning model using a total of 36,995 serial mammographic examinations from 21,438 women (cancer-enriched mammograms, 17.5%). To determine the feasibility of the AI prediction model, mammograms and detailed clinical information were collected. C-indices and area under the receiver operating characteristic curves (AUCs) for 1-5-year outcomes were obtained. We compared the AUCs of our AI prediction model, Mirai, and clinical statistical risk models, including the Tyrer-Cuzick (TC) model and Gail model, using DeLong's test. A total of 16,894 mammograms were independently collected for external validation, of which 4002 were followed by a cancer diagnosis within 5 years. Our AI prediction model obtained a C-index of 0.76, with AUCs of 0.90, 0.84, 0.81, 0.78, and 0.81, to predict the 1-5-year risks. Our AI prediction model showed significantly higher AUCs than those of the TC model (AUC: 0.57; < 0.001) and Gail model (AUC: 0.52; < 0.001), and achieved similar performance to Mirai. The deep learning AI model using mammograms and AI-powered imaging biomarkers has substantial potential to advance accurate breast cancer risk prediction.
PubMed: 38928628
DOI: 10.3390/diagnostics14121212 -
Biomedicines Jun 2024Breast cancer remains a leading cause of mortality among women, with molecular subtypes significantly influencing prognosis and treatment strategies. Currently,...
Breast cancer remains a leading cause of mortality among women, with molecular subtypes significantly influencing prognosis and treatment strategies. Currently, identifying the molecular subtype of cancer requires a biopsy-a specialized, expensive, and time-consuming procedure, often yielding to results that must be supported with additional biopsies due to technique errors or tumor heterogeneity. This study introduces a novel approach for predicting breast cancer molecular subtypes using mammography images and advanced artificial intelligence (AI) methodologies. Using the OPTIMAM imaging database, 1397 images from 660 patients were selected. The pretrained deep learning model ResNet-101 was employed to classify tumors into five subtypes: Luminal A, Luminal B1, Luminal B2, HER2, and Triple Negative. Various classification strategies were studied: binary classifications (one vs. all others, specific combinations) and multi-class classification (evaluating all subtypes simultaneously). To address imbalanced data, strategies like oversampling, undersampling, and data augmentation were explored. Performance was evaluated using accuracy and area under the receiver operating characteristic curve (AUC). Binary classification results showed a maximum average accuracy and AUC of 79.02% and 64.69%, respectively, while multi-class classification achieved an average AUC of 60.62% with oversampling and data augmentation. The most notable binary classification was HER2 vs. non-HER2, with an accuracy of 89.79% and an AUC of 73.31%. Binary classification for specific combinations of subtypes revealed an accuracy of 76.42% for HER2 vs. Luminal A and an AUC of 73.04% for HER2 vs. Luminal B1. These findings highlight the potential of mammography-based AI for non-invasive breast cancer subtype prediction, offering a promising alternative to biopsies and paving the way for personalized treatment plans.
PubMed: 38927578
DOI: 10.3390/biomedicines12061371 -
Journal of Cancer Education : the... Jun 2024Breast cancer remains a significant global concern, underscoring the critical need for early detection and prevention strategies. Primary and secondary preventive...
Breast Cancer Prevention Practices and Knowledge in Italian and Chinese Women in Italy: Clinical Checkups, Free NHS Screening Adherence, and Breast Self-Examination (BSE).
Breast cancer remains a significant global concern, underscoring the critical need for early detection and prevention strategies. Primary and secondary preventive measures, such as routine screenings and behaviors like breast self-examination (BSE), play a crucial role in facilitating early diagnosis. While the National Health System (NHS) in Italy offers free regular screenings for women aged 50-69, there is a lack of clarity regarding the participation of both Italian and Chinese women residing in Italy in these screening programs. This study aims to bridge this knowledge gap by thoroughly assessing the involvement in regular clinical check-ups and the types of screening employed, the adherence to free screenings offered by the NHS, and the practice of BSE among women aged 50-69 of these two groups. Furthermore, it investigates their knowledge and perceptions regarding breast cancer and BSE. Results reveal disparities in breast cancer control practice between Italian and Chinese women in Italy: the former demonstrates higher adherence to clinical checkups (53% vs. 3%, p < 0.001), while both groups show low participation in free NHS screenings (70% vs. 4%, p < 0.001). Additionally, Chinese women reported significantly lower frequency of mammography (96% vs. 33%, p < 0.001) and ultrasound (69% vs. 16%, p < 0.001). The frequency of BSE also differed substantially, with 47% of Chinese women never performing BSE compared to 12% of Italian women (p < 0.001). This comprehensive exploration provides valuable insights, attitudes, and knowledge into the disparities and potential areas for improvement in breast cancer prevention, thus contributing to the overall well-being of these communities. The findings highlight the necessity for educational initiatives aimed at improving awareness and participation in screenings, particularly among the Chinese population. These initiatives could have profound implications for patient education by equipping women with the knowledge and skills necessary to engage in proactive health behaviors.
PubMed: 38926291
DOI: 10.1007/s13187-024-02463-4 -
Tomography (Ann Arbor, Mich.) Jun 2024Computer-aided diagnosis systems play a crucial role in the diagnosis and early detection of breast cancer. However, most current methods focus primarily on the...
Computer-aided diagnosis systems play a crucial role in the diagnosis and early detection of breast cancer. However, most current methods focus primarily on the dual-view analysis of a single breast, thereby neglecting the potentially valuable information between bilateral mammograms. In this paper, we propose a Four-View Correlation and Contrastive Joint Learning Network (FV-Net) for the classification of bilateral mammogram images. Specifically, FV-Net focuses on extracting and matching features across the four views of bilateral mammograms while maximizing both their similarities and dissimilarities. Through the Cross-Mammogram Dual-Pathway Attention Module, feature matching between bilateral mammogram views is achieved, capturing the consistency and complementary features across mammograms and effectively reducing feature misalignment. In the reconstituted feature maps derived from bilateral mammograms, the Bilateral-Mammogram Contrastive Joint Learning module performs associative contrastive learning on positive and negative sample pairs within each local region. This aims to maximize the correlation between similar local features and enhance the differentiation between dissimilar features across the bilateral mammogram representations. Our experimental results on a test set comprising 20% of the combined Mini-DDSM and Vindr-mamo datasets, as well as on the INbreast dataset, show that our model exhibits superior performance in breast cancer classification compared to competing methods.
Topics: Humans; Breast Neoplasms; Mammography; Female; Radiographic Image Interpretation, Computer-Assisted; Breast; Diagnosis, Computer-Assisted; Machine Learning; Algorithms
PubMed: 38921942
DOI: 10.3390/tomography10060065 -
Journal of Imaging Jun 2024After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to...
BACKGROUND
After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to investigate whether a U-Net-based deep convolutional neural network (dCNN) may be used to detect surgical clips in follow-up mammograms after BCS.
METHODS
884 mammograms and 517 tomosynthetic images depicting surgical clips and calcifications were manually segmented and classified. A U-Net-based segmentation network was trained with 922 images and validated with 394 images. An external test dataset consisting of 39 images was annotated by two radiologists with up to 7 years of experience in breast imaging. The network's performance was compared to that of human readers using accuracy and interrater agreement (Cohen's Kappa).
RESULTS
The overall classification accuracy on the validation set after 45 epochs ranged between 88.2% and 92.6%, indicating that the model's performance is comparable to the decisions of a human reader. In 17.4% of cases, calcifications have been misclassified as post-operative clips. The interrater reliability of the model compared to the radiologists showed substantial agreement (κ = 0.72, κ = 0.78) while the readers compared to each other revealed a Cohen's Kappa of 0.84, thus showing near-perfect agreement.
CONCLUSIONS
With this study, we show that surgery clips can adequately be identified by an AI technique. A potential application of the proposed technique is patient triage as well as the automatic exclusion of post-operative cases from PGMI (Perfect, Good, Moderate, Inadequate) evaluation, thus improving the quality management workflow.
PubMed: 38921624
DOI: 10.3390/jimaging10060147 -
International Journal of Surgery... Jun 2024
PubMed: 38920323
DOI: 10.1097/JS9.0000000000001890 -
BMJ (Clinical Research Ed.) Jun 2024
Topics: Humans; Breast Neoplasms; Female; Early Detection of Cancer; United States; Adult; Mammography; Middle Aged; Mass Screening; Age Factors; Aged
PubMed: 38914429
DOI: 10.1136/bmj.q1353 -
Journal of Breast Imaging Jun 2024High mammographic density increases breast cancer risk and reduces mammographic sensitivity. We reviewed evidence on accuracy of supplemental MRI for women with dense...
BACKGROUND
High mammographic density increases breast cancer risk and reduces mammographic sensitivity. We reviewed evidence on accuracy of supplemental MRI for women with dense breasts at average or increased risk.
METHODS
PubMed and Embase were searched 1995-2022. Articles were included if women received breast MRI following 2D or tomosynthesis mammography. Risk of bias was assessed using QUADAS-2. Analysis used independent studies from the articles. Fixed-effect meta-analytic summaries were estimated for predefined groups (PROSPERO: 230277).
RESULTS
Eighteen primary research articles (24 studies) were identified in women aged 19-87 years. Breast density was heterogeneously or extremely dense (BI-RADS C/D) in 15/18 articles and extremely dense (BI-RADS D) in 3/18 articles. Twelve of 18 articles reported on increased-risk populations. Following 21 440 negative mammographic examinations, 288/320 cancers were detected by MRI. Substantial variation was observed between studies in MRI cancer detection rate, partly associated with prevalent vs incident MRI exams (prevalent: 16.6/1000 exams, 12 studies; incident: 6.8/1000 exams, 7 studies). MRI had high sensitivity for mammographically occult cancer (20 studies with at least 1-year follow-up). In 5/18 articles with sufficient data to estimate relative MRI detection rate, approximately 2 in 3 cancers were detected by MRI (66.3%, 95% CI, 56.3%-75.5%) but not mammography. Positive predictive value was higher for more recent studies. Risk of bias was low in most studies.
CONCLUSION
Supplemental breast MRI following negative mammography in women with dense breasts has breast cancer detection rates of ~16.6/1000 at prevalent and ~6.8/1000 at incident MRI exams, considering both high and average risk settings.
PubMed: 38912622
DOI: 10.1093/jbi/wbae019 -
The Indian Journal of Radiology &... Jul 2024Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely... (Review)
Review
Although abundant literature is currently available on the use of deep learning for breast cancer detection in mammography, the quality of such literature is widely variable. To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. The PubMed and Scopus databases were searched to identify records that described the use of deep learning to detect lesions or classify images into cancer or noncancer. A modification of Quality Assessment of Diagnostic Accuracy Studies (mQUADAS-2) tool was developed for this review and was applied to the included studies. Results of reported studies (area under curve [AUC] of receiver operator curve [ROC] curve, sensitivity, specificity) were recorded. A total of 12,123 records were screened, of which 107 fit the inclusion criteria. Training and test datasets, key idea behind model architecture, and results were recorded for these studies. Based on mQUADAS-2 assessment, 103 studies had high risk of bias due to nonrepresentative patient selection. Four studies were of adequate quality, of which three trained their own model, and one used a commercial network. Ensemble models were used in two of these. Common strategies used for model training included patch classifiers, image classification networks (ResNet in 67%), and object detection networks (RetinaNet in 67%). The highest reported AUC was 0.927 ± 0.008 on a screening dataset, while it reached 0.945 (0.919-0.968) on an enriched subset. Higher values of AUC (0.955) and specificity (98.5%) were reached when combined radiologist and Artificial Intelligence readings were used than either of them alone. None of the studies provided explainability beyond localization accuracy. None of the studies have studied interaction between AI and radiologist in a real world setting. While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.
PubMed: 38912238
DOI: 10.1055/s-0043-1775737