Self-detection and clinical breast examination: Comparison of the two “classical” physical examination methods for the diagnosis of breast cancer

Study on the classification of benign and malignant breast lesions using a multi-sequence breast MRI fusion radiomics and deep learning model

Purpose

To develop a multi-modal model combining multi-sequence breast MRI fusion radiomics and deep learning for the classification of benign and malignant breast lesions, to assist clinicians in better selecting treatment plans.

Methods

A total of 314 patients who underwent breast MRI examinations were included. They were randomly divided into training, validation, and test sets in a ratio of 7:1:2. Subsequently, features of T1-weighted images (T1WI), T2-weighted images (T2WI), and dynamic contrast-enhanced MRI (DCE-MRI) were extracted using the convolutional neural network ResNet50 for fusion, and then combined with radiomic features from the three sequences. The following models were established: T1 model, T2 model, DCE model, DCE_T1_T2 model, and DCE_T1_T2_rad model. The performance of the models was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The differences between the DCE_T1_T2_rad model and the other four models were compared using the Delong test, with a P-value < 0.05 considered statistically significant.

Results

The five models established in this study performed well, with AUC values of 0.53 for the T1 model, 0.62 for the T2 model, 0.79 for the DCE model, 0.94 for the DCE_T1_T2 model, and 0.98 for the DCE_T1_T2_rad model. The DCE_T1_T2_rad model showed statistically significant differences (P < 0.05) compared to the other four models.

Conclusion

The use of a multi-modal model combining multi-sequence breast MRI fusion radiomics and deep learning can effectively improve the diagnostic performance of breast lesion classification.

Clinical breast examination: A screening tool for lower- and middle-income countries

Breast cancer (BC) remains a global health challenge, devastatingly impacting women's lives. Low-and-middle-income countries (LMIC), such as India, experience a concerning upward trend in BC incidence, necessitating the implementation of cost-effective screening methods. While mammography, ultrasonography, and magnetic resonance imaging are preferred screening modalities in resource-rich settings, limited resources in LMICs make clinical breast examination (CBE) the method of choice. This review explores the merits of CBE, its coverage, barriers, and facilitators in the Indian context for developing strategies in resource-constrained settings. CBE has shown significant down-staging and cost-effectiveness. Performed by trained health workers in minutes, CBE offers an opportunity for education about BC. Various individual and health system barriers, such as stigma, financial constraints, and the absence of opportunistic screening hinder CBE coverage. Promising facilitators include awareness programs, capacity building, and integrating CBE through universal health care. No healthcare provider must miss any screening opportunity through CBE.

Radiomics and artificial intelligence analysis by T2-weighted imaging and dynamic contrast-enhanced magnetic resonance imaging to predict Breast Cancer Histological Outcome

OBJECTIVE

The objective of the study was to evaluate the accuracy of radiomics features obtained by MR images to predict Breast Cancer Histological Outcome.

METHODS

A total of 217 patients with malignant lesions were analysed underwent MRI examinations. Considering histological findings as the ground truth, four different types of findings were used in both univariate and multivariate analyses: (1) G1 + G2 vs G3 classification; (2) presence of human epidermal growth factor receptor 2 (HER2 + vs HER2 -); (3) presence of the hormone receptor (HR + vs HR -); and (4) presence of luminal subtypes of breast cancer.

RESULTS

The best accuracy for discriminating HER2 + versus HER2 - breast cancers was obtained considering nine predictors by early phase T1-weighted subtraction images and a decision tree (accuracy of 88% on validation set). The best accuracy for discriminating HR + versus HR - breast cancers was obtained considering nine predictors by T2-weighted subtraction images and a decision tree (accuracy of 90% on validation set). The best accuracy for discriminating G1 + G2 versus G3 breast cancers was obtained considering 16 predictors by early phase T1-weighted subtraction images in a linear regression model with an accuracy of 75%. The best accuracy for discriminating luminal versus non-luminal breast cancers was obtained considering 27 predictors by early phase T1-weighted subtraction images and a decision tree (accuracy of 94% on validation set).

CONCLUSIONS

The combination of radiomics analysis and artificial intelligence techniques could be used to support physician decision-making in prediction of Breast Cancer Histological Outcome.

The Efficacy of Clinical Breast Exams and Breast Self-Exams in Detecting Malignancy or Positive Ultrasound Findings

Objective

A breast exam is a low-risk, low-cost method for early detection, which is crucial for improved mortality. However, clinical breast exams (CBE) and breast self-exams (BSEs) remain controversial with unclear guidelines. This study analyzes the efficacy of these two exam types in evaluating palpable breast masses.

Methods

This retrospective cross-sectional study included 2019 medical records from Epic of women with breast lumps. Patient demographics, provider types, and breast exam types were recorded. Primary outcomes were detection of cancer and positive ultrasound finding. Fisher’s exact tests and two-sample t-tests determined the statistical significance of the association between the outcomes and categorical and continuous variables.

Results

Of 462 breast masses, 69 demonstrated positive ultrasound findings, with 26 of those yielding cancer; 96% of cancers and 81% of ultrasound findings resulted from patient-identified lumps. Of provider-identified lumps, 100% of cancers and 92.3% of positive ultrasound findings were diagnosed by MDs (doctors of medicine) rather than midlevel providers. There was no statistically significant difference in identifying cancer or positive ultrasound finding between CBEs and BSEs (p = 0.3709 and p = 0.1556).

Conclusion

Despite no difference between CBEs and BSEs in identifying cancer or positive ultrasound finding, 25 of the 26 breast cancers were initially detected by patients, while only one of 26 was detected by CBE. BSEs detect breast cancers. Although some guidelines encourage CBEs over self-exams, not all CBEs are equal.

Key message

There is no significant difference between CBEs and BSEs in identifying cancer or positive ultrasound finding. The majority of cancers were initially identified by patients. BSEs detect breast cancers and women should continue performing them. Not all CBEs are equal. CBEs by MDs, especially women health specialists, are generally more effective than those by midlevel providers.

Breast cancer, screening and diagnostic tools: All you need to know

Breast cancer is one of the most frequent malignancies among women worldwide. Methods for screening and diagnosis allow health care professionals to provide personalized treatments that improve the outcome and survival. Scientists and physicians are working side-by-side to develop evidence-based guidelines and equipment to detect cancer earlier. However, the lack of comprehensive interdisciplinary information and understanding between biomedical, medical, and technology professionals makes innovation of new screening and diagnosis tools difficult. This critical review gathers, for the first time, information concerning normal breast and cancer biology, established and emerging methods for screening and diagnosis, staging and grading, molecular and genetic biomarkers. Our purpose is to address key interdisciplinary information about these methods for physicians and scientists. Only the multidisciplinary interaction and communication between scientists, health care professionals, technical experts and patients will lead to the development of better detection tools and methods for an improved screening and early diagnosis.

Exploring the Influencing Factors on Breast Self-Examination Among Myanmar Women: A Qualitative Study

Introduction: Breast self-examination (BSE) is the most sensitive and cost-effective method to diagnose breast cancer at an early stage in healthcare resources’ limited setting. However, the practice of BSE is low in Myanmar. Although various international studies were conducted to clarify the influencing factors in irregular BSE practice, there is a range of different factors and the answer is not yet clear. Hence, this study is aimed to explore the influencing factors on the practice of breast self-examination among Myanmar women.Methods: A qualitative exploratory-descriptive study was conducted on eight women through in-depth semi-structured interviews between February 2020 and March 2020. The samples were women who lived in the rural area of Myanmar and purposive sampling technique was used. Data were analyzed using Colaizzi’s method, which consisted of seven stages.Results: Four themes emerged as the results of the in-depth interview, namely knowledge of breast cancer, knowledge regarding breast self-examination, barriers to performing regular BSE and ways to improve BSE practice.Conclusion: This study showed that the women were inadequate in knowledge and practice regarding BSE and breast cancer. Some barriers of BSE practice are rooted in the inadequate skill of BSE and the women’s attitude.  Greater understanding about breast cancer and improving the confidence of women in BSE will lead to better prognosis. Hence, healthcare authorities and providers should encourage a formal health education program and the results from this study hope to be useful in future rural health education programs of BSE practice.

Work Transitions in Breast Cancer Survivors and Effects on Quality of Life

Purpose Work transitions among breast cancer survivors remain an underexplored area. We aimed to examine prevalence and determinants of changes in work status, and the effect of these changes on quality of life of breast cancer survivors. Methods A cross-sectional study of 410 female breast cancer survivors randomly drawn from a larger study sample pool (n = 2644), members of "Leumit" healthcare fund, who were diagnosed with primary nonmetastatic invasive breast cancer in the years 2002-2012. The study questionnaire included questions on work characteristics and health-related quality-of-life and was completed by all women contacted. Work transition was defined as a downgrade (from full-time to part-time), termination, or retirement, and was contrasted to no change in work status (retention of full-time or part-time). Work transition was assessed at two intervals: between breast cancer diagnosis and treatment, and between breast cancer diagnosis and time of the survey. Results A total of 206 breast cancer survivors (50%) were employed prior to their diagnosis, of whom 12% stopped working, and 79% downgraded to part-time during treatment. At the time of survey (mean 8 ± 3 years post-diagnosis), 33% of those employed prior to their diagnosis stopped working or retired, 48% downgraded to part-time, and 19% had no change in their work situation. Work transition between diagnosis and time of the survey was significantly associated with poorer quality-of-life. In multivariable analyses, work transition between diagnosis and time of the survey was positively associated with being immigrant compared to native-born Israeli (odds ratio (OR) 4.65; 95% confidence interval (CI) 1.91-11.37; P = .001), and inversely with education level of college or over compared to high school or less (OR 0.27; 95% CI 0.09-0.86; P = .026). Conclusions Breast cancer survivors with characteristics pointing at underprivileged social circumstances more often experienced changes in work status after surviving breast cancer, irrespective of diagnosis, comorbidity or treatment. Breast cancer patients with immigrant status and/or lower educational attainment need more support to be able to keep their job.

The Advent of Salivary Breast Cancer Biomarker Detection Using Affinity Sensors

Breast Cancer is one of the world's most notorious diseases affecting two million women in 2018 worldwide. It is a highly heterogeneous disease, making it difficult to treat. However, its linear progression makes it a candidate for early screening programs, and the earlier its detection the higher the chance of recovery. However, one key hurdle for breast cancer screening is the fact that most screening techniques are expensive, time-consuming, and cumbersome, making them impractical for use in several parts of the world. One current trend in breast cancer detection has pointed to a possible solution, the use of salivary breast cancer biomarkers. Saliva is an attractive medium for diagnosis because it is readily available in large quantities, easy to obtain at low cost, and contains all the biomarkers present in blood, albeit in lower quantities. Affinity sensors are devices that detect molecules through their interactions with biological recognition molecules. Their low cost, high sensitivity, and selectivity, as well as rapid detection time make them an attractive alternative to traditional means of detection. In this review article, we discuss the current status of breast cancer diagnosis, its salivary biomarkers, as well as the current trends in the development of affinity sensors for their detection.

Targeting breast cancer outcomes-what about the primary relatives?

BACKGROUND

Up to 65% of newly diagnosed breast cancer patients had not been screened correctly before diagnosis resulting in increased stage of cancer at presentation. This study assessed whether their primary relatives are, in turn, assessed appropriately.

METHODS

An ethically approved prospective study involving 274 primary relatives of women diagnosed with breast cancer, between 2009-2012, at a symptomatic breast unit in Ireland. Telephone interview established: demographics, menstrual history, family history verification, breast screening history. Personal risk level was calculated and whether current screening met screening guidelines. Participants were enrolled into appropriate screening programs if currently not in one and results analyzed.

RESULTS

Two hundred and fifteen of the 280 (76.8%) newly diagnosed patients responded giving details of their 274 primary relatives; this made up the study cohort. Mean age 50 ± 10 (35-75). Thirty two percent were low risk, 64% moderate and 4% high. 190/274 (69%) were being screened appropriately. Seventy five relatives were then assessed with: mammography in 55, Mg and US in 16. Four underwent a biopsy and to date none had cancer. Surveillance was: annual screening in 48%; national screening program and General Practitioner (GP) in 33%; GP only in over 65s in 13%; 6% await further assessment at specialist genetics clinics where their surveillance will be decided.

CONCLUSIONS

This study has identified an opportunity to improve the delivery of appropriate screening to higher risk primary relatives of patients with breast cancer. This necessitates an integrated national approach involving providers of primary care, patients and screening breast programs.

Comparison of Direct and Indirect Methods of Teaching Breast Self-Examination – Influence on Knowledge and Attitudes of Iranian Nursing and Midwifery Personnel

Background:

Breast cancer is the most common cancer in women. Monthly breast self-examination (BSE) has been presented as one of the best screening methods available. The aim of this study was to compare effects of both direct and indirect methods of teaching of BSE on knowledge and attitudes of nursing and midwifery personnel.

Materials and Methods:

The present study was performed on 89 nursing and midwifery personnel in Valiasr hospital of Borujen city. Participants were randomly divided into a direct and an indirect training group. Researcher-designed BSE knowledge and attitude and demographic information questionnaires were used for data collection.

Results:

Before the education intervention, the mean levels of knowledge and attitude were 9.82±2.79 and 56.5±6.21 in the direct training group and 9.59±2.71 and 54.5±4.51 in the indirect training group; after the intervention, they reached 19.2±0.96 and 62.9±4.21, and 11.0±2.58 and 59.0±3.44, respectively. The difference in the mean levels of knowledge and attitude were significantly higher in the direct training group post intervention (P<0.05).

Conclusion:

It appears that educational planners and hospital personnel education officials should seek to teach aspects of crucial health behavior to female personnel using cooperative and direct training methods.

Prevalence and Risk Factors for Patient Delay Among Women With Breast Cancer in Rural India

Delay in seeking health care by women with breast cancer increases mortality risk. This study was conducted in rural India to identify risk factors associated with patient delay. A total of 212 women with primary breast cancer diagnosed between 2010 and 2012 were interviewed. Sociodemographic characteristics, time interval between seeking medical attention and appearance of symptoms, and reasons for delay were inquired. Patient delay was defined as more than 3 months between date of first symptoms and medical consultation. Logistic regression was applied to assess associations between potential risk factors and patient delay. Almost half the women with breast cancer experienced patient delay. Age more than 60 years (odds ratio = 4.9, 95% confidence interval = 1.3-18.0) was significantly associated with patient delay. Only 6.6% of patients had heard about breast self-examination. Significantly higher number of patients with delay presented with advanced clinical stage (P = .000). Health education programs should be introduced with specific strategies to shorten patient delay.