Bahcesehir long-term population-based screening compared to National Breast Cancer Registry Data: effectiveness of screening in an emerging country

Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program

OBJECTIVES

We aimed to evaluate the early-detection capabilities of AI in a screening program over its duration, with a specific focus on the detection of interval cancers, the early detection of cancers with the assistance of AI from prior visits, and its impact on workload for various reading scenarios.

MATERIALS AND METHODS

The study included 22,621 mammograms of 8825 women within a 10-year biennial two-reader screening program. The statistical analysis focused on 5136 mammograms from 4282 women due to data retrieval issues, among whom 105 were diagnosed with breast cancer. The AI software assigned scores from 1 to 100. Histopathology results determined the ground truth, and Youden's index was used to establish a threshold. Tumor characteristics were analyzed with ANOVA and chi-squared test, and different workflow scenarios were evaluated using bootstrapping.

RESULTS

The AI software achieved an AUC of 89.6% (86.1-93.2%, 95% CI). The optimal threshold was 30.44, yielding 72.38% sensitivity and 92.86% specificity. Initially, AI identified 57 screening-detected cancers (83.82%), 15 interval cancers (51.72%), and 4 missed cancers (50%). AI as a second reader could have led to earlier diagnosis in 24 patients (average 29.92 ± 19.67 months earlier). No significant differences were found in cancer-characteristics groups. A hybrid triage workflow scenario showed a potential 69.5% reduction in workload and a 30.5% increase in accuracy.

CONCLUSION

This AI system exhibits high sensitivity and specificity in screening mammograms, effectively identifying interval and missed cancers and identifying 23% of cancers earlier in prior mammograms. Adopting AI as a triage mechanism has the potential to reduce workload by nearly 70%.

CLINICAL RELEVANCE STATEMENT

The study proposes a more efficient method for screening programs, both in terms of workload and accuracy.

KEY POINTS

• Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers. • AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage. • AI has the potential to facilitate early diagnosis compared to human reading.

High-value breast cancer care within resource limitations

Breast cancer care is a costly global health issue where effective management depends on early detection and treatment. A breast cancer diagnosis can result in financial catastrophe especially in low- and middle-income countries (LMIC). Large inequities in breast cancer care are observed and represent a global challenge to caregivers and patients. Strategies to improve early diagnosis include awareness and clinical breast examination in LMIC, and screening in high-income countries (HIC). The use of clinical guidelines for the management of breast cancer is needed. Adapted guidelines from HIC can address disparities in populations with limited resources. Locally developed strategies still provide effective guidance in improving survival. Integrated practice units (IPU) with timely multidisciplinary breast care conferences and patient navigators are required to achieve high-value, personalized breast cancer management in HIC as well as LMIC. Breast cancer patient care should include a quality of life evaluation using ideally patient-reported outcomes (PROM) and experience measurements (PREM). Evaluation of breast cancer outcomes must include the financial cost of delivered care. The resulting value perspective should guide resource allocation and program priorities. The value of care must be improved by translating the findings of social and economic research into practice and resolving systemic inequity in clinical breast cancer research. Cancer survivorship programs must be put in place everywhere. The treatment of patients with metastatic breast cancer must require more attention in the future, especially in LMIC.

The efficacy of artificial intelligence (AI) in detecting interval cancers in the national screening program of a middle-income country

AIM

We aimed to investigate the efficiency and accuracy of an artificial intelligence (AI) algorithm for detecting interval cancers in a middle-income country's national screening program.

MATERIAL AND METHODS

A total of 2,129,486 mammograms reported as BIRADS 1 and 2 were matched with the national cancer registry for interval cancers (IC). The IC group consisted of 442 cases, of which 36 were excluded due to having mammograms incompatible with the AI system. A control group of 446 women with two negative consequent mammograms was defined as time-proven normal and constituted the normal group. The cancer risk scores of both groups were determined from 1 to 10 with the AI system. The sensitivity and specificity values of the AI system were defined in terms of IC detection. The IC group was divided into subgroups with six-month intervals according to their time from screening to diagnosis: 0-6 months, 6-12 months, 12-18 months, and 18-24 months. The diagnostic performance of the AI system for all patients was evaluated using receiver operating characteristics (ROC) curve analysis. The diagnostic performance of the AI system for major and minor findings that expert readers determined was re-evaluated.

RESULTS

AI labeled 53% of ICs with the highest score of 10. The sensitivity of AI in detecting ICs was 53.7% and 38.5% at specificities of 90% and 95%, respectively. Area under the curve (AUC) of AI in detecting major signs was 0.93 (95% CI: 0.90-0.95) with a sensitivity of 81.6% and 72.4% at specificities of 90% and 95%, respectively (95% CI: 0.73-0.88 and 95% CI: 0.60-0.82 respectively) and minor signs was 0.87 (95% CI: 0.87-0.92) with a sensitivity of 70% and 53% at a specificity of 90% and 95%, respectively (95% CI: 0.65-0.82 and 95% CI: 0.52-0.71 respectively). In subgroup analysis for time to diagnosis, the AUC value of the AI system was higher in the 0-6 month period than in later periods.

CONCLUSION

This study showed the potential of AI in detecting ICs in initial mammograms and reducing human errors and undetected cancers.

Identify risk factors affecting participation of Turkish women in mammography screening for breast cancer prevention

PURPOSE

Cancer screening is a public health intervention aiming to reduce cancer-caused deaths. This study aims to determine the factors affecting the mammography screening time among women aged 40-69.

METHODS

The micro dataset obtained from the Türkiye Health Survey conducted by the Turkish Statistical Institute (TurkStat) in 2019 and 2022 was used in the present study. Stereotype logistic regression was used to determine the variables affecting mammography screening and period for breast cancer prevention in women in Türkiye.

RESULTS

Given the results achieved from the analysis, it was found that factors such as age, marital status, general health condition, comorbidity, receiving psychosocial support, high blood lipid levels, and performing breast self-examinations affected women's adherence to cancer screening programs.

CONCLUSION

Since adherence to mammography increases with age, it is recommended to pay importance to education for women approaching the age of mammography screening. Educated individuals are expected to have access to multiple sources of information as to cancer and to access this information more easily. In order to gain more insight into the recommended preventive measures and outcomes related to cancer, it is suggested to review policies, which will increase the educational level of women, and provide privileges in the field of education.

Dynamic contrast-enhanced mammography and breast MRI in the diagnosis of breast cancer and detection of tumor size

Background/aim

The aim of this study is to evaluate the performance of contrast-enhanced mammography (CEM) and dynamic breast MRI techniques for diagnosing breast lesions, assess the diagnostic accuracy of CEM's using histopathological findings, and compare lesion size measurements obtained from both methods with pathological size.

Materials and methods

This prospective study included 120 lesions, of which 70 were malignant, in 104 patients who underwent CEM and MRI within a week. Two radiologists independently evaluated the MR and CEM images in separate sessions, using the BI-RADS classification system. Additionally, the maximum sizes of lesion were measured. Diagnostic accuracy parameters and the receiver operating characteristics (ROC) curves were constructed for the two modalities. The correlation between the maximum diameter of breast lesions observed in MRI, CEM, and pathology was analyzed.

Results

The overall diagnostic values for MRI were as follows: sensitivity 97.1%, specificity 60%, positive predictive value (PPV) 77.3%, negative predictive value (NPV) 93.8%, and accuracy 81.7%. Correspondingly, for CEM, the sensitivity, accuracy, specificity, PPV, and NPV were 97.14%, 81.67%, 60%, 77.27%, and 93.75%, respectively. The ROC analysis of CEM revealed an area under the curve (AUC) of 0.907 for observer 1 and 0.857 for observer 2, whereas MRI exhibited an AUC of 0.910 for observer 1 and 0.914 for observer 2. Notably, CEM showed the highest correlation with pathological lesion size (r = 0.660 for observer 1 and r = 0.693 for observer 2, p < 0.001 for both).

Conclusion

CEM can be used with high sensitivity and similar diagnostic performance comparable to MRI for diagnosing breast cancer. CEM proves to be a successful diagnostic method for precisely determining tumor size.

Diagnosis Rates Through Cancer Screening Programs in Patients with Breast Carcinoma

AIM

This study investigated whether breast cancer patients had ever applied for Cancer Early Diagnosis Screening and Training Centers (KETEM).

METHOD

This study, conducted from November 2020 to April 2021, adopts a cross-sectional research design and is planned as a survey study. The "Diagnosis Rates with Screening Programs in Breast Cancer Patients" survey was conducted on women over 45 who were diagnosed with breast cancer in the Medical Oncology Clinic of İzmir Katip Çelebi University Atatürk Education and Research Hospital. Further information about the cancer stage was gathered from the Medical Oncology outpatient clinic file records. Data obtained in the study were evaluated using the the Statistical Package for Social Sciences version 26.0 software (IBM Corp.; Armonk, NY, USA), using the number, percentage distribution, arithmetic mean, and chi-square test methods.

RESULTS

It has been determined that most patients diagnosed did not receive a diagnosis through screening programs, were not aware of KETEM, and did not apply to KETEM. A positive relationship was found between the level of education and participation in screening programs. It was observed that women who knew about the KETEM's participated more often in the scans.

CONCLUSION

The study discovered a lack of knowledge and inadequacy in screening programs for patients with breast cancer. We believe that it is essential to introduce and disseminate KETEMs so that cancers can be detected early through screening.

Cost-Effectiveness of Breast Cancer Early Detection Program in Low- and Middle-Income Countries: A Systematic Review

OBJECTIVES

This review explores the cost-effectiveness of the strategies used in the breast cancer early detection programs of low- to middle-income countries.

METHODS

A systematic review was performed to identify related studies, published up to August 2021, on PubMed, Cochrane, ProQuest, and the Cumulative Index to Nursing and Allied Health Literature. The Cochrane Handbook and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol were referenced during the reporting process. The Consolidated Health Economic Evaluation Reporting Standards 2022 criteria were used to assess the requirements of the selected studies. Articles with original data and full texts were included in the review. Non-low- to middle-income countries and non-English articles were excluded.

RESULTS

This review identified 12 suitable studies, wherein 6 investigated the cost-effectiveness of clinical breast examinations (CBEs), whereas 10 looked into mammogram (MMG) with or without CBE. In 2 studies, the cost-effectiveness of raising awareness through mass media and the use of ultrasounds combined with CBE were investigated. Although cost-effective, MMG incurs greater costs and requires more skill to be performed. MMG screenings before the age of 40 years were not cost-effective. The limitations of this review include variability in the methodological approaches of its selected studies. Most of the chosen studies met the Consolidated Health Economic Evaluation Reporting Standards 2022 criteria.

CONCLUSIONS

This review shows that adopting an age- and risk-based MMG screening approach could be viable in countries with limited resources. Future cost-effectiveness analysis research should include a section on patient and stakeholder engagement with the study's results.