Effect of Digital Mammography for Breast Cancer Screening: A Comparative Study of More than 8 Million Korean Women

Improving mammography interpretation for both novice and experienced readers: a comparative study of two commercial artificial intelligence software

OBJECTIVES

To evaluate the improvement of mammography interpretation for novice and experienced radiologists assisted by two commercial AI software.

METHODS

We compared the performance of two AI software (AI-1 and AI-2) in two experienced and two novice readers for 200 mammographic examinations (80 cancer cases). Two reading sessions were conducted within 4 weeks. The readers rated the likelihood of malignancy (range, 1-7) and the percentage probability of malignancy (range, 0-100%), with and without AI assistance. Differences in AUROC, sensitivity, and specificity were analyzed.

RESULTS

Mean AUROC increased in both novice (0.86 to 0.90 with AI-1 [p = 0.005]; 0.91 with AI-2 [p < 0.001]) and experienced readers (0.87 to 0.92 with AI-1 [p < 0.001]; 0.90 with AI-2 [p = 0.004]). Sensitivities increased from 81.3 to 88.8% with AI-1 (p = 0.027) and to 91.3% with AI-2 (p = 0.005) in novice readers, and from 81.9 to 90.6% with AI-1 (p = 0.001) and to 87.5% with AI-2 (p = 0.016) in experienced readers. Specificity did not decrease significantly in both novice (p > 0.999, both) and experienced readers (p > 0.999 with AI-1 and 0.282 with AI-2). There was no significant difference in the performance change depending on the type of AI software (p > 0.999).

CONCLUSION

Commercial AI software improved the diagnostic performance of both novice and experienced readers. The type of AI software used did not significantly impact performance changes. Further validation with a larger number of cases and readers is needed.

CLINICAL RELEVANCE STATEMENT

Commercial AI software effectively aided mammography interpretation irrespective of the experience level of human readers.

KEY POINTS

• Mammography interpretation remains challenging and is subject to a wide range of interobserver variability. • In this multi-reader study, two commercial AI software improved the sensitivity of mammography interpretation by both novice and experienced readers. The type of AI software used did not significantly impact performance changes. • Commercial AI software may effectively support mammography interpretation irrespective of the experience level of human readers.

Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection

BACKGROUND

Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women.

METHODS

We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI's performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A-D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories.

RESULTS

Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7-77.3] vs. 67.1% [95% CI, 58.8-74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9-93.2] vs. 77.6% [95% CI, 61.7-77.9]), PPV (1.5% [95% CI, 1.2-1.9] vs. 0.5% [95% CI, 0.4-0.6]), recall rate (7.1% [95% CI, 6.9-7.2] vs. 22.5% [95% CI, 22.2-22.7]), and AUC values (0.8 [95% CI, 0.76-0.84] vs. 0.74 [95% CI, 0.7-0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category.

CONCLUSIONS

AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection Software for Automated Breast Ultrasound

RATIONALE AND OBJECTIVES

This study aimed to evaluate the diagnostic performance of radiologists following the utilization of artificial intelligence (AI)-based computer-aided detection software (CAD) in detecting suspicious lesions in automated breast ultrasounds (ABUS).

MATERIALS AND METHODS

ABUS-detected 262 breast lesions (histopathological verification; January 2020 to December 2022) were included. Two radiologists reviewed the images and assigned a Breast Imaging Reporting and Data System (BI-RADS) category. ABUS images were classified as positive or negative using AI-CAD. The BI-RADS category was readjusted in four ways: the radiologists modified the BI-RADS category using the AI results (AI-aided 1), upgraded or downgraded based on AI results (AI-aided 2), only upgraded for positive results (AI-aided 3), or only downgraded for negative results (AI-aided 4). The AI-aided diagnostic performances were compared to radiologists. The AI-CAD-positive and AI-CAD-negative cancer characteristics were compared.

RESULTS

For 262 lesions (145 malignant and 117 benign) in 231 women (mean age, 52.2 years), the area under the receiver operator characteristic curve (AUC) of radiologists was 0.870 (95% confidence interval [CI], 0.832-0.908). The AUC significantly improved to 0.919 (95% CI, 0.890-0.947; P = 0.001) using AI-aided 1, whereas it improved without significance to 0.884 (95% CI, 0.844-0.923), 0.890 (95% CI, 0.852-0.929), and 0.890 (95% CI, 0.853-0.928) using AI-aided 2, 3, and 4, respectively. AI-CAD-negative cancers were smaller, less frequently exhibited retraction phenomenon, and had lower BI-RADS category. Among nonmass lesions, AI-CAD-negative cancers showed no posterior shadowing.

CONCLUSION

AI-CAD implementation significantly improved the radiologists' diagnostic performance and may serve as a valuable diagnostic tool.

Development and quality appraisal of a new English breast screening linked data set as part of the age, test threshold, and frequency of mammography screening (ATHENA-M) study

OBJECTIVES

To build a data set capturing the whole breast cancer screening journey from individual breast cancer screening records to outcomes and assess data quality.

METHODS

Routine screening records (invitation, attendance, test results) from all 79 English NHS breast screening centres between January 1, 1988 and March 31, 2018 were linked to cancer registry (cancer characteristics and treatment) and national mortality data. Data quality was assessed using comparability, validity, timeliness, and completeness.

RESULTS

Screening records were extracted from 76/79 English breast screening centres, 3/79 were not possible due to software issues. Data linkage was successful from 1997 after introduction of a universal identifier for women (NHS number). Prior to 1997 outcome data are incomplete due to linkage issues, reducing validity. Between January 1, 1997 and March 31, 2018, a total of 11 262 730 women were offered screening of whom 9 371 973 attended at least one appointment, with 139 million person-years of follow-up (a median of 12.4 person years for each woman included) with 73 810 breast cancer deaths and 1 111 139 any-cause deaths. Comparability to reference data sets and internal validity were demonstrated. Data completeness was high for core screening variables (>99%) and main cancer outcomes (>95%).

CONCLUSIONS

The ATHENA-M project has created a large high-quality and representative data set of individual women's screening trajectories and outcomes in England from 1997 to 2018, data before 1997 are lower quality.

ADVANCES IN KNOWLEDGE

This is the most complete data set of English breast screening records and outcomes constructed to date, which can be used to evaluate and optimize screening.

Multi-MicroRNA Analysis Can Improve the Diagnostic Performance of Mammography in Determining Breast Cancer Risk

The objective of this study was to determine whether multi-microRNA analysis using a combination of four microRNA biomarkers (miR-1246, 202, 21, and 219B) could improve the diagnostic performance of mammography in determining breast cancer risk by age group (under 50 vs. over 50) and distinguish breast cancer from benign breast diseases and other cancers (thyroid, colon, stomach, lung, liver, and cervix cancers). To verify breast cancer classification performance of the four miRNA biomarkers and whether the model providing breast cancer risk score could distinguish between benign breast disease and other cancers, the model was verified using nonlinear support vector machine (SVM) and generalized linear model (GLM) and age and four miRNA qRT-PCR analysis values (dCt) were input to these models. Breast cancer risk scores for each Breast Imaging-Reporting and Data System (BI-RADS) category in multi-microRNA analysis were analyzed to examine the correlation between breast cancer risk scores and mammography categories. We generated two models using two classification algorithms, SVM and GLM, with a combination of four miRNA biomarkers showing high performance and sensitivities of 84.5% and 82.1%, a specificity of 85%, and areas under the curve (AUCs) of 0.967 and 0.965, respectively, which showed consistent performance across all stages of breast cancer and patient ages. The results of this study showed that this multi-microRNA analysis using the four miRNA biomarkers was effective in classifying breast cancer in patients under the age of 50, which is challenging to accurately diagnose. In addition, breast cancer and benign breast diseases can be classified, showing the possibility of helping with diagnosis by mammography. Verification of the performance of the four miRNA biomarkers confirmed that multi-microRNA analysis could be used as a new breast cancer screening aid to improve the accuracy of mammography. However, many factors must be considered for clinical use. Further validation with an appropriate screening population in large clinical trials is required. This trial is registered with (KNUCH 2022-04-036).

Diagnostic performance of screening mammography according to menstrual cycle among Asian women

PURPOSE

To investigate the performance metrics of screening mammography according to menstrual cycle week in premenopausal Asian women.

METHODS

This retrospective study included 69,556 premenopausal Asian women who underwent their first screening mammography between 2011 and 2019. The presence or absence of a breast cancer diagnosis within 12 months after the index screening mammography served as the reference standard, determined by linking the study data to the national cancer registry data. Menstrual cycles were calculated, and participants were assigned to groups according to weeks 1-4. The performance metrics included cancer detection rate (CDR), sensitivity, specificity, and positive predictive value (PPV), with comparisons across menstrual cycles.

RESULTS

Among menstrual cycles, the lowest CDR at 4.7 per 1000 women (95% confidence interval [CI], 3.8-5.8 per 1000 women) was observed in week 4 (all P < 0.05). The highest sensitivity of 72.7% (95% CI, 61.4-82.3) was observed in week 1, although the results failed to reach statistical significance. The highest specificity of 80.4% (95% CI, 79.5-81.3%) was observed in week 1 (P = 0.01). The lowest PPV of 2.2% (95% CI, 1.8-2.7) was observed in week 4 (all P < 0.05).

CONCLUSION

Screening mammography tended to show a higher performance during week 1 and a lower performance during week 4 of the menstrual cycle among Asian women. These results emphasize the importance of timing recommendations that consider menstrual cycles to optimize the effectiveness of screening mammography for breast cancer detection.

Effect of artificial intelligence-based computer-aided diagnosis on the screening outcomes of digital mammography: a matched cohort study

OBJECTIVE

To investigate whether artificial intelligence-based computer-aided diagnosis (AI-CAD) can improve radiologists' performance when used to support radiologists' interpretation of digital mammography (DM) in breast cancer screening.

METHODS

A retrospective database search identified 3158 asymptomatic Korean women who consecutively underwent screening DM between January and December 2019 without AI-CAD support, and screening DM between February and July 2020 with image interpretation aided by AI-CAD in a tertiary referral hospital using single reading. Propensity score matching was used to match the DM with AI-CAD group in a 1:1 ratio with the DM without AI-CAD group according to age, breast density, experience level of the interpreting radiologist, and screening round. Performance measures were compared with the McNemar test and generalized estimating equations.

RESULTS

A total of 1579 women who underwent DM with AI-CAD were matched with 1579 women who underwent DM without AI-CAD. Radiologists showed higher specificity (96% [1500 of 1563] vs 91.6% [1430 of 1561]; p < 0.001) and lower abnormal interpretation rates (AIR) (4.9% [77 of 1579] vs 9.2% [145 of 1579]; p < 0.001) with AI-CAD than without. There was no significant difference in the cancer detection rate (CDR) (AI-CAD vs no AI-CAD, 8.9 vs 8.9 per 1000 examinations; p = 0.999), sensitivity (87.5% vs 77.8%; p = 0.999), and positive predictive value for biopsy (PPV3) (35.0% vs 35.0%; p = 0.999) according to AI-CAD support.

CONCLUSIONS

AI-CAD increases the specificity for radiologists without decreasing sensitivity as a supportive tool in the single reading of DM for breast cancer screening.

CLINICAL RELEVANCE STATEMENT

This study shows that AI-CAD could improve the specificity of radiologists' DM interpretation in the single reading system without decreasing sensitivity, suggesting that it can benefit patients by reducing false positive and recall rates.

KEY POINTS

• In this retrospective-matched cohort study (DM without AI-CAD vs DM with AI-CAD), radiologists showed higher specificity and lower AIR when AI-CAD was used to support decision-making in DM screening. • CDR, sensitivity, and PPV for biopsy did not differ with and without AI-CAD support.

Overcoming the limitations of screening mammography in Japan and Korea: a paradigm shift to personalized breast cancer screening based on ultrasonography

Screening mammography programs have been implemented in numerous Western countries with the aim of reducing breast cancer mortality. However, despite over 20 years of population-based screening mammography, the mortality rates in Japan and Korea continue to rise. This may be due to the fact that screening mammography is not as effective for Japanese and Korean women, who often have dense breasts. This density decreases the sensitivity of mammography due to a masking effect. Therefore, the early detection of small invasive cancers requires more than just mammography, particularly for women in their 40s. This review discusses the limitations and challenges of screening mammography, as well as the keys to successful population-based breast cancer screening in Japan and Korea. This includes a focus on breast ultrasonography techniques, which are based on histopathologic anatomical knowledge, and personalized screening strategies that are based on risk assessments measured by glandular tissue components.

Multi-agent Systems and Cancer Pain Management

PURPOSE

The present investigation explores multi-agent systems, their function in cancer pain management, and how they might enhance patient care. Since cancer is a complex disease, technology can help doctors and patients coordinate care and communicate effectively. Even when a patient has a dedicated team, treatment may be fragmented. Multi-agent systems (MAS) are one component of technology that is making progress for cancer patients. Wireless sensory networks (WSN) and body area sensory networks (BASN) are examples of MAS.

RECENT FINDINGS

Technology is advancing the care of patients, not only in everyday clinical practice, but also in creating accessible communication between patients and provider. Many hospitals have utilized electronic medical records (EHR), but recent advancements allowed the pre-existing infrastructure to network with personal devices creating a more congruent form of communications. Better communication can better organize pain management, leading to better clinical outcomes for patients, integrating body sensors, such as smart watch, or using self-reporting apps. Certain software applications are also used to help providers in early detections of some cancers, having accurate results. The integration of technology in the field of cancer management helps create an organized structure for cancer patients trying to understand/manage their complex diagnosis. The systems for the various healthcare entities can receive and access frequently updated information that can better provide better coverage of the patient's pain and still be within the legalities as it pertains to opioid medications. The systems include the EHR communicating with the information provided by the patient's cellular devices and then communicating with the healthcare team to determine the next step in management. This all happens automatically with much physical input from the patient decreasing the amount of effort from the patient and hopefully decreasing the number of patients' loss to follow-up.

Screening Outcomes of Supplemental Automated Breast US in Asian Women with Dense and Nondense Breasts

Background Automated breast (AB) US effectively depicts mammographically occult breast cancers in Western women. However, few studies have focused on the outcome of supplemental AB US in Asian women who have denser breasts than Western women. Purpose To evaluate the performance of supplemental AB US on mammography-based breast cancer screening in Asian women with dense breasts and those with nondense breasts. Materials and Methods A retrospective database search identified asymptomatic Korean women who underwent digital mammography (DM) and supplemental AB US screening for breast cancer between January 2018 and December 2019. We excluded women without sufficient follow-up, established final diagnosis, or histopathologic results. Performance measures of DM alone and AB US combined with DM (hereafter AB US plus DM) were compared. The primary outcome was cancer detection rate (CDR), and the secondary outcomes were sensitivity and specificity. Subgroup analyses were performed based on mammography density. Results From 2785 screening examinations in 2301 women (mean age, 52 years ± 9 [SD]), 28 cancers were diagnosed (26 screening-detected cancers, two interval cancers). When compared with DM alone, AB US plus DM resulted in a higher CDR of 9.3 per 1000 examinations (95% CI: 7.7, 10.3) versus 6.5 per 1000 examinations (95% CI: 5.2, 7.2; P < .001) and a higher sensitivity of 90.9% (95% CI: 77.3, 100.0) versus 63.6% (95% CI: 40.9, 81.8; P < .001) but a lower specificity of 86.8% (95% CI: 85.2, 88.2) versus 94.6% (95% CI: 93.6, 95.5; P < .001) in women with dense breasts. In women with nondense breasts, AB US plus DM resulted in a higher CDR of 9.5 per 1000 examinations (95% CI: 7.1, 10.6) versus 6.3 per 1000 examinations (95% CI: 3.5, 7.1; P < .001), whereas specificity was lower at 95.2% (95% CI: 93.4, 96.8) versus 97.1% (95% CI: 95.8, 98.4; P < .001). Conclusion In Asian women, the addition of automated breast US to digital mammography showed higher cancer detection rates but lower specificities in both dense and nondense breasts. © RSNA, 2023 Supplemental material is available for this article.

Performance analysis of screening mammography in Asian women under 40 years

BACKGROUND

Screening mammography performance among young women remains uncertain in East Asia, where the proportion of young breast cancer patients is higher than that in Western countries. Thus, we analyzed the performance of screening mammography in women under 40 years in comparison with older age groups.

METHODS

This retrospective study comprised 95,431 Asian women with 197,525 screening mammograms. The reference standard was determined by linkage to the national cancer registry data and the 12-month follow-up outcomes after the index mammogram. The performance metrics included sensitivity, specificity, cancer detection rate (CDR), positive predictive value (PPV), recall rate, and areas under the receiver operating characteristic curve (AUCs), with comparisons across age groups (30 s, 40 s, and ≥ 50 s).

RESULTS

For young women aged < 40 years, sensitivity and AUC (95% confidence interval [CI]) of screening mammography were 60.4% (50.4-69.7) and 0.73 (0.68-0.77), respectively, with no significant difference compared to women in their 40 s (sensitivity: 64.0% [95% CI: 57.8-69.8], P = 0.52; AUC: 0.75 [95% CI: 0.73-0.78], P = 0.35). The CDR (95% CI) was 0.8 (0.6-1.1) per 1,000 mammograms for young women, poorer than 1.8 (1.6-2.1) per 1,000 mammograms for women in their 40 s (P < 0.001). The PPV and recall rate (95% CI) for young women were 0.6% (0.4-0.7) and 14.9% (14.6-15.1), poorer than 1.4% (1.2-1.6) and 13.3% (13.1-13.5) for women in their 40 s (P < 0.001), respectively.

CONCLUSION

The accuracy of screening mammography for young women in their 30 s was not significantly different from that for women in their 40 s, but the cancer detection and recall rates were poorer.

[Breast Imaging Reporting and Data System (BI-RADS): Advantages and Limitations]

Breast Imaging Reporting and Data System (BI-RADS) is a communication and data tracking system that standardizes and controls the quality of reporting by presenting lexicon descriptors, assessment categories, and recommendations for managing breast lesions. Using standardized terminology recommended by BI-RADS, radiologists can concisely and reproducibly communicate breast imaging results to clinicians. They can also provide the estimated malignant probability of the lesions found and guide management for them by determining the final assessment category. The limitations of BI-RADS 5th edition currently in use are that there are some areas for which standardized terminologies still need to be established, and that the diagnostic criteria of MRI assessment categories 3 and 4 are ambiguous compared to those for mammography or ultrasound. The next revision of BI-RADS is expected to include solutions for overcoming current limitations.

Trends in breast cancer screening rates among Korean women: results from the Korean National Cancer Screening Survey, 2005-2020

OBJECTIVES

Since 2002, the Korean government has provided breast cancer screening as part of the National Cancer Screening Program. This study reported trends in the screening rate among Korean women from 2005 to 2020, including organized and opportunistic screening for breast cancer.

METHODS

Data from the Korean National Cancer Screening Survey, an annual cross-sectional nationwide survey, were collected using a structured questionnaire between 2005 and 2020. The study population included 23,702 women aged 40-74 years with no history of cancer. We estimated the screening rate based on the current recommendation of biennial mammographic screening for breast cancer. In addition, a joinpoint trend analysis was performed for breast cancer screening rates among various subgroups.

RESULTS

In 2020, the breast cancer screening rate was 63.5%, reflecting an annual increase of 7.72% (95% confidence interval 5.53 to 9.95) between 2005 and 2012, followed by non-significant trends thereafter. In particular, a significant decrease in the breast cancer screening rate was observed in the subgroups aged 50-59 years old, with 12-15 years of education, and living in rural areas.

CONCLUSIONS

Although there has been substantial improvement in breast cancer screening rates in Korean women, the trend has flattened in recent years. Therefore, continual efforts are required to identify subgroups with unmet needs and solve barriers to the uptake of breast cancer screening.

Reducing Unnecessary Biopsies Using Digital Breast Tomosynthesis and Ultrasound in Dense and Nondense Breasts

Aim: To compare digital breast tomosynthesis (DBT) and ultrasound in women recalled for assessment after a positive screening mammogram and assess the potential for each of these tools to reduce unnecessary biopsies. Methods: This data linkage study included 538 women recalled for assessment from January 2017 to December 2019. The association between the recalled mammographic abnormalities and breast density was analysed using the chi-square independence test. Relative risks and the number of recalled cases requiring DBT and ultrasound assessment to prevent one unnecessary biopsy were compared using the McNemar test. Results: Breast density significantly influenced recall decisions (p < 0.001). Ultrasound showed greater potential to decrease unnecessary biopsies than DBT: in entirely fatty (21% vs. 5%; p = 0.04); scattered fibroglandular (23% vs. 10%; p = 0.003); heterogeneously dense (34% vs. 7%; p < 0.001) and extremely dense (39% vs. 9%; p < 0.001) breasts. The number of benign cases needing assessment to prevent one unnecessary biopsy was significantly lower with ultrasound than DBT in heterogeneously dense (1.8 vs. 7; p < 0.001) and extremely dense (1.9 vs. 5.1; p = 0.03) breasts. Conclusion: Women with dense breasts are more likely to be recalled for assessment and have a false-positive biopsy. Women with dense breasts benefit more from ultrasound assessment than from DBT.

Automated Segmentation of Mass Regions in DBT Images Using a Dilated DCNN Approach

To overcome the limitations of conventional breast screening methods based on digital mammography, a quasi-3D imaging technique, digital breast tomosynthesis (DBT) has been developed in the field of breast cancer screening in recent years. In this work, a computer-aided architecture for mass regions segmentation in DBT images using a dilated deep convolutional neural network (DCNN) is developed. First, to improve the low contrast of breast tumour candidate regions and depress the background tissue noise in the DBT image effectively, the constraint matrix is established after top-hat transformation and multiplied with the DBT image. Second, input image patches are generated, and the data augmentation technique is performed to create the training data set for training a dilated DCNN architecture. Then the mass regions in DBT images are preliminarily segmented; each pixel is divided into two different kinds of labels. Finally, the postprocessing procedure removes all false-positives regions with less than 50 voxels. The final segmentation results are obtained by smoothing the boundaries of the mass regions with a median filter. The testing accuracy (ACC), sensitivity (SEN), and the area under the receiver operating curve (AUC) are adopted as the evaluation metrics, and the ACC, SEN, as well as AUC are 86.3%, 85.6%, and 0.852 for segmenting the mass regions in DBT images on the entire data set, respectively. The experimental results indicate that our proposed approach achieves promising results compared with other classical CAD-based frameworks.

Artificial intelligence for breast cancer analysis: Trends & directions

Breast cancer is one of the leading causes of death among women. Early detection of breast cancer can significantly improve the lives of millions of women across the globe. Given importance of finding solution/framework for early detection and diagnosis, recently many AI researchers are focusing to automate this task. The other reasons for surge in research activities in this direction are advent of robust AI algorithms (deep learning), availability of hardware that can run/train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths and limitations. It also enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade to detect breast cancer using various imaging modalities. Primarily, in this article we have focused on reviewing frameworks that have reported results using mammograms as it is the most widely used breast imaging modality that serves as the first test that medical practitioners usually prescribe for the detection of breast cancer. Another reason for focusing on mammogram imaging modalities is the availability of its labelled datasets. Datasets availability is one of the most important aspects for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Artificial Intelligence for Breast Cancer Screening in Mammography (AI-STREAM): A Prospective Multicenter Study Design in Korea Using AI-based CADe/x

Purpose

Artificial intelligence (AI)-based computer-aided detection/diagnosis (CADe/x) has helped improve radiologists’ performance and provides results equivalent or superior to those of radiologists’ alone. This prospective multicenter cohort study aims to generate real-world evidence on the overall benefits and disadvantages of using AI-based CADe/x for breast cancer detection in a population-based breast cancer screening program comprising Korean women aged ≥ 40 years. The purpose of this report is to compare the diagnostic accuracy of radiologists with and without the use of AI-based CADe/x in mammography readings for breast cancer screening of Korean women with average breast cancer risk.

Methods

Approximately 32,714 participants will be enrolled between February 2021 and December 2022 at 5 study sites in Korea. A radiologist specializing in breast imaging will interpret the mammography readings with or without the use of AI-based CADe/x. If recall is required, further diagnostic workup will be conducted to confirm the cancer detected on screening. The findings will be recorded for all participants regardless of their screening status to identify study participants with breast cancer diagnosis within both 1 year and 2 years of screening. The national cancer registry database will be reviewed in 2026 and 2027, and the results of this study are expected to be published in 2027. In addition, the diagnostic accuracy of general radiologists and radiologists specializing in breast imaging from another hospital with or without the use of AI-based CADe/x will be compared considering mammography readings for breast cancer screening.

Discussion

The Artificial Intelligence for Breast Cancer Screening in Mammography (AI-STREAM) study is a prospective multicenter study that aims to compare the diagnostic accuracy of radiologists with and without the use of AI-based CADe/x in mammography readings for breast cancer screening of women with average breast cancer risk. AI-STREAM is currently in the patient enrollment phase.

Trial Registration

ClinicalTrials.gov Identifier: NCT05024591

Evaluation of the Value of Multiplex MicroRNA Analysis as a Breast Cancer Screening in Korean Women under 50 Years of Age with a High Proportion of Dense Breasts

This study was conducted to confirm the performance of the microRNA (miRNA) biomarker combination as a new breast cancer screening method in Korean women under the age of 50 with a high percentage of dense breasts. To determine the classification performance of a set of miRNA biomarkers (miR-1246, 202, 21, and 219B) useful for breast cancer screening, we determined whether there was a significant difference between the breast cancer and healthy control groups through box plots and the Mann–Whitney U-test, which was further examined in detail by age group. To verify the classification performance of the 4 miRNA biomarker set, 4 classification methods (logistic regression, random forest, XGBoost, and generalized linear model plus random forest) were applied, and 10-fold cross-validation was used as a validation method to improve performance stability. We confirmed that the best breast cancer detection performance was achievable in patients under 50 years of age when the set of 4 miRNAs were used. Under the age of 50, the 4 miRNA biomarkers showed the highest performance with a sensitivity of 85.29%, specificity of 93.33%, and area under the curve (AUC) of 0.961. Examining the results of 4 miRNA biomarkers was found to be an effective strategy for diagnosing breast cancer in Korean women under 50 years of age with dense breasts, and hence has the potential as a new breast cancer screening tool. Further validation in an appropriate screening population with large-scale clinical trials is required.

Effectiveness of the Korean National Cancer Screening Program in reducing breast cancer mortality

High incidences of breast cancer (BC) are reported in Asian women in their forties, and it is not clear whether mammographic screening reduces mortality among them. This study evaluated the effect of BC screening on mortality in Korea. We conducted a nationwide prospective cohort study of women invited to the Korean National Cancer Screening Program (KNCSP) between 2002 and 2003 (N = 8,300,682), with data linkage to the Korea Central Cancer Registry and death certificates through 2014 and 2015, respectively. Exposure to mammographic screening was defined using a modified never/ever approach. The primary study outcome was adjusted mortality rate ratio (MRR) for BC among screened and non-screened women estimated by Poisson regression. An adjusted MRR for all cause-death other than BC was examined to account for selection bias in the cohort. BC incidence rates for screened and non-screened women were 84.41 and 82.88 per 100,000 women-years, respectively. BC mortality rates for screened and non-screened women were 5.81 and 13.43 per 100,000 women-years, respectively, with an adjusted MRR for BC of 0.43 (95% CI, 0.41-0.44). The adjusted MRR for all-cause death excluding BC was 0.52 (95% CI, 0.52-0.52). The greatest reduction in BC mortality was noted for women aged 45-54 years, and there was no observable reduction in mortality after the age of 70 years. In conclusion, the KNCSP has been effective in reducing BC mortality among Korean women aged 40-69 years.

SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography

Early diagnosis of breast cancer unequivocally improves the survival rate of patients and is crucial for disease treatment. With the current developments in infrared imaging, breast screening using dynamic thermography seems to be a great complementary method for clinical breast examination (CBE) prior to mammography. In this study, we propose a sparse deep convolutional autoencoder model named SPAER to extract low-dimensional deep thermomics to aid breast cancer diagnosis. The model receives multichannel, low-rank, approximated thermal bases as input images. SPAER provides a solution for high-dimensional deep learning features and selects the predominant basis matrix using matrix factorization techniques. The model has been evaluated using five state-of-the-art matrix factorization methods and 208 thermal breast cancer screening cases. The best accuracy was for non-negative matrix factorization (NMF)-SPAER + Clinical and NMF-SPAER for maintaining thermal heterogeneity, leading to finding symptomatic cases with accuracies of 78.2% (74.3–82.5%) and 77.7% (70.9–82.1%), respectively. SPAER showed significant robustness when tested for additive Gaussian noise cases (3–20% noise), evaluated by the signal-to-noise ratio (SNR). The results suggest high performance of SPAER for preserveing thermal heterogeneity, and it can be used as a noninvasive in vivo tool aiding CBE in the early detection of breast cancer.

Automated breast US as the primary screening test for breast cancer among East Asian women aged 40-49 years: a multicenter prospective study

OBJECTIVES

To prospectively evaluate the diagnostic performance of screening ABUS as the primary screening test for breast cancer among Korean women aged 40-49 years.

METHODS

This prospective, multicenter study included asymptomatic Korean women aged 40-49 years from three academic centers between February 2017 and October 2019. Each participant underwent ABUS without mammography, and the ABUS images were interpreted at each hospital with double-reading by two breast radiologists. Biopsy and at least 1 year of follow-up was considered the reference standard. Diagnostic performance of ABUS screening and subgroup analyses according to patient and tumor characteristics were evaluated.

RESULTS

Reference standard data were available for 959 women. The recall rate was 9.8% (95% confidence interval [CI]: 7.9%, 11.7%; 94 of 959 women) and the cancer detection yield was 5.2 per 1000 women (95% CI: -0.6, 11.1; 5 of 959 women). There was only one interval cancer. The sensitivity was 83.3% (95% CI: 53.5%, 100%; 5 of 6 cancers) and the specificity was 90.7% (95% CI: 88.8%, 92.5%; 864 of 95. women). The positive predictive values of biopsies performed (PPV₃) was 20.0% (95% CI: 4.3%, 35.7%; 5 of 25 women). Women with heterogeneous background echotexture had a higher recall rate (p = .009) and lower specificity (p = .036). Women with body mass index values < 25 kg/m² had a higher mean recall rate (p = .046).

CONCLUSION

In East Asia, screening automated breast US may be an alternative to screening mammography for detecting breast cancers in women aged 40-49 years.

KEY POINTS

• Automated breast US screening for breast cancer in asymptomatic women aged 40-49 is effective with 5.2 per 1000 cancer detection yield. • Women with heterogeneous background echotexture had a higher recall rate and lower specificity. • Women with body mass index < 25 kg/m² had a higher recall rate.

Digital Mammography as a Screening Tool in Korea

국가암검진사업에서 매년 400만 명 이상의 여성이 유방촬영술을 이용한 유방암 검진을 받고 있다. 2000년 디지털 유방촬영술의 도입 이후, 선행 연구들에 의하면 디지털 유방촬영술은 치밀유방을 가진 여성에서 제한적으로 기존의 필름 방식 또는 computed radiography (이하 CR)보다 높은 진단 정확도를 보고하였다. 최근 국가암검진사업에서 수행된 자료를 분석한 결과에 따르면 디지털 유방촬영술의 진단 정확도가 필름 또는 CR 방식에 비해서 치밀유방을 가진 여성뿐만 아니라 모든 연령대의 여성에서 검진 횟수와 상관없이 보다 정확하였다. 우리나라는 OECD 국가 중에서도 높은 유방촬영기기 보급률에도 불구하고 현재 디지털 유방촬영기기의 보급은 전체 유방촬영기기 중, 35% 정도 수준으로 더디기만 하다. 디지털 유방촬영기기로의 신속한 전환을 위하여 수가제도의 개선, 유방 영상 판독 교육 지원 등 관련법과 제도의 정비가 필요할 것이다. 아울러 국가암검진사업에서 보다 많은 여성이 디지털 유방촬영기기를 이용한 유방암 검진을 받을 수 있도록 장비 보급의 지역 간 격차 해소를 위해 노력해야 할 것이다.

Noise modeling and variance stabilization of a computed radiography (CR) mammography system subject to fixed-pattern noise

In this work we model the noise properties of a computed radiography (CR) mammography system by adding an extra degree of freedom to a well-established noise model, and derive a variance-stabilizing transform (VST) to convert the signal-dependent noise into approximately signal-independent. The proposed model relies on a quadratic variance function, which considers fixed-pattern (structural), quantum and electronic noise. It also accounts for the spatial-dependency of the noise by assuming a space-variant quantum coefficient. The proposed noise model was compared against two alternative models commonly found in the literature. The first alternative model ignores the spatial-variability of the quantum noise, and the second model assumes negligible structural noise. We also derive a VST to convert noisy observations contaminated by the proposed noise model into observations with approximately Gaussian noise and constant variance equals to one. Finally, we estimated a look-up table that can be used as an inverse transform in denoising applications. A phantom study was conducted to validate the noise model, VST and inverse VST. The results show that the space-variant signal-dependent quadratic noise model is appropriate to describe noise in this CR mammography system (errors< 2.0% in terms of signal-to-noise ratio). The two alternative noise models were outperformed by the proposed model (errors as high as 14.7% and 9.4%). The designed VST was able to stabilize the noise so that it has variance approximately equal to one (errors< 4.1%), while the two alternative models achieved errors as high as 26.9% and 18.0%, respectively. Finally, the proposed inverse transform was capable of returning the signal to the original signal range with virtually no bias.

Detecting Vasodilation as Potential Diagnostic Biomarker in Breast Cancer Using Deep Learning-Driven Thermomics

Breast cancer is the most common cancer in women. Early diagnosis improves outcome and survival, which is the cornerstone of breast cancer treatment. Thermography has been utilized as a complementary diagnostic technique in breast cancer detection. Artificial intelligence (AI) has the capacity to capture and analyze the entire concealed information in thermography. In this study, we propose a method to potentially detect the immunohistochemical response to breast cancer by finding thermal heterogeneous patterns in the targeted area. In this study for breast cancer screening 208 subjects participated and normal and abnormal (diagnosed by mammography or clinical diagnosis) conditions were analyzed. High-dimensional deep thermomic features were extracted from the ResNet-50 pre-trained model from low-rank thermal matrix approximation using sparse principal component analysis. Then, a sparse deep autoencoder designed and trained for such data decreases the dimensionality to 16 latent space thermomic features. A random forest model was used to classify the participants. The proposed method preserves thermal heterogeneity, which leads to successful classification between normal and abnormal subjects with an accuracy of 78.16% (73.3-81.07%). By non-invasively capturing a thermal map of the entire tumor, the proposed method can assist in screening and diagnosing this malignancy. These thermal signatures may preoperatively stratify the patients for personalized treatment planning and potentially monitor the patients during treatment.