Identifying normal mammograms in a large screening population using artificial intelligence

Workload reduction of digital breast tomosynthesis screening using artificial intelligence and synthetic mammography: a simulation study

Purpose

To achieve the high sensitivity of digital breast tomosynthesis (DBT), a time-consuming reading is necessary. However, synthetic mammography (SM) images, equivalent to digital mammography (DM), can be generated from DBT images. SM is faster to read and might be sufficient in many cases. We investigate using artificial intelligence (AI) to stratify examinations into reading of either SM or DBT to minimize workload and maximize accuracy.

Approach

This is a retrospective study based on double-read paired DM and one-view DBT from the Malmö Breast Tomosynthesis Screening Trial. DBT examinations were analyzed with the cancer detection AI system ScreenPoint Transpara 1.7. For low-risk examinations, SM reading was simulated by assuming equality with DM reading. For high-risk examinations, the DBT reading results were used. Different combinations of single and double reading were studied.

Results

By double-reading the DBT of 30% (4452/14,772) of the cases with the highest risk, and single-reading SM for the rest, 122 cancers would be detected with the same reading workload as DM double reading. That is 28% (27/95) more cancers would be detected than with DM double reading, and in total, 96% (122/127) of the cancers detectable with full DBT double reading would be found.

Conclusions

In a DBT-based screening program, AI could be used to select high-risk cases where the reading of DBT is valuable, whereas SM is sufficient for low-risk cases. Substantially, more cancers could be detected compared with DM only, with only a limited increase in reading workload. Prospective studies are necessary.

AI-supported approaches for mammography single and double reading: A controlled multireader study

PURPOSE

To assess the impact of artificial intelligence (AI) on the diagnostic performance of radiologists with varying experience levels in mammography reading, considering single and simulated double reading approaches.

METHODS

In this retrospective study, 150 mammography examinations (30 with pathology-confirmed malignancies, 120 without malignancies [confirmed by 2-year follow-up]) were reviewed according to five approaches: A) human single reading by 26 radiologists of varying experience; B) AI single reading (Lunit INSIGHT MMG; C) human single reading with simultaneous AI support; D) simulated human-human double reading; E) simulated human-AI double reading, with AI as second independent reader flagging cases with a cancer probability ≥10 %. Sensitivity and specificity were calculated and compared using McNemar's test, univariate and multivariable logistic regression.

RESULTS

Compared to single reading without AI support, single reading with simultaneous AI support improved mean sensitivity from 69.2 % (standard deviation [SD] 15.6) to 84.5 % (SD 8.1, p < 0.001), providing comparable mean specificity (91.8 % versus 90.8 %, p = 0.06). The sensitivity increase provided by the AI-supported single reading was largest in the group of radiologists with a sensitivity below the median in the non-supported single reading, from 56.7 % (SD 12.1) to 79.7 % (SD 10.2, p < 0.001). In the simulated human-AI double reading approach, sensitivity further increased to 91.8 % (SD 3.4), surpassing that of the human-human simulated double reading (87.4 %, SD 8.8, p = 0.016), with comparable mean specificity (from 84.0 % to 83.0 %, p = 0.17).

CONCLUSION

AI support significantly enhanced sensitivity across all reading approaches, particularly benefiting worse performing radiologists. In the simulated double reading approaches, AI incorporation as independent second reader significantly increased sensitivity without compromising specificity.

Development and validation of a multi-stage self-supervised learning model for optical coherence tomography image classification

OBJECTIVE

This study aimed to develop a novel multi-stage self-supervised learning model tailored for the accurate classification of optical coherence tomography (OCT) images in ophthalmology reducing reliance on costly labeled datasets while maintaining high diagnostic accuracy.

MATERIALS AND METHODS

A private dataset of 2719 OCT images from 493 patients was employed, along with 3 public datasets comprising 84 484 images from 4686 patients, 3231 images from 45 patients, and 572 images. Extensive internal, external, and clinical validation were performed to assess model performance. Grad-CAM was employed for qualitative analysis to interpret the model's decisions by highlighting relevant areas. Subsampling analyses evaluated the model's robustness with varying labeled data availability.

RESULTS

The proposed model outperformed conventional supervised or self-supervised learning-based models, achieving state-of-the-art results across 3 public datasets. In a clinical validation, the model exhibited up to 17.50% higher accuracy and 17.53% higher macro F-1 score than a supervised learning-based model under limited training data.

DISCUSSION

The model's robustness in OCT image classification underscores the potential of the multi-stage self-supervised learning to address challenges associated with limited labeled data. The availability of source codes and pre-trained models promotes the use of this model in a variety of clinical settings, facilitating broader adoption.

CONCLUSION

This model offers a promising solution for advancing OCT image classification, achieving high accuracy while reducing the cost of extensive expert annotation and potentially streamlining clinical workflows, thereby supporting more efficient patient management.

Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions

Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020. Breast imaging plays a significant role in early diagnosis and intervention to improve the outcome of breast cancer patients. In the past decade, deep learning has shown remarkable progress in breast cancer imaging analysis, holding great promise in interpreting the rich information and complex context of breast imaging modalities. Considering the rapid improvement in deep learning technology and the increasing severity of breast cancer, it is critical to summarize past progress and identify future challenges to be addressed. This paper provides an extensive review of deep learning-based breast cancer imaging research, covering studies on mammograms, ultrasound, magnetic resonance imaging, and digital pathology images over the past decade. The major deep learning methods and applications on imaging-based screening, diagnosis, treatment response prediction, and prognosis are elaborated and discussed. Drawn from the findings of this survey, we present a comprehensive discussion of the challenges and potential avenues for future research in deep learning-based breast cancer imaging.

Artificial intelligence for breast cancer detection and its health technology assessment: A scoping review

BACKGROUND

Recent healthcare advancements highlight the potential of Artificial Intelligence (AI) - and especially, among its subfields, Machine Learning (ML) - in enhancing Breast Cancer (BC) clinical care, leading to improved patient outcomes and increased radiologists' efficiency. While medical imaging techniques have significantly contributed to BC detection and diagnosis, their synergy with AI algorithms has consistently demonstrated superior diagnostic accuracy, reduced False Positives (FPs), and enabled personalized treatment strategies. Despite the burgeoning enthusiasm for leveraging AI for early and effective BC clinical care, its widespread integration into clinical practice is yet to be realized, and the evaluation of AI-based health technologies in terms of health and economic outcomes remains an ongoing endeavor.

OBJECTIVES

This scoping review aims to investigate AI (and especially ML) applications that have been implemented and evaluated across diverse clinical tasks or decisions in breast imaging and to explore the current state of evidence concerning the assessment of AI-based technologies for BC clinical care within the context of Health Technology Assessment (HTA).

METHODS

We conducted a systematic literature search following the Preferred Reporting Items for Systematic review and Meta-Analysis Protocols (PRISMA-P) checklist in PubMed and Scopus to identify relevant studies on AI (and particularly ML) applications in BC detection and diagnosis. We limited our search to studies published from January 2015 to October 2023. The Minimum Information about CLinical Artificial Intelligence Modeling (MI-CLAIM) checklist was used to assess the quality of AI algorithms development, evaluation, and reporting quality in the reviewed articles. The HTA Core Model® was also used to analyze the comprehensiveness, robustness, and reliability of the reported results and evidence in AI-systems' evaluations to ensure rigorous assessment of AI systems' utility and cost-effectiveness in clinical practice.

RESULTS

Of the 1652 initially identified articles, 104 were deemed eligible for inclusion in the review. Most studies examined the clinical effectiveness of AI-based systems (78.84%, n= 82), with one study focusing on safety in clinical settings, and 13.46% (n=14) focusing on patients' benefits. Of the studies, 31.73% (n=33) were ethically approved to be carried out in clinical practice, whereas 25% (n=26) evaluated AI systems legally approved for clinical use. Notably, none of the studies addressed the organizational implications of AI systems in clinical practice. Of the 104 studies, only two of them focused on cost-effectiveness analysis, and were analyzed separately. The average percentage scores for the first 102 AI-based studies' quality assessment based on the MI-CLAIM checklist criteria were 84.12%, 83.92%, 83.98%, 74.51%, and 14.7% for study design, data and optimization, model performance, model examination, and reproducibility, respectively. Notably, 20.59% (n=21) of these studies relied on large-scale representative real-world breast screening datasets, with only 10.78% (n =11) studies demonstrating the robustness and generalizability of the evaluated AI systems.

CONCLUSION

In bridging the gap between cutting-edge developments and seamless integration of AI systems into clinical workflows, persistent challenges encompass data quality and availability, ethical and legal considerations, robustness and trustworthiness, scalability, and alignment with existing radiologists' workflow. These hurdles impede the synthesis of comprehensive, robust, and reliable evidence to substantiate these systems' clinical utility, relevance, and cost-effectiveness in real-world clinical workflows. Consequently, evaluating AI-based health technologies through established HTA methodologies becomes complicated. We also highlight potential significant influences on AI systems' effectiveness of various factors, such as operational dynamics, organizational structure, the application context of AI systems, and practices in breast screening or examination reading of AI support tools in radiology. Furthermore, we emphasize substantial reciprocal influences on decision-making processes between AI systems and radiologists. Thus, we advocate for an adapted assessment framework specifically designed to address these potential influences on AI systems' effectiveness, mainly addressing system-level transformative implications for AI systems rather than focusing solely on technical performance and task-level evaluations.

The top 100 most-cited articles on artificial intelligence in breast radiology: a bibliometric analysis

INTRODUCTION

Artificial intelligence (AI) in radiology is a rapidly evolving field. In breast imaging, AI has already been applied in a real-world setting and multiple studies have been conducted in the area. The aim of this analysis is to identify the most influential publications on the topic of artificial intelligence in breast imaging.

METHODS

A retrospective bibliometric analysis was conducted on artificial intelligence in breast radiology using the Web of Science database. The search strategy involved searching for the keywords 'breast radiology' or 'breast imaging' and the various keywords associated with AI such as 'deep learning', 'machine learning,' and 'neural networks'.

RESULTS

From the top 100 list, the number of citations per article ranged from 30 to 346 (average 85). The highest cited article titled 'Artificial Neural Networks In Mammography-Application To Decision-Making In The Diagnosis Of Breast-Cancer' was published in Radiology in 1993. Eighty-three of the articles were published in the last 10 years. The journal with the greatest number of articles was Radiology (n = 22). The most common country of origin was the United States (n = 51). Commonly occurring topics published were the use of deep learning models for breast cancer detection in mammography or ultrasound, radiomics in breast cancer, and the use of AI for breast cancer risk prediction.

CONCLUSION

This study provides a comprehensive analysis of the top 100 most-cited papers on the subject of artificial intelligence in breast radiology and discusses the current most influential papers in the field.

CLINICAL RELEVANCE STATEMENT

This article provides a concise summary of the top 100 most-cited articles in the field of artificial intelligence in breast radiology. It discusses the most impactful articles and explores the recent trends and topics of research in the field.

KEY POINTS

Multiple studies have been conducted on AI in breast radiology. The most-cited article was published in the journal Radiology in 1993. This study highlights influential articles and topics on AI in breast radiology.

Australian healthcare workers' views on artificial intelligence in BreastScreen: Results of a mixed method survey study

Introduction

The evolving role of Artificial Intelligence (AI) in medicine, particularly in radiology and population-based breast cancer screening programs, offers potential accuracy gains and efficiency improvements. However, successful implementation requires understanding of healthcare workers' views on AI, which this study aims to explore within the Australian BreastScreen program.

Methods

An online survey was distributed to clinical staff involved in breast imaging, collecting responses from November 2022 to April 2023. The survey encompassed demographic information, opinions, and experiences with AI in medical imaging, with questions covering various scenarios of AI integration in BreastScreen.

Results

Out of an estimated 350 professionals contacted, 95 responded, with 84.2 % (80/95) being radiologists. Less than half of respondents (44.9 %, 40/89) had worked with artificial intelligence for image classification previously. The majority of radiologists 74.2 % (46/62) thought that the use of AI in reading mammograms for BreastScreen would improve workflow. However, radiologists thought they would behave with increasing caution with scenarios where AI was more autonomous, with the majority of radiologists (63.3 %, 38/60) uncomfortable with holding accountability when the AI was used to triage and remove cases from the workflow. Notably, 60 % of radiologists (36/60) expressed concerns about accountability.

Discussion

The findings suggest an optimistic attitude towards AI among Australian healthcare workers, although when given hypothetical scenarios for the way AI could be integrated into BreastScreen, there was increasing caution with scenarios where AI was more autonomous. This study highlights understanding and concerns of healthcare professionals working in population screening which are important to address when implementing AI into the healthcare system.

Impact of human and artificial intelligence collaboration on workload reduction in medical image interpretation

Clinicians face increasing workloads in medical imaging interpretation, and artificial intelligence (AI) offers potential relief. This meta-analysis evaluates the impact of human-AI collaboration on image interpretation workload. Four databases were searched for studies comparing reading time or quantity for image-based disease detection before and after AI integration. The Quality Assessment of Studies of Diagnostic Accuracy was modified to assess risk of bias. Workload reduction and relative diagnostic performance were pooled using random-effects model. Thirty-six studies were included. AI concurrent assistance reduced reading time by 27.20% (95% confidence interval, 18.22%-36.18%). The reading quantity decreased by 44.47% (40.68%-48.26%) and 61.72% (47.92%-75.52%) when AI served as the second reader and pre-screening, respectively. Overall relative sensitivity and specificity are 1.12 (1.09, 1.14) and 1.00 (1.00, 1.01), respectively. Despite these promising results, caution is warranted due to significant heterogeneity and uneven study quality.

Strategies for integrating artificial intelligence into mammography screening programmes: a retrospective simulation analysis

BACKGROUND

Integrating artificial intelligence (AI) into mammography screening can support radiologists and improve programme metrics, yet the potential of different strategies for integrating the technology remains understudied. We compared programme-level performance metrics of seven AI integration strategies.

METHODS

We performed a retrospective comparative evaluation of seven strategies for integrating AI into mammography screening using datasets generated from screening programmes in Germany (n=1 657 068), the UK (n=223 603) and Sweden (n=22 779). The commercially available AI model used was Vara version 2.10, trained from scratch on German data. We simulated the performance of each strategy in terms of cancer detection rate (CDR), recall rate, and workload reduction, and compared the metrics with those of the screening programmes. We also assessed the distribution of the stages and grades of the cancers detected by each strategy and the AI model's ability to correctly localise those cancers.

FINDINGS

Compared with the German screening programme (CDR 6·32 per 1000 examinations, recall rate 4·11 per 100 examinations), replacement of both readers (standalone AI strategy) achieved a non-inferior CDR of 6·37 (95% CI 6·10-6·64) at a recall rate of 3·80 (95% CI 3·67-3·93), whereas single reader replacement achieved a CDR of 6·49 (6·31-6·67), a recall rate of 4·01 (3·92-4·10), and a 49% workload reduction. Programme-level decision referral achieved a CDR of 6·85 (6·61-7·11), a recall rate of 3·55 (3·43-3·68), and an 84% workload reduction. Compared with the UK programme CDR of 8·19, the reader-level, programme-level, and deferral to single reader strategies achieved CDRs of 8·24 (7·82-8·71), 8·59 (8·12-9·06), and 8·28 (7·86-8·71), without increasing recall and while reducing workload by 37%, 81%, and 95%, respectively. On the Swedish dataset, programme-level decision referral increased the CDR by 17·7% without increasing recall and while reducing reading workload by 92%.

INTERPRETATION

The decision referral strategies offered the largest improvements in cancer detection rates and reduction in recall rates, and all strategies except normal triaging showed potential to improve screening metrics.

FUNDING

Vara.

Artificial Intelligence Algorithm for Subclinical Breast Cancer Detection

Importance

Early breast cancer detection is associated with lower morbidity and mortality.

Objective

To examine whether a commercial artificial intelligence (AI) algorithm for breast cancer detection could estimate the development of future cancer.

Design, Setting, and Participants

This retrospective cohort study of 116 495 women aged 50 to 69 years with no prior history of breast cancer before they underwent at least 3 consecutive biennial screening examinations used scores from an AI algorithm (INSIGHT MMG, version 1.1.7.2; Lunit Inc; used September 28, 2022, to April 5, 2023) for breast cancer detection and screening data from multiple, consecutive rounds of mammography performed from September 13, 2004, to December 21, 2018, at 9 breast centers in Norway. The statistical analyses were performed from September 2023 to August 2024.

Exposure

Artificial intelligence algorithm score indicating suspicion for the presence of breast cancer. The algorithm provided a continuous cancer detection score for each examination ranging from 0 to 100, with increasing values indicating a higher likelihood of cancer being present on the current mammogram.

Main Outcomes and Measures

Maximum AI algorithm score for cancer detection and absolute difference in score among breasts of women developing screening-detected cancer, women with interval cancer, and women who screened negative.

Results

The mean (SD) age at the first study round was 58.5 (4.5) years for 1265 women with screening-detected cancer in the third round, 57.4 (4.6) years for 342 women with interval cancer after 3 negative screening rounds, and 56.4 (4.9) years for 116 495 women without breast cancer all 3 screening rounds. The mean (SD) absolute differences in AI scores among breasts of women developing screening-detected cancer were 21.3 (28.1) at the first study round, 30.7 (32.5) at the second study round, and 79.0 (28.9) at the third study round. The mean (SD) differences prior to interval cancer were 19.7 (27.0) at the first study round, 21.0 (27.7) at the second study round, and 34.0 (33.6) at the third study round. The mean (SD) differences among women who did not develop breast cancer were 9.9 (17.5) at the first study round, 9.6 (17.4) at the second study round, and 9.3 (17.3) at the third study round. Areas under the receiver operating characteristic curve for the absolute difference were 0.63 (95% CI, 0.61-0.65) at the first study round, 0.72 (95% CI, 0.71-0.74) at the second study round, and 0.96 (95% CI, 0.95-0.96) at the third study round for screening-detected cancer and 0.64 (95% CI, 0.61-0.67) at the first study round, 0.65 (95% CI, 0.62-0.68) at the second study round, and 0.77 (95% CI, 0.74-0.79) at the third study round for interval cancers.

Conclusions and Relevance

In this retrospective cohort study of women undergoing screening mammography, mean absolute AI scores were higher for breasts developing vs not developing cancer 4 to 6 years before their eventual detection. These findings suggest that commercial AI algorithms developed for breast cancer detection may identify women at high risk of a future breast cancer, offering a pathway for personalized screening approaches that can lead to earlier cancer diagnosis.

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.

How do AI markings on screening mammograms correspond to cancer location? An informed review of 270 breast cancer cases in BreastScreen Norway

OBJECTIVES

To compare the location of AI markings on screening mammograms with cancer location on diagnostic mammograms, and to classify interval cancers with high AI score as false negative, minimal sign, or true negative.

METHODS

In a retrospective study from 2022, we compared the performance of an AI system with independent double reading according to cancer detection. We found 93% (880/949) of the screen-detected cancers, and 40% (122/305) of the interval cancers to have the highest AI risk score (AI score of 10). In this study, four breast radiologists reviewed mammograms from 126 randomly selected screen-detected cancers and all 120 interval cancers with an AI score of 10. The location of the AI marking was stated as correct/not correct in craniocaudal and mediolateral oblique view. Interval cancers with an AI score of 10 were classified as false negative, minimal sign significant/non-specific, or true negative.

RESULTS

All screen-detected cancers and 78% (93/120) of the interval cancers with an AI score of 10 were correctly located by the AI system. The AI markings matched in both views for 79% (100/126) of the screen-detected cancers and 22% (26/120) of the interval cancers. For interval cancers with an AI score of 10, 11% (13/120) were correctly located and classified as false negative, 10% (12/120) as minimal sign significant, 26% (31/120) as minimal sign non-specific, and 31% (37/120) as true negative.

CONCLUSION

AI markings corresponded to cancer location for all screen-detected cancers and 78% of the interval cancers with high AI score, indicating a potential for reducing the number of interval cancers. However, it is uncertain whether interval cancers with subtle findings in only one view are actionable for recall in a true screening setting.

CLINICAL RELEVANCE STATEMENT

In this study, AI markings corresponded to the location of the cancer in a high percentage of cases, indicating that the AI system accurately identifies the cancer location in mammograms with a high AI score.

KEY POINTS

• All screen-detected and 78% of the interval cancers with high AI risk score (AI score of 10) had AI markings in one or two views corresponding to the location of the cancer on diagnostic images. • Among all 120 interval cancers with an AI score of 10, 21% (25/120) were classified as a false negative or minimal sign significant and had AI markings matching the cancer location, suggesting they may be visible on prior screening. • Most of the correctly located interval cancers matched only in one view, and the majority were classified as either true negative or minimal sign non-specific, indicating low potential for being detected earlier in a real screening setting.

Frequency and characteristics of errors by artificial intelligence (AI) in reading screening mammography: a systematic review

PURPOSE

Artificial intelligence (AI) for reading breast screening mammograms could potentially replace (some) human-reading and improve screening effectiveness. This systematic review aims to identify and quantify the types of AI errors to better understand the consequences of implementing this technology.

METHODS

Electronic databases were searched for external validation studies of the accuracy of AI algorithms in real-world screening mammograms. Descriptive synthesis was performed on error types and frequency. False negative proportions (FNP) and false positive proportions (FPP) were pooled within AI positivity thresholds using random-effects meta-analysis.

RESULTS

Seven retrospective studies (447,676 examinations; published 2019-2022) met inclusion criteria. Five studies reported AI error as false negatives or false positives. Pooled FPP decreased incrementally with increasing positivity threshold (71.83% [95% CI 69.67, 73.90] at Transpara 3 to 10.77% [95% CI 8.34, 13.79] at Transpara 9). Pooled FNP increased incrementally from 0.02% [95% CI 0.01, 0.03] (Transpara 3) to 0.12% [95% CI 0.06, 0.26] (Transpara 9), consistent with a trade-off with FPP. Heterogeneity within thresholds reflected algorithm version and completeness of the reference standard. Other forms of AI error were reported rarely (location error and technical error in one study each).

CONCLUSION

AI errors are largely interpreted in the framework of test accuracy. FP and FN errors show expected variability not only by positivity threshold, but also by algorithm version and study quality. Reporting of other forms of AI errors is sparse, despite their potential implications for adoption of the technology. Considering broader types of AI error would add nuance to reporting that can inform inferences about AI's utility.

Preoperative prediction of nodal status using clinical data and artificial intelligence derived mammogram features enabling abstention of sentinel lymph node biopsy in breast cancer

Introduction

Patients with clinically node-negative breast cancer have a negative sentinel lymph node status (pN0) in approximately 75% of cases and the necessity of routine surgical nodal staging by sentinel lymph node biopsy (SLNB) has been questioned. Previous prediction models for pN0 have included postoperative variables, thus defeating their purpose to spare patients non-beneficial axillary surgery. We aimed to develop a preoperative prediction model for pN0 and to evaluate the contribution of mammographic breast density and mammogram features derived by artificial intelligence for de-escalation of SLNB.

Materials and methods

This retrospective cohort study included 755 women with primary breast cancer. Mammograms were analyzed by commercially available artificial intelligence and automated systems. The additional predictive value of features was evaluated using logistic regression models including preoperative clinical variables and radiological tumor size. The final model was internally validated using bootstrap and externally validated in a separate cohort. A nomogram for prediction of pN0 was developed. The correlation between pathological tumor size and the preoperative radiological tumor size was calculated.

Results

Radiological tumor size was the strongest predictor of pN0 and included in a preoperative prediction model displaying an area under the curve of 0.68 (95% confidence interval: 0.63-0.72) in internal validation and 0.64 (95% confidence interval: 0.59-0.69) in external validation. Although the addition of mammographic features did not improve discrimination, the prediction model provided a 21% SLNB reduction rate when a false negative rate of 10% was accepted, reflecting the accepted false negative rate of SLNB.

Conclusion

This study shows that the preoperatively available radiological tumor size might replace pathological tumor size as a key predictor in a preoperative prediction model for pN0. While the overall performance was not improved by mammographic features, one in five patients could be omitted from axillary surgery by applying the preoperative prediction model for nodal status. The nomogram visualizing the model could support preoperative patient-centered decision-making on the management of the axilla.

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.

Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature

Background  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. Purpose  To evaluate published literature on breast cancer detection in mammography for reproducibility and to ascertain best practices for model design. Methods  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. Results  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. Conclusion  While deep learning holds much promise in mammography interpretation, evaluation in a reproducible clinical setting and explainable networks are the need of the hour.

AI-enhanced Mammography With Digital Breast Tomosynthesis for Breast Cancer Detection: Clinical Value and Comparison With Human Performance

Purpose To compare two deep learning-based commercially available artificial intelligence (AI) systems for mammography with digital breast tomosynthesis (DBT) and benchmark them against the performance of radiologists. Materials and Methods This retrospective study included consecutive asymptomatic patients who underwent mammography with DBT (2019-2020). Two AI systems (Transpara 1.7.0 and ProFound AI 3.0) were used to evaluate the DBT examinations. The systems were compared using receiver operating characteristic (ROC) analysis to calculate the area under the ROC curve (AUC) for detecting malignancy overall and within subgroups based on mammographic breast density. Breast Imaging Reporting and Data System results obtained from standard-of-care human double-reading were compared against AI results with use of the DeLong test. Results Of 419 female patients (median age, 60 years [IQR, 52-70 years]) included, 58 had histologically proven breast cancer. The AUC was 0.86 (95% CI: 0.85, 0.91), 0.93 (95% CI: 0.90, 0.95), and 0.98 (95% CI: 0.96, 0.99) for Transpara, ProFound AI, and human double-reading, respectively. For Transpara, a rule-out criterion of score 7 or lower yielded 100% (95% CI: 94.2, 100.0) sensitivity and 60.9% (95% CI: 55.7, 66.0) specificity. The rule-in criterion of higher than score 9 yielded 96.6% sensitivity (95% CI: 88.1, 99.6) and 78.1% specificity (95% CI: 73.8, 82.5). For ProFound AI, a rule-out criterion of lower than score 51 yielded 100% sensitivity (95% CI: 93.8, 100) and 67.0% specificity (95% CI: 62.2, 72.1). The rule-in criterion of higher than score 69 yielded 93.1% (95% CI: 83.3, 98.1) sensitivity and 82.0% (95% CI: 77.9, 86.1) specificity. Conclusion Both AI systems showed high performance in breast cancer detection but lower performance compared with human double-reading. Keywords: Mammography, Breast, Oncology, Artificial Intelligence, Deep Learning, Digital Breast Tomosynthesis © RSNA, 2024.

Artificial Intelligence for breast cancer detection: Technology, challenges, and prospects

PURPOSE

This review provides an overview of the current state of artificial intelligence (AI) technology for automated detection of breast cancer in digital mammography (DM) and digital breast tomosynthesis (DBT). It aims to discuss the technology, available AI systems, and the challenges faced by AI in breast cancer screening.

METHODS

The review examines the development of AI technology in breast cancer detection, focusing on deep learning (DL) techniques and their differences from traditional computer-aided detection (CAD) systems. It discusses data pre-processing, learning paradigms, and the need for independent validation approaches.

RESULTS

DL-based AI systems have shown significant improvements in breast cancer detection. They have the potential to enhance screening outcomes, reduce false negatives and positives, and detect subtle abnormalities missed by human observers. However, challenges like the lack of standardised datasets, potential bias in training data, and regulatory approval hinder their widespread adoption.

CONCLUSIONS

AI technology has the potential to improve breast cancer screening by increasing accuracy and reducing radiologist workload. DL-based AI systems show promise in enhancing detection performance and eliminating variability among observers. Standardised guidelines and trustworthy AI practices are necessary to ensure fairness, traceability, and robustness. Further research and validation are needed to establish clinical trust in AI. Collaboration between researchers, clinicians, and regulatory bodies is crucial to address challenges and promote AI implementation in breast cancer screening.

Diagnostic performance with and without artificial intelligence assistance in real-world screening mammography

Purpose

To evaluate artificial intelligence-based computer-aided diagnosis (AI-CAD) for screening mammography, we analyzed the diagnostic performance of radiologists by providing and withholding AI-CAD results alternatively every month.

Methods

This retrospective study was approved by the institutional review board with a waiver for informed consent. Between August 2020 and May 2022, 1819 consecutive women (mean age 50.8 ± 9.4 years) with 2061 screening mammography and ultrasound performed on the same day in a single institution were included. Radiologists interpreted screening mammography in clinical practice with AI-CAD results being provided or withheld alternatively by month. The AI-CAD results were retrospectively obtained for analysis even when withheld from radiologists. The diagnostic performances of radiologists and stand-alone AI-CAD were compared and the performances of radiologists with and without AI-CAD assistance were also compared by cancer detection rate, recall rate, sensitivity, specificity, accuracy and area under the receiver-operating-characteristics curve (AUC).

Results

Twenty-nine breast cancer patients and 1790 women without cancers were included. Diagnostic performances of the radiologists did not significantly differ with and without AI-CAD assistance. Radiologists with AI-CAD assistance showed the same sensitivity (76.5%) and similar specificity (92.3% vs 93.8%), AUC (0.844 vs 0.851), and recall rates (8.8% vs. 7.4%) compared to standalone AI-CAD. Radiologists without AI-CAD assistance showed lower specificity (91.9% vs 94.6%) and accuracy (91.5% vs 94.1%) and higher recall rates (8.6% vs 5.9%, all p < 0.05) compared to stand-alone AI-CAD.

Conclusion

Radiologists showed no significant difference in diagnostic performance when both screening mammography and ultrasound were performed with or without AI-CAD assistance for mammography. However, without AI-CAD assistance, radiologists showed lower specificity and accuracy and higher recall rates compared to stand-alone AI-CAD.

Impact of real-life use of artificial intelligence as support for human reading in a population-based breast cancer screening program with mammography and tomosynthesis

OBJECTIVES

To evaluate the impact of using an artificial intelligence (AI) system as support for human double reading in a real-life scenario of a breast cancer screening program with digital mammography (DM) or digital breast tomosynthesis (DBT).

MATERIAL AND METHODS

We analyzed the performance of double reading screening with mammography and tomosynthesis after implementarion of AI as decision support. The study group consisted of a consecutive cohort of 1 year screening between March 2021 and March 2022 where double reading was performed with concurrent AI support that automatically detects and highlights lesions suspicious of breast cancer in mammography and tomosynthesis. Screening performance was measured as cancer detection rate (CDR), recall rate (RR), and positive predictive value (PPV) of recalls. Performance in the study group was compared using a McNemar test to a control group that included a screening cohort of the same size, recorded just prior to the implementation of AI.

RESULTS

A total of 11,998 women (mean age 57.59 years ± 5.8 [sd]) were included in the study group (5049 DM and 6949 DBT). Comparing global results (including DM and DBT) of double reading with vs. without AI support, we observed an increase in CDR, PPV, and RR by 3.2/‰ (5.8 vs. 9; p < 0.001), 4% (10.6 vs. 14.6; p < 0.001), and 0.7% (5.4 vs. 6.1; p < 0.001) respectively.

CONCLUSION

AI used as support for human double reading in a real-life breast cancer screening program with DM and DBT increases CDR and PPV of the recalled women.

CLINICAL RELEVANCE STATEMENT

Artificial intelligence as support for human double reading improves accuracy in a real-life breast cancer screening program both in digital mammography and digital breast tomosynthesis.

KEY POINTS

• AI systems based on deep learning technology offer potential for improving breast cancer screening programs. • Using artificial intelligence as support for reading improves radiologists' performance in breast cancer screening programs with mammography or tomosynthesis. • Artificial intelligence used concurrently with human reading in clinical screening practice increases breast cancer detection rate and positive predictive value of the recalled women.

Patient Characteristics Impact Performance of AI Algorithm in Interpreting Negative Screening Digital Breast Tomosynthesis Studies

Background Artificial intelligence (AI) is increasingly used to manage radiologists' workloads. The impact of patient characteristics on AI performance has not been well studied. Purpose To understand the impact of patient characteristics (race and ethnicity, age, and breast density) on the performance of an AI algorithm interpreting negative screening digital breast tomosynthesis (DBT) examinations. Materials and Methods This retrospective cohort study identified negative screening DBT examinations from an academic institution from January 1, 2016, to December 31, 2019. All examinations had 2 years of follow-up without a diagnosis of atypia or breast malignancy and were therefore considered true negatives. A subset of unique patients was randomly selected to provide a broad distribution of race and ethnicity. DBT studies in this final cohort were interpreted by a U.S. Food and Drug Administration-approved AI algorithm, which generated case scores (malignancy certainty) and risk scores (1-year subsequent malignancy risk) for each mammogram. Positive examinations were classified based on vendor-provided thresholds for both scores. Multivariable logistic regression was used to understand relationships between the scores and patient characteristics. Results A total of 4855 patients (median age, 54 years [IQR, 46-63 years]) were included: 27% (1316 of 4855) White, 26% (1261 of 4855) Black, 28% (1351 of 4855) Asian, and 19% (927 of 4855) Hispanic patients. False-positive case scores were significantly more likely in Black patients (odds ratio [OR] = 1.5 [95% CI: 1.2, 1.8]) and less likely in Asian patients (OR = 0.7 [95% CI: 0.5, 0.9]) compared with White patients, and more likely in older patients (71-80 years; OR = 1.9 [95% CI: 1.5, 2.5]) and less likely in younger patients (41-50 years; OR = 0.6 [95% CI: 0.5, 0.7]) compared with patients aged 51-60 years. False-positive risk scores were more likely in Black patients (OR = 1.5 [95% CI: 1.0, 2.0]), patients aged 61-70 years (OR = 3.5 [95% CI: 2.4, 5.1]), and patients with extremely dense breasts (OR = 2.8 [95% CI: 1.3, 5.8]) compared with White patients, patients aged 51-60 years, and patients with fatty density breasts, respectively. Conclusion Patient characteristics influenced the case and risk scores of a Food and Drug Administration-approved AI algorithm analyzing negative screening DBT examinations. © RSNA, 2024.

Transfer learning for the generalization of artificial intelligence in breast cancer detection: a case-control study

BACKGROUND

Some researchers have questioned whether artificial intelligence (AI) systems maintain their performance when used for women from populations not considered during the development of the system.

PURPOSE

To evaluate the impact of transfer learning as a way of improving the generalization of AI systems in the detection of breast cancer.

MATERIAL AND METHODS

This retrospective case-control Finnish study involved 191 women diagnosed with breast cancer and 191 matched healthy controls. We selected a state-of-the-art AI system for breast cancer detection trained using a large US dataset. The selected baseline system was evaluated in two experimental settings. First, we examined our private Finnish sample as an independent test set that had not been considered in the development of the system (unseen population). Second, the baseline system was retrained to attempt to improve its performance in the unseen population by means of transfer learning. To analyze performance, we used areas under the receiver operating characteristic curve (AUCs) with DeLong's test.

RESULTS

Two versions of the baseline system were considered: ImageOnly and Heatmaps. The ImageOnly and Heatmaps versions yielded mean AUC values of 0.82±0.008 and 0.88±0.003 in the US dataset and 0.56 (95% CI=0.50-0.62) and 0.72 (95% CI=0.67-0.77) when evaluated in the unseen population, respectively. The retrained systems achieved AUC values of 0.61 (95% CI=0.55-0.66) and 0.69 (95% CI=0.64-0.75), respectively. There was no statistical difference between the baseline system and the retrained system.

CONCLUSION

Transfer learning with a small study sample did not yield a significant improvement in the generalization of the system.

The role of an artificial intelligence software in clinical senology: a mammography multi-reader study

PURPOSE

To evaluate the diagnostic role of a dedicated AI software in detecting anomalous breast findings on mammography and tomosynthesis images in the clinical setting, stand-alone and as aid of four readers.

METHODS

A total of 210 patients with complete clinical and radiologic records were retrospectively analyzed. Pathology was used as the reference standard for patients undergoing surgery or biopsy, and a 1-year follow-up was used to confirm no change in the remaining patients. The image evaluation was performed by four readers with different levels of experience (a junior and three senior breast radiologists) using a 5-point Likert scale moving from 1 (definitively no cancer) to 5 (definitively cancer). The positivity of mammograms was assessed on the presence of any breast lesion (masses, architectural distortions, asymmetries, calcifications), including malignant and benign ones. A multi-reader multi-case analysis was performed. A p value < 0.05 was considered statistically significant.

RESULTS

The stand-alone AI system achieved an accuracy of 71% (69% sensitivity and 73% specificity), which is overall lower than the value achieved by readers without AI. However, with the aid of AI, a significant increase of accuracy (p value  = 0.004) and specificity (p value  = 0.04) was achieved for the less experienced radiologist and a senior one.

CONCLUSION

The use of AI software as a second reader for breast lesions assessment could play a crucial role in the clinical setting, by increasing sensitivity and specificity, especially for less experienced radiologists.

A deep learning-based semiautomated workflow for triaging follow-up MR scans in treated nasopharyngeal carcinoma

It is imperative to optimally utilize virtues and obviate defects of fully automated analysis and expert knowledge in new paradigms of healthcare. We present a deep learning-based semiautomated workflow (RAINMAN) with 12,809 follow-up scans among 2,172 patients with treated nasopharyngeal carcinoma from three centers (ChiCTR.org.cn, Chi-CTR2200056595). A boost of diagnostic performance and reduced workload was observed in RAINMAN compared with the original manual interpretations (internal vs. external: sensitivity, 2.5% [p = 0.500] vs. 3.2% [p = 0.031]; specificity, 2.9% [p < 0.001] vs. 0.3% [p = 0.302]; workload reduction, 79.3% vs. 76.2%). The workflow also yielded a triaging performance of 83.6%, with increases of 1.5% in sensitivity (p = 1.000) and 0.6%-1.3% (all p < 0.05) in specificity compared to three radiologists in the reader study. The semiautomated workflow shows its unique superiority in reducing radiologist's workload by eliminating negative scans while retaining the diagnostic performance of radiologists.

Deep learning performance for detection and classification of microcalcifications on mammography

BACKGROUND

Breast cancer screening through mammography is crucial for early detection, yet the demand for mammography services surpasses the capacity of radiologists. Artificial intelligence (AI) can assist in evaluating microcalcifications on mammography. We developed and tested an AI model for localizing and characterizing microcalcifications.

METHODS

Three expert radiologists annotated a dataset of mammograms using histology-based ground truth. The dataset was partitioned for training, validation, and testing. Three neural networks (AlexNet, ResNet18, and ResNet34) were trained and evaluated using specific metrics including receiver operating characteristics area under the curve (AUC), sensitivity, and specificity. The reported metrics were computed on the test set (10% of the whole dataset).

RESULTS

The dataset included 1,000 patients aged 21-73 years and 1,986 mammograms (180 density A, 220 density B, 380 density C, and 220 density D), with 389 malignant and 611 benign groups of microcalcifications. AlexNet achieved the best performance with 0.98 sensitivity, 0.89 specificity of, and 0.98 AUC for microcalcifications detection and 0.85 sensitivity, 0.89 specificity, and 0.94 AUC of for microcalcifications classification. For microcalcifications detection, ResNet18 and ResNet34 achieved 0.96 and 0.97 sensitivity, 0.91 and 0.90 specificity and 0.98 and 0.98 AUC, retrospectively. For microcalcifications classification, ResNet18 and ResNet34 exhibited 0.75 and 0.84 sensitivity, 0.85 and 0.84 specificity, and 0.88 and 0.92 AUC, respectively.

CONCLUSIONS

The developed AI models accurately detect and characterize microcalcifications on mammography.

RELEVANCE STATEMENT

AI-based systems have the potential to assist radiologists in interpreting microcalcifications on mammograms. The study highlights the importance of developing reliable deep learning models possibly applied to breast cancer screening.

KEY POINTS

• A novel AI tool was developed and tested to aid radiologists in the interpretation of mammography by accurately detecting and characterizing microcalcifications. • Three neural networks (AlexNet, ResNet18, and ResNet34) were trained, validated, and tested using an annotated dataset of 1,000 patients and 1,986 mammograms. • The AI tool demonstrated high accuracy in detecting/localizing and characterizing microcalcifications on mammography, highlighting the potential of AI-based systems to assist radiologists in the interpretation of mammograms.

Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography

OBJECTIVE

We aimed to evaluate the false interpretations between artificial intelligence (AI) and radiologists in screening mammography to get a better understanding of how the distribution of diagnostic mistakes might change when moving from entirely radiologist-driven to AI-integrated breast cancer screening.

METHODS AND MATERIALS

This retrospective case-control study was based on a mammography screening cohort from 2008 to 2015. The final study population included screening examinations for 714 women diagnosed with breast cancer and 8029 randomly selected healthy controls. Oversampling of controls was applied to attain a similar cancer proportion as in the source screening cohort. We examined how false-positive (FP) and false-negative (FN) assessments by AI, the first reader (RAD 1) and the second reader (RAD 2), were associated with age, density, tumor histology and cancer invasiveness in a single- and double-reader setting.

RESULTS

For each reader, the FN assessments were distributed between low- and high-density females with 53 (42%) and 72 (58%) for AI; 59 (36%) and 104 (64%) for RAD 1 and 47 (36%) and 84 (64%) for RAD 2. The corresponding numbers for FP assessments were 1820 (47%) and 2016 (53%) for AI; 1568 (46%) and 1834 (54%) for RAD 1 and 1190 (43%) and 1610 (58%) for RAD 2. For ductal cancer, the FN assessments were 79 (77%) for AI CAD; with 120 (83%) for RAD 1 and with 96 (16%) for RAD 2. For the double-reading simulation, the FP assessments were distributed between younger and older females with 2828 (2.5%) and 1554 (1.4%) for RAD 1 + RAD 2; 3850 (3.4%) and 2940 (2.6%) for AI+RAD 1 and 3430 (3%) and 2772 (2.5%) for AI+RAD 2.

CONCLUSION

The most pronounced decrease in FN assessments was noted for females over the age of 55 and for high density-women. In conclusion, AI could have an important complementary role when combined with radiologists to increase sensitivity for high-density and older females.

ADVANCES IN KNOWLEDGE

Our results highlight the potential impact of integrating AI in breast cancer screening, particularly to improve interpretation accuracy. The use of AI could enhance screening outcomes for high-density and older females.

Mammography Breast Cancer Screening Triage Using Deep Learning: A UK Retrospective Study

Background Breast screening enables early detection of cancers; however, most women have normal mammograms, resulting in repetitive and resource-intensive reading tasks. Purpose To investigate if deep learning (DL) algorithms can be used to triage mammograms by identifying normal results to reduce workload or flag cancers that may be overlooked. Materials and Methods In this retrospective study, three commercial DL algorithms were investigated using consecutive mammograms from two UK Breast Screening Program sites from January 2015 to December 2017 and January 2017 to December 2018 on devices from two mammography vendors. Normal mammograms with a 3-year follow-up and histopathologically proven cancer detected at screening, the subsequent round, or in the 3-year interval were included. Two algorithm thresholds were set: in scenario A, 99.0% sensitivity for rule-out triage to a lone reader, and in scenario B, approximately 1.0% additional recall providing a rule-in triage for further assessment. Both thresholds were then applied to the screening workflow in scenario C. The sensitivity and specificity were used to assess the overall predictive performance of each DL algorithm. Results The data set comprised 78 849 patients (median age, 59 years [IQR, 53-63 years]) and 887 screening-detected, 439 interval, and 688 subsequent screening round-detected cancers. In scenario A (rule-out triage), models DL-1, DL-2, and DL-3 triaged 35.0% (27 565 of 78 849), 53.2% (41 937 of 78 849), and 55.6% (43 869 of 78 849) of mammograms, respectively, with 0.0% (0 of 887) to 0.1% (one of 887) of screening-detected cancers undetected. In scenario B, DL algorithms triaged in 4.6% (20 of 439) to 8.2% (36 of 439) of interval and 5.2% (36 of 688) to 6.1% (42 of 688) of subsequent-round cancers when applied after the routine double-reading workflow. Combining both approaches in scenario C resulted in an overall noninferior specificity (difference, -0.9%; P < .001) and superior sensitivity (difference, 2.7%; P < .001) for the adaptive workflow compared with routine double reading for all three algorithms. Conclusion Rule-out and rule-in DL-adapted triage workflows can improve the efficiency and efficacy of mammography breast cancer screening. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Nishikawa and Lu in this issue.

Use of novel artificial intelligence computer-assisted detection (AI-CAD) for screening mammography: an analysis of 17,884 consecutive two-view full-field digital mammography screening exams

BACKGROUND

Novel artificial intelligence computer-assisted detection (AI-CAD) systems based on deep learning (DL) promise to support screen reading.

PURPOSE

To test a DL-AI-CAD system compared to human reading on consecutive screening mammograms.

MATERIAL AND METHODS

In this retrospective study, 17,884 consecutive anonymized screening mammograms, double-read from January to November 2018, were processed by the DL-AI-CAD system. AI-CAD reading was considered positive if the AI-CAD case scores exceeded 30 (range = 1-100) and the lesion was correctly marked. Likewise, human reading (R1 or R2, respectively) was considered positive if the lesion was correctly identified and called. Receiver operating characteristic (ROC) analysis was performed and accuracy data were calculated. Ground truth for benign lesions: absence of malignancy after cancer registry matching (2022); for malignancy: histopathologic proof; evaluation was patient-based.

RESULTS

In total, 114 screen-detected and 17 interval cancers (ICA) occurred. ROC analysis of screen-detected cancers yielded an AUC of 89% for AI-CAD. Sensitivity/specificity was 81.7%/80.2% for AI-CAD; 77.1%/91.7% for R1; 78.6/91.6% for R2. Combining each human reading with AI-CAD was as sensitive as human double-reading (all approximately 88%), but less specific (approximately 75%) compared to human double-reading (approximately 87%). These AI-CAD combinations required consensus readings for twice as many cases as the human combination. Four of 17 ICA exceeded a case score of 30; two of four CAD correctly marked the quadrant of the subsequent ICA.

CONCLUSION

Including ICA cases, this AI-CAD achieved comparable sensitivity to human reading at lower specificity. Combining human reading and AI-CAD allows increasing sensitivity compared to single-reading.

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.

Artificial intelligence in breast imaging: Current situation and clinical challenges

Breast cancer ranks among the most prevalent malignant tumours and is the primary contributor to cancer-related deaths in women. Breast imaging is essential for screening, diagnosis, and therapeutic surveillance. With the increasing demand for precision medicine, the heterogeneous nature of breast cancer makes it necessary to deeply mine and rationally utilize the tremendous amount of breast imaging information. With the rapid advancement of computer science, artificial intelligence (AI) has been noted to have great advantages in processing and mining of image information. Therefore, a growing number of scholars have started to focus on and research the utility of AI in breast imaging. Here, an overview of breast imaging databases and recent advances in AI research are provided, the challenges and problems in this field are discussed, and then constructive advice is further provided for ongoing scientific developments from the perspective of the National Natural Science Foundation of China.

Overview of trials on artificial intelligence algorithms in breast cancer screening - A roadmap for international evaluation and implementation

Accumulating evidence from retrospective studies demonstrate at least non-inferior performance when using AI algorithms with different strategies versus double-reading in mammography screening. In addition, AI algorithms for mammography screening can reduce work load by moving to single human reading. Prospective trials are essential to avoid unintended adverse consequences before incorporation of AI algorithms into UK's National Health Service (NHS) Breast Screening Programme (BSP). A stakeholders' meeting was organized in Newnham College, Cambridge, UK to undertake a review of the current evidence to enable consensus discussion on next steps required before implementation into a screening programme. It was concluded that a multicentre multivendor testing platform study with opt-out consent is preferred. AI thresholds from different vendors should be determined while maintaining non-inferior screening performance results, particularly ensuring recall rates are not increased. Automatic recall of cases using an agreed high sensitivity AI score versus automatic rule out with a low AI score set at a high sensitivity could be used. A human reader should still be involved in decision making with AI-only recalls requiring human arbitration. Standalone AI algorithms used without prompting maintain unbiased screening reading performance, but reading with prompts should be tested prospectively and ideally provided for arbitration.

AI Risk Score on Screening Mammograms Preceding Breast Cancer Diagnosis

Background Few studies have evaluated the role of artificial intelligence (AI) in prior screening mammography. Purpose To examine AI risk scores assigned to screening mammography in women who were later diagnosed with breast cancer. Materials and Methods Image data and screening information of examinations performed from January 2004 to December 2019 as part of BreastScreen Norway were used in this retrospective study. Prior screening examinations from women who were later diagnosed with cancer were assigned an AI risk score by a commercially available AI system (scores of 1-7, low risk of malignancy; 8-9, intermediate risk; and 10, high risk of malignancy). Mammographic features of the cancers based on the AI score were also assessed. The association between AI score and mammographic features was tested with a bivariate test. Results A total of 2787 prior screening examinations from 1602 women (mean age, 59 years ± 5.1 [SD]) with screen-detected (n = 1016) or interval (n = 586) cancers showed an AI risk score of 10 for 389 (38.3%) and 231 (39.4%) cancers, respectively, on the mammograms in the screening round prior to diagnosis. Among the screen-detected cancers with AI scores available two screening rounds (4 years) before diagnosis, 23.0% (122 of 531) had a score of 10. Mammographic features were associated with AI score for invasive screen-detected cancers (P < .001). Density with calcifications was registered for 13.6% (43 of 317) of screen-detected cases with a score of 10 and 4.6% (15 of 322) for those with a score of 1-7. Conclusion More than one in three cases of screen-detected and interval cancers had the highest AI risk score at prior screening, suggesting that the use of AI in mammography screening may lead to earlier detection of breast cancers. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Mehta in this issue.

Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model

OBJECTIVES

The aim of the study is to develop and evaluate the performance of a deep learning (DL) model to triage breast magnetic resonance imaging (MRI) findings in high-risk patients without missing any cancers.

MATERIALS AND METHODS

In this retrospective study, 16,535 consecutive contrast-enhanced MRIs performed in 8354 women from January 2013 to January 2019 were collected. From 3 New York imaging sites, 14,768 MRIs were used for the training and validation data set, and 80 randomly selected MRIs were used for a reader study test data set. From 3 New Jersey imaging sites, 1687 MRIs (1441 screening MRIs and 246 MRIs performed in recently diagnosed breast cancer patients) were used for an external validation data set. The DL model was trained to classify maximum intensity projection images as "extremely low suspicion" or "possibly suspicious." Deep learning model evaluation (workload reduction, sensitivity, specificity) was performed on the external validation data set, using a histopathology reference standard. A reader study was performed to compare DL model performance to fellowship-trained breast imaging radiologists.

RESULTS

In the external validation data set, the DL model triaged 159/1441 of screening MRIs as "extremely low suspicion" without missing a single cancer, yielding a workload reduction of 11%, a specificity of 11.5%, and a sensitivity of 100%. The model correctly triaged 246/246 (100% sensitivity) of MRIs in recently diagnosed patients as "possibly suspicious." In the reader study, 2 readers classified MRIs with a specificity of 93.62% and 91.49%, respectively, and missed 0 and 1 cancer, respectively. On the other hand, the DL model classified MRIs with a specificity of 19.15% and missed 0 cancers, highlighting its potential use not as an independent reader but as a triage tool.

CONCLUSIONS

Our automated DL model triages a subset of screening breast MRIs as "extremely low suspicion" without misclassifying any cancer cases. This tool may be used to reduce workload in standalone mode, to shunt low suspicion cases to designated radiologists or to the end of the workday, or to serve as base model for other downstream AI tools.

'Earlier than Early' Detection of Breast Cancer in Israeli BRCA Mutation Carriers Applying AI-Based Analysis to Consecutive MRI Scans

Female BRCA1/BRCA2 (=BRCA) pathogenic variants (PVs) carriers are at a substantially higher risk for developing breast cancer (BC) compared with the average risk population. Detection of BC at an early stage significantly improves prognosis. To facilitate early BC detection, a surveillance scheme is offered to BRCA PV carriers from age 25-30 years that includes annual MRI based breast imaging. Indeed, adherence to the recommended scheme has been shown to be associated with earlier disease stages at BC diagnosis, more in-situ pathology, smaller tumors, and less axillary involvement. While MRI is the most sensitive modality for BC detection in BRCA PV carriers, there are a significant number of overlooked or misinterpreted radiological lesions (mostly enhancing foci), leading to a delayed BC diagnosis at a more advanced stage. In this study we developed an artificial intelligence (AI)-network, aimed at a more accurate classification of enhancing foci, in MRIs of BRCA PV carriers, thus reducing false-negative interpretations. Retrospectively identified foci in prior MRIs that were either diagnosed as BC or benign/normal in a subsequent MRI were manually segmented and served as input for a convolutional network architecture. The model was successful in classification of 65% of the cancerous foci, most of them triple-negative BC. If validated, applying this scheme routinely may facilitate 'earlier than early' BC diagnosis in BRCA PV carriers.

Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis

Background There is considerable interest in the potential use of artificial intelligence (AI) systems in mammographic screening. However, it is essential to critically evaluate the performance of AI before it can become a modality used for independent mammographic interpretation. Purpose To evaluate the reported standalone performances of AI for interpretation of digital mammography and digital breast tomosynthesis (DBT). Materials and Methods A systematic search was conducted in PubMed, Google Scholar, Embase (Ovid), and Web of Science databases for studies published from January 2017 to June 2022. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) values were reviewed. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Comparative (QUADAS-2 and QUADAS-C, respectively). A random effects meta-analysis and meta-regression analysis were performed for overall studies and for different study types (reader studies vs historic cohort studies) and imaging techniques (digital mammography vs DBT). Results In total, 16 studies that include 1 108 328 examinations in 497 091 women were analyzed (six reader studies, seven historic cohort studies on digital mammography, and four studies on DBT). Pooled AUCs were significantly higher for standalone AI than radiologists in the six reader studies on digital mammography (0.87 vs 0.81, P = .002), but not for historic cohort studies (0.89 vs 0.96, P = .152). Four studies on DBT showed significantly higher AUCs in AI compared with radiologists (0.90 vs 0.79, P < .001). Higher sensitivity and lower specificity were seen for standalone AI compared with radiologists. Conclusion Standalone AI for screening digital mammography performed as well as or better than radiologists. Compared with digital mammography, there is an insufficient number of studies to assess the performance of AI systems in the interpretation of DBT screening examinations. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Scaranelo in this issue.

Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload

OBJECTIVE

To evaluate the effectiveness of a new strategy for using artificial intelligence (AI) as supporting reader for the detection of breast cancer in mammography-based double reading screening practice.

METHODS

Large-scale multi-site, multi-vendor data were used to retrospectively evaluate a new paradigm of AI-supported reading. Here, the AI served as the second reader only if it agrees with the recall/no-recall decision of the first human reader. Otherwise, a second human reader made an assessment followed by the standard clinical workflow. The data included 280 594 cases from 180 542 female participants screened for breast cancer at seven screening sites in two countries and using equipment from four hardware vendors. The statistical analysis included non-inferiority and superiority testing of cancer screening performance and evaluation of the reduction in workload, measured as arbitration rate and number of cases requiring second human reading.

RESULTS

Artificial intelligence as a supporting reader was found to be superior or noninferior on all screening metrics compared with human double reading while reducing the number of cases requiring second human reading by up to 87% (245 395/280 594). Compared with AI as an independent reader, the number of cases referred to arbitration was reduced from 13% (35 199/280 594) to 2% (5056/280 594).

CONCLUSION

The simulation indicates that the proposed workflow retains screening performance of human double reading while substantially reducing the workload. Further research should study the impact on the second human reader because they would only assess cases in which the AI prediction and first human reader disagree.

Quality control system for mammographic breast positioning using deep learning

This study proposes a deep convolutional neural network (DCNN) classification for the quality control and validation of breast positioning criteria in mammography. A total of 1631 mediolateral oblique mammographic views were collected from an open database. We designed two main steps for mammographic verification: automated detection of the positioning part and classification of three scales that determine the positioning quality using DCNNs. After acquiring labeled mammograms with three scales visually evaluated based on guidelines, the first step was automatically detecting the region of interest of the subject part by image processing. The next step was classifying mammographic positioning accuracy into three scales using four representative DCNNs. The experimental results showed that the DCNN model achieved the best positioning classification accuracy of 0.7836 using VGG16 in the inframammary fold and a classification accuracy of 0.7278 using Xception in the nipple profile. Furthermore, using the softmax function, the breast positioning criteria could be evaluated quantitatively by presenting the predicted value, which is the probability of determining positioning accuracy. The proposed method can be quantitatively evaluated without the need for an individual qualitative evaluation and has the potential to improve the quality control and validation of breast positioning criteria in mammography.

Ethics of Artificial Intelligence in Breast Imaging

There is great interest in the development of artificial intelligence (AI) applications for medical imaging in general and specifically in breast imaging. Because of the scale of application and the potential for harm, there has been a parallel interest in assuring that these new technologies are scrutinized and applied in ethical ways. The four principles of autonomy, beneficence, non-maleficence, and justice are widely accepted as a framework for bioethical analysis. We incorporate a fifth principle of explicability (adapted from Floridi and Cowls) because of the unique considerations of AI. We review definitions of each of these principles and provide examples of their practical application to breast imaging.

Artificial intelligence in BreastScreen Norway: a retrospective analysis of a cancer-enriched sample including 1254 breast cancer cases

OBJECTIVES

To compare results of selected performance measures in mammographic screening for an artificial intelligence (AI) system versus independent double reading by radiologists.

METHODS

In this retrospective study, we analyzed data from 949 screen-detected breast cancers, 305 interval cancers, and 13,646 negative examinations performed in BreastScreen Norway during the period from 2010 to 2018. An AI system scored the examinations from 1 to 10, based on the risk of malignancy. Results from the AI system were compared to screening results after independent double reading. AI score 10 was set as the threshold. The results were stratified by mammographic density.

RESULTS

A total of 92.7% of the screen-detected and 40.0% of the interval cancers had an AI score of 10. Among women with a negative screening outcome, 9.1% had an AI score of 10. For women with the highest breast density, the AI system scored 100% of the screen-detected cancers and 48.6% of the interval cancers with an AI score of 10, which resulted in a sensitivity of 80.9% for women with the highest breast density for the AI system, compared to 62.8% for independent double reading. For women with screen-detected cancers who had prior mammograms available, 41.9% had an AI score of 10 at the prior screening round.

CONCLUSIONS

The high proportion of cancers with an AI score of 10 indicates a promising performance of the AI system, particularly for women with dense breasts. Results on prior mammograms with AI score 10 illustrate the potential for earlier detection of breast cancers by using AI in screen-reading.

KEY POINTS

• The AI system scored 93% of the screen-detected cancers and 40% of the interval cancers with AI score 10. • The AI system scored all screen-detected cancers and almost 50% of interval cancers among women with the highest breast density with AI score 10. • About 40% of the screen-detected cancers had an AI score of 10 on the prior mammograms, indicating a potential for earlier detection by using AI in screen-reading.

Performance evaluation methods for improvements at post-market of artificial intelligence/machine learning-based computer-aided detection/diagnosis/triage in the United States

Computer-aided detection (CADe), computer-aided diagnosis (CADx), and computer-aided simple triage (CAST), which incorporate artificial intelligence (AI) and machine learning (ML), are continually undergoing post-market improvement. Therefore, understanding the evaluation and approval process of improved products is important. This study intended to conduct a comprehensive survey of AI/ML-based CAD products approved by the U.S. Food and Drug Administration (FDA) that had been improved post-market to gain insights into the efficacy and safety required for market approval. A survey of the product code database published by the FDA identified eight products that were improved post-market. The methods used to evaluate the performance of improvements were analysed, and post-market improvements were approved with retrospective data. Reader study testing (RT) or software standalone testing (SA) procedures were conducted retrospectively. Six RT procedures were conducted because of modifications to the intended use. An average of 17.3 readers (minimum 14, maximum 24) participated, and the area under the curve (AUC) was considered the primary endpoint. The addition of study learning data that did not change the intended use and changes in the analysis algorithm were evaluated by SA. The average sensitivity, specificity, and AUC were 93% (minimum 91.1, maximum 97), 89.6% (minimum 85.9, maximum 96), and 0.96 (minimum 0.96, maximum 0.97), respectively. The average interval between applications was 348 days (minimum -18, maximum 975), which showed that the improvements were implemented within approximately one year. This is the first comprehensive study on AI/ML-based CAD products that have been improved post-market to elucidate evaluation points for post-market improvements. The findings will be informative for the industry and academia in developing and improving AI/ML-based CAD.

Mammographically detected asymmetries in the era of artificial intelligence

Background

Proper assessment of mammographically detected asymmetries is essential to avoid unnecessary biopsies and missed cancers as they may be of a benign or malignant cause. According to ACR BIRADS atlas 2013, mammographically detected asymmetries are classified into asymmetry, focal asymmetry, global asymmetry, and developing asymmetry. We aimed to assess the diagnostic performance of artificial intelligence in mammographically detected asymmetries compared to breast ultrasound as well as combined mammography and ultrasound.

Results

This study was a prospective study that comprised 51 women with breast asymmetry found on screening as well as diagnostic mammography. All participants conducted full-field digital mammography and ultrasound. Then the obtained mammographic images were processed by the artificial intelligence software system. Mammography had a sensitivity of 100%, specificity of 73%, a positive predictive value of 56.52%, a negative predictive value of 100%, and diagnostic accuracy of 80%. The results of Ultrasound revealed a sensitivity of 100.00%, a specificity of 89.47%, a positive predictive value of 76.47%, a negative predictive value of 100.00%, and an accuracy of 92.16%. Combined mammography and breast ultrasound showed a sensitivity of 100.00%, a specificity of 86.84%, a positive predictive value of 72.22%, a negative predictive value of 100.00%, and an accuracy of 90.20%. Artificial intelligence results demonstrated a sensitivity of 84.62%, a specificity of 94.74%, a positive predictive value of 48.26%, a negative predictive value of 94.47%, and an accuracy of 92.16%.

Conclusions

Adding breast ultrasound in the assessment of mammographically detected asymmetries led to better characterization, so it reduced the false-positive results and improved the specificity. Also, Artificial intelligence showed better specificity compared to mammography, breast ultrasound, and combined Mammography and ultrasound, so AI can be used to decrease unnecessary biopsies as it increases confidence in diagnosis, especially in cases with no definite ultrasound suspicious abnormality.

Personalized breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence

Purpose

Breast cancer screening is predominantly performed using digital mammography (DM), but digital breast tomosynthesis (DBT) has higher sensitivity. DBT demands more resources than DM, and it might be more feasible to reserve DBT for women with a clear benefit from the technique. We explore if artificial intelligence (AI) can select women who would benefit from DBT imaging.

Approach

We used data from Malmö Breast Tomosynthesis Screening Trial, where all women prospectively were examined with separately double read DM and DBT. We retrospectively analyzed DM examinations (n = 14768 ) with a breast cancer detection system and used the provided risk score (1 to 10) for risk stratification. We tested how different score thresholds for adding DBT to an initial DM affects the number of detected cancers, additional DBT examinations needed, detection rate, and false positives.

Results

If using a threshold of 9.0, 25 (26%) more cancers would be detected compared to using DM alone. Of the 41 cancers only detected on DBT, 61% would be detected, with only 1797 (12%) of the women examined with both DM and DBT. The detection rate for the added DBT would be 14/1000 women, whereas the false-positive recalls would be increased with 58 (21%).

Conclusion

Using DBT only for selected high gain cases could be an alternative to complete DBT screening. AI can analyze initial DM images to identify high gain cases where DBT can be added during the same visit. There might be logistical challenges, and further studies in a prospective setting are necessary.

Comparison of Diagnostic Performance in Mammography Assessment: Radiologist with Reference to Clinical Information Versus Standalone Artificial Intelligence Detection

We compared diagnostic performances between radiologists with reference to clinical information and standalone artificial intelligence (AI) detection of breast cancer on digital mammography. This study included 392 women (average age: 57.3 ± 12.1 years, range: 30−94 years) diagnosed with malignancy between January 2010 and June 2021 who underwent digital mammography prior to biopsy. Two radiologists assessed mammographic findings based on clinical symptoms and prior mammography. All mammographies were analyzed via AI. Breast cancer detection performance was compared between radiologists and AI based on how the lesion location was concordant between each analysis method (radiologists or AI) and pathological results. Kappa coefficient was used to measure the concordance between radiologists or AI analysis and pathology results. Binominal logistic regression analysis was performed to identify factors influencing the concordance between radiologists’ analysis and pathology results. Overall, the concordance was higher in radiologists’ diagnosis than on AI analysis (kappa coefficient: 0.819 vs. 0.698). Impact of prior mammography (odds ratio (OR): 8.55, p < 0.001), clinical symptom (OR: 5.49, p < 0.001), and fatty breast density (OR: 5.18, p = 0.008) were important factors contributing to the concordance of lesion location between radiologists’ diagnosis and pathology results.

Breast cancer screening with digital breast tomosynthesis: comparison of different reading strategies implementing artificial intelligence

Objectives

Digital breast tomosynthesis (DBT) can detect more cancers than the current standard breast screening method, digital mammography (DM); however, it can substantially increase the reading workload and thus hinder implementation in screening. Artificial intelligence (AI) might be a solution. The aim of this study was to retrospectively test different ways of using AI in a screening workflow.

Methods

An AI system was used to analyse 14,772 double-read single-view DBT examinations from a screening trial with paired DM double reading. Three scenarios were studied: if AI can identify normal cases that can be excluded from human reading; if AI can replace the second reader; if AI can replace both readers. The number of detected cancers and false positives was compared with DM or DBT double reading.

Results

By excluding normal cases and only reading 50.5% (7460/14,772) of all examinations, 95% (121/127) of the DBT double reading detected cancers could be detected. Compared to DM screening, 27% (26/95) more cancers could be detected (p < 0.001) while keeping recall rates at the same level. With AI replacing the second reader, 95% (120/127) of the DBT double reading detected cancers could be detected—26% (25/95) more than DM screening (p < 0.001)—while increasing recall rates by 53%. AI alone with DBT has a sensitivity similar to DM double reading (p = 0.689).

Conclusion

AI can open up possibilities for implementing DBT screening and detecting more cancers with the total reading workload unchanged. Considering the potential legal and psychological implications, replacing the second reader with AI would probably be most the feasible approach.

Key Points

• Breast cancer screening with digital breast tomosynthesis and artificial intelligence can detect more cancers than mammography screening without increasing screen-reading workload.

• Artificial intelligence can either exclude low-risk cases from double reading or replace the second reader.

• Retrospective study based on paired mammography and digital breast tomosynthesis screening data.

Insight into breast cancer detection: new hybrid feature selection method

Breast cancer, which is also the leading cause of death among women, is one of the most common forms of the disease that affects females all over the world. The discovery of breast cancer at an early stage is extremely important because it allows selecting appropriate treatment protocol and thus, stops the development of cancer cells. In this paper, a new patients detection strategy has been presented to identify patients with the disease earlier. The proposed strategy composes of two parts which are data preprocessing phase and patient detection phase (PDP). The purpose of this study is to introduce a feature selection methodology for determining the most efficient and significant features for identifying breast cancer patients. This method is known as new hybrid feature selection method (NHFSM). NHFSM is made up of two modules which are quick selection module that uses information gain, and feature selection module that uses hybrid bat algorithm and particle swarm optimization. Consequently, NHFSM is a hybrid method that combines the advantages of bat algorithm and particle swarm optimization based on filter method to eliminate many drawbacks such as being stuck in a local optimal solution and having unbalanced exploitation. The preprocessed data are then used during PDP in order to enable a quick and accurate detection of patients. Based on experimental results, the proposed NHFSM improves the efficiency of patients’ classification in comparison with state-of-the-art feature selection approaches by roughly 0.97, 0.76, 0.75, and 0.716 in terms of accuracy, precision, sensitivity/recall, and F-measure. In contrast, it has the lowest error rate value of 0.03.

Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort

Objective

This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment.

Materials and Methods

This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI).

Results

Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity.

Conclusion

This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

Evaluation of an artificial intelligence support system for breast cancer screening in Chinese people based on mammogram

BACKGROUND

To evaluate the diagnostic performance of radiologists on breast cancer with or without artificial intelligence (AI) support.

METHODS

A retrospective study was performed. In total, 643 mammograms (average age: 54 years; female: 100%; cancer: 62.05%) were randomly allocated into two groups. Seventy-five percent of mammograms in each group were randomly selected for assessment by two independent radiologists, and the rest were read once. Half of the 71 radiologists could read mammograms with AI support, and the other half could not. Sensitivity, specificity, Youden's index, agreement rate, Kappa value, the area under the receiver operating characteristic curve (AUC) and the reading time of radiologists in each group were analyzed.

RESULTS

The average AUC was higher if the AI support system was used (unaided: 0.84; with AI support: 0.91; p < 0.01). The average sensitivity increased from 84.77% to 95.07% with AI support (p < 0.01), but the average specificity decreased (p = 0.07). Youden's index, agreement rate and Kappa value were larger in the group with AI support, and the average reading time was shorter (p < 0.01).

CONCLUSIONS

The AI support system might contribute to enhancing the diagnostic performance (e.g., higher sensitivity and AUC) of radiologists. In the future, the AI algorithm should be improved, and prospective studies should be conducted.

Does artificial intelligence aid in the detection of different types of breast cancer?

Background

On mammography many cancers may be missed even in retrospect either due to the breast density, the small size of the tumor or the subtle signs of cancer that are imperceptible. We aimed to compare the sensitivity of artificial intelligence (AI) to that of digital mammography in the detection of different types of breast cancer. Also, the sensitivity of AI in picking up the different breast cancer morphologies namely mass, pathological calcifications, asymmetry, and distortion was assessed. Tissue biopsy and pathology were used as the standard reference. The study included 123 female patients with 134 proved carcinoma. All patients underwent digital mammogram (DM) examination scanned with artificial intelligence algorithm.

Results

AI achieved higher sensitivity than mammography in detecting malignant breast lesions. The sensitivity of AI was 96.6%, and false negative rate was 3.4%, while mammography sensitivity was 87.3% and false negative rate 12.7%. Our study showed AI performed better than mammography in detecting ductal carcinoma in situ and invasive lobular carcinoma with sensitivity (100% and 96.6%) vs (88.9% and 82.2%) respectively. AI was more sensitive to detect cancers presented with suspicious mass 95.2% vs 75%, suspicious calcifications 100% vs 86.5% and asymmetry and distortion 100% vs 84.6%, than mammography.

Conclusions

AI showed potential values to overcome mammographic limitations in the detection of breast cancer even those with challenging morphology as invasive lobular carcinoma, ductal carcinoma in situ, tubular carcinoma and micropapillary carcinoma.