Overdiagnosis in breast imaging

Evans, Andy; Vinnicombe, Sarah

doi:10.1016/j.breast.2016.10.011

Cited by 22 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This implies that using this AI system in screening is likely to maintain or increase the detection rate of in situ cancers, hence possibly adding to overdiagnosis [27]. On the other hand, of the cancers that were missed by AI, three out of seven were small, low-grade invasive tubular cancers, which in the light of overdiagnosis might not necessarily be a drawback [28]. Studies with other AI vendors have shown varying results; the sensitivity for calcifications can increase with the assistance of AI [10] or that AI seems to be more sensitive to invasive than in situ cancers [8].…”

Section: Discussionmentioning

confidence: 99%

Identifying normal mammograms in a large screening population using artificial intelligence

et al. 2020

View full text Add to dashboard Cite

Objectives To evaluate the potential of artificial intelligence (AI) to identify normal mammograms in a screening population. Methods In this retrospective study, 9581 double-read mammography screening exams including 68 screen-detected cancers and 187 false positives, a subcohort of the prospective population-based Malmö Breast Tomosynthesis Screening Trial, were analysed with a deep learning-based AI system. The AI system categorises mammograms with a cancer risk score increasing from 1 to 10. The effect on cancer detection and false positives of excluding mammograms below different AI risk thresholds from reading by radiologists was investigated. A panel of three breast radiologists assessed the radiographic appearance, type, and visibility of screen-detected cancers assigned low-risk scores (≤ 5). The reduction of normal exams, cancers, and false positives for the different thresholds was presented with 95% confidence intervals (CI). Results If mammograms scored 1 and 2 were excluded from screen-reading, 1829 (19.1%; 95% CI 18.3-19.9) exams could be removed, including 10 (5.3%; 95% CI 2.1-8.6) false positives but no cancers. In total, 5082 (53.0%; 95% CI 52.0-54.0) exams, including 7 (10.3%; 95% CI 3.1-17.5) cancers and 52 (27.8%; 95% CI 21.4-34.2) false positives, had low-risk scores. All, except one, of the seven screen-detected cancers with low-risk scores were judged to be clearly visible. Conclusions The evaluated AI system can correctly identify a proportion of a screening population as cancer-free and also reduce false positives. Thus, AI has the potential to improve mammography screening efficiency. Key Points • Retrospective study showed that AI can identify a proportion of mammograms as normal in a screening population. • Excluding normal exams from screening using AI can reduce false positives.

show abstract

Section: Discussionmentioning

confidence: 99%

Identifying normal mammograms in a large screening population using artificial intelligence

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Considering that TC has limited impact on outcome ( 3 , 8 , 18 , 33 – 36 ), several groups hypothesized that its detection could represent an example of overdiagnosis ( 37 ). However, Aulmann et al ( 38 ) provided the molecular evidence for a direct clonal relationship of flat epithelial atypia and low-grade ductal carcinoma in situ with TC, indicating their precursor role.…”

Section: Discussionmentioning

confidence: 99%

Clinical Relevance of Tubular Breast Carcinoma: Large Retrospective Study and Meta-Analysis

et al. 2021

View full text Add to dashboard Cite

Background: Tubular carcinoma (TC) is a low proliferative grade 1 (G1) breast cancer (BC). Despite its favorable outcome and allegedly lower aggressiveness, patients are treated like other luminal G1 BC, with radiotherapy (RT) and hormonal therapy (HT). We performed: (1) a retrospective study comparing a TC cohort and a control series of luminal G1 BC and (2) a systematic review and meta-analysis focused on TC outcome.Materials and Methods: We selected a series of 572 G1 luminal BC patients [111 TC, 350 not otherwise specified (NOS), and 111 special-type (ST) BC] with follow-up and clinico-pathological data, who underwent local excision followed by RT at Città della Salute e della Scienza Hospital, Turin. Moreover, 22 and 13 studies were included in qualitative and quantitative meta-analysis, respectively.Results: TCs were generally smaller (≤10 mm) (P < 0.001), with lower lymph node involvement (P < 0.001). TCs showed no local and/or distant recurrences, while 16 NOS and 2 ST relapsed (P = 0.036). Kaplan–Meier curves confirmed more favorable TC outcome (DFI: log-rank test P = 0.03). Meta-analysis data, including the results of our study, showed that the pooled DFI rate was 96.4 and 91.8% at 5 and 10 years, respectively. Meta-regression analyses did not show a significant influence of RT nor HT on the DFI at 10 years.Conclusions: Compared to the other G1 BCs, TCs have an excellent outcome. The meta-analysis shows that TC recurrences are infrequent, and HT and RT have limited influence on prognosis. Hence, accurate diagnosis of TC subtype is critical to ensuring a tailored treatment approach.

show abstract

“…The cumulative probabilities of false positive findings from screening mammography over 10 years of annual screening in the United States is as high as 61%, and can be up to 16% for a woman’s first mammogram 2 , 9 – 12 . The data range widely for estimated rates of breast cancer overdiagnosis, from 5% to 50%; contributing to this variability is the lack of consensus on the definition of overdiagnosis and how to measure it 13 . In addition to physical harms from unnecessary testing, procedures, or treatment, women can also experience significant psychological distress with false positive results.…”

Section: Screening Mammography In Average-risk Women: a Brief Summarymentioning

confidence: 99%

The Challenges of Screening Mammography in Racial/Ethnic Minority Populations in the United States: A mini-review and observations from a predominantly Hispanic community

McGuinness

Crew

2018

J Cancer Treat & Diagnosis

View full text Add to dashboard Cite

Screening mammography is recommended by U.S. medical organizations for breast cancer screening in average risk women because of its demonstrated reductions in breast cancer mortality. However, significant disparities in breast cancer screening utilization and mortality remain among racial/ethnic minorities. Efforts have appropriately been directed at increasing engagement with screening services in these populations, however, there is a dearth of data regarding false-positive rates and overdiagnosis in minority patients engaged in breast cancer screening. We recently examined screening practices among a predominantly Hispanic population presenting to an academic medical center in New York, NY, and found that approximately 53% of women experienced at least one false-positive mammography result over a median of 8.9 years of screening. We also observed that Hispanic women were more likely to screen annually than white women despite recommendations to screen less frequently. In this review, we briefly review the benefits and harms of screening mammography in average-risk women, namely, false-positive results and breast cancer overdiagnosis, followed by a discussion of the disparities in breast cancer screening and mortality among racial/ethnic minority populations. We then present our own recent observations and propose that future interventions among Hispanic and other minority populations could include patient- and provider-centered educational programs that focus on providing a balanced discussion of benefits and harms of screening mammography.

show abstract

Overdiagnosis in breast imaging

Cited by 22 publications

References 29 publications

Identifying normal mammograms in a large screening population using artificial intelligence

Identifying normal mammograms in a large screening population using artificial intelligence

Clinical Relevance of Tubular Breast Carcinoma: Large Retrospective Study and Meta-Analysis

The Challenges of Screening Mammography in Racial/Ethnic Minority Populations in the United States: A mini-review and observations from a predominantly Hispanic community

Contact Info

Product

Resources

About