Retrospective analysis of the effect on interval cancer rate of adding an artificial intelligence algorithm to the reading process for two-dimensional full-field digital mammography

Journal of Medical Screening ◽

10.1177/0969141320988049 ◽

2021 ◽

pp. 096914132098804

Author(s):

Axel Graewingholt ◽

Paolo Giorgi Rossi

Keyword(s):

Breast Cancer ◽

Artificial Intelligence ◽

Cancer Screening ◽

Confidence Interval ◽

Digital Mammography ◽

Interval Cancer ◽

Interval Cancers ◽

Cancer Rate ◽

Interval Cancer Rate ◽

Artificial Intelligence Algorithm

Interval cancers are a commonly seen problem in organized breast cancer screening programs and their rate is measured for quality assurance. Artificial intelligence algorithms have been proposed to improve mammography sensitivity, in which case it is likely that the interval cancer rate would decrease and the quality of the screening system could be improved. Interval cancers from negative screening in 2011 and 2012 of one regional unit of the national German breast cancer screening program were classified by a group of radiologists, categorizing the screening digital mammography with diagnostic images as true interval, minimal signs, false negative and occult cancer. Screening mammograms were processed using a detection algorithm based on deep learning. Of the 29 cancer cases available, artificial intelligence identified eight out of nine of those classified as minimal signs, all six false negatives and none of the true interval and occult cancers. Sensitivity for lesions judged to be already present in screening mammogram was 93% (95% confidence interval 68–100) and sensitivity for any interval cancer was 48% (95% confidence interval 29–67). Using an artificial intelligence algorithm as an additional reading tool has the potential to reduce interval cancers. How and if this theoretical advantage can be reached without a negative effect on recall rate is a challenge for future research.

Download Full-text

Pathways to breast cancer screening artificial intelligence algorithm validation

The Breast ◽

10.1016/j.breast.2019.09.005 ◽

2020 ◽

Vol 52 ◽

pp. 146-149 ◽

Cited By ~ 3

Author(s):

Christoph I. Lee ◽

Nehmat Houssami ◽

Joann G. Elmore ◽

Diana S.M. Buist

Keyword(s):

Breast Cancer ◽

Artificial Intelligence ◽

Cancer Screening ◽

Breast Cancer Screening ◽

Intelligence Algorithm ◽

Algorithm Validation ◽

Artificial Intelligence Algorithm

Download Full-text

Impact of Full-Field Digital Mammography Versus Film-Screen Mammography in Population Screening: A Meta-Analysis

JNCI Journal of the National Cancer Institute ◽

10.1093/jnci/djaa080 ◽

2020 ◽

Vol 113 (1) ◽

pp. 16-26 ◽

Cited By ~ 1

Author(s):

Rachel Farber ◽

Nehmat Houssami ◽

Sally Wortley ◽

Gemma Jacklyn ◽

Michael L Marinovich ◽

...

Keyword(s):

Health Outcomes ◽

Cancer Detection ◽

Digital Mammography ◽

Meta Analysis ◽

Interval Cancer ◽

Population Screening ◽

Cancer Rate ◽

Screening Programs ◽

Interval Cancer Rate ◽

Cancer Rates

Abstract Background Breast screening programs replaced film mammography with digital mammography, and the effects of this practice shift in population screening on health outcomes can be measured through examination of cancer detection and interval cancer rates. Methods A systematic review and random effects meta-analysis were undertaken. Seven databases were searched for publications that compared film with digital mammography within the same population of asymptomatic women and reported cancer detection and/or interval cancer rates. Results The analysis included 24 studies with 16 583 743 screening examinations (10 968 843 film and 5 614 900 digital). The pooled difference in the cancer detection rate showed an increase of 0.51 per 1000 screens (95% confidence interval [CI] = 0.19 to 0.83), greater relative increase for ductal carcinoma in situ (25.2%, 95% CI = 17.4% to 33.5%) than invasive (4%, 95% CI = −3% to 13%), and a recall rate increase of 6.95 (95% CI = 3.47 to 10.42) per 1000 screens after the transition from film to digital mammography. Seven studies (80.8% of screens) reported interval cancers: the pooled difference showed no change in the interval cancer rate with −0.02 per 1000 screens (95% CI = −0.06 to 0.03). Restricting analysis to studies at low risk of bias resulted in findings consistent with the overall pooled results for all outcomes. Conclusions The increase in cancer detection following the practice shift to digital mammography did not translate into a reduction in the interval cancer rate. Recall rates were increased. These results suggest the transition from film to digital mammography did not result in health benefits for screened women. This analysis reinforces the need to carefully evaluate effects of future changes in technology, such as tomosynthesis, to ensure new technology leads to improved health outcomes and beyond technical gains.

Download Full-text

Breast MRI screening of women at average risk of breast cancer: An observational cohort study.

Journal of Clinical Oncology ◽

10.1200/jco.2015.33.28_suppl.1 ◽

2015 ◽

Vol 33 (28_suppl) ◽

pp. 1-1 ◽

Cited By ~ 2

Author(s):

Christiane K. Kuhl ◽

Heribert Bieling ◽

Kevin Strobel ◽

Claudia Leutner ◽

Hans H Schild ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Detection ◽

Detection Rate ◽

False Positive Rate ◽

Interval Cancer ◽

Breast Mri ◽

Cancer Detection Rate ◽

Average Risk ◽

Cancer Rate ◽

Interval Cancer Rate

1 Background: Breast-MRI is currently recommended for screening women at high-risk of breast-cancer only. However, despite decades of mammographic-screening, breast-cancer continues to represent a major cause of cancer-death also for women at average-risk – suggesting a need for improved methods for early diagnosis also for these women. Therefore, we investigated the utility of supplemental MRI-screening of women who carry an average-risk of breast-cancer. Methods: Prospective observational cohort-study conducted in two academic breast-centers on asymptomatic women at average-risk in the usual age range for screening-mammography (40 to 70). Women underwent DCE-breast-MRI in addition to mammography every 12, 24, or 36 months, plus follow-up of 2 years to establish a standard-of-reference. We report on the supplemental-cancer-yield, interval-cancer-rate, diagnostic accuracy of screening-MRI, and biologic profiles of additional, MRI-detected breast-cancers. Results: 2120 women underwent a total 3861 MRI-studies covering 7007 women-years. Breast-cancer was diagnosed in 61/2120 women (DCIS: 20, invasive: 41), and ADH/LIN in another 21. Interval-cancer-rate was 0%, irrespective of screening interval. Forty-eight women were diagnosed with breast-cancer at prevalence-screening by MRI alone (supplemental cancer-detection-rate: 22.6 per 1000); 13 women were diagnosed with breast-cancer in 1741 incidence-screening-rounds collected over 4887 women-years. A total 12 of these 13 incident cancers were diagnosed by screening-MRI alone (supplemental-cancer-detection-rate: 6.9 per 1000), one by MRI and mammography, none by mammography alone. Supplemental-cancer-detection-rate was independent of mammographic breast-density. Invasive cancers were small (mean size: 8mm), node-negative in 93.4%, ER/PR-negative in 32.8%, and de-differentiated in 41.7% at prevalence, and 46.0% at incidence-screening. Specificity of MRI-screening was 97.1%, False-Positive-Rate 2.9%. Conclusions: MRI-screening improves detection of biologically relevant breast-cancer in women at average-risk, and reduces the interval-cancer-rate down to 0%, at a low false-positive rate.

Download Full-text

Diagnostic performances of supplemental breast ultrasound screening in women with personal history of breast cancer

Acta Radiologica ◽

10.1177/0284185117725779 ◽

2017 ◽

Vol 59 (5) ◽

pp. 533-539 ◽

Cited By ~ 6

Author(s):

Sung Eun Song ◽

Nariya Cho ◽

Jung Min Chang ◽

A Jung Chu ◽

Ann Yi ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Detection ◽

Detection Rate ◽

Interval Cancer ◽

Cancer Detection Rate ◽

Personal History ◽

Ultrasound Screening ◽

Cancer Rate ◽

Interval Cancer Rate ◽

History Of

Background Supplemental breast ultrasonography (US) has been used as a surveillance imaging method in women with personal history of breast cancer (PHBC). However, there have been limited data regarding diagnostic performances. Purpose To evaluate diagnostic performances of supplemental breast US screening for women with PHBC and to compare with those for women without PHBC. Material and Methods Between 2011 and 2012, 12,230 supplemental US exams were performed in 12,230 women with negative mammograms: 6584 women with PHBC and 5646 women without PHBC. Cancer detection rate, interval cancer rate, abnormal interpretation rate, positive predictive values (PPVs), sensitivity, and specificity were calculated and compared. Results Overall cancer detection rate and first-year interval cancer rate were 1.80/1000 exams and 0.91/1000 negative exams, both of which were higher in women with PHBC than in women without PHBC (2.88 vs. 0.53 per 1000, P = 0.003; 1.50 vs. 0.20 per 1000, P = 0.027). Abnormal interpretation rate was lower in the women with PHBC than in women without PHBC (9.1% vs. 12.1%, P < 0.001). Sensitivity was not different (67.9% vs. 75.0%, P = 1.000), whereas specificity and PPV3 were higher in women with PHBC than in women without PHBC (91.2% vs. 88.0%, P < 0.001; 22.6% vs. 3.1%, P < 0.001). The majority of detected cancers in women with PHBC (78.9%, 15/19) were stage 0 or 1. Conclusion Supplemental breast US screening increases early stage second breast cancers with high specificity and PPV3 in women with PHBC, however, high interval cancer rate in younger women with PHBC should be noted.

Download Full-text

Artificial intelligence (AI) to enhance breast cancer screening: protocol for population-based cohort study of cancer detection

BMJ Open ◽

10.1136/bmjopen-2021-054005 ◽

2022 ◽

Vol 12 (1) ◽

pp. e054005

Author(s):

M Luke Marinovich ◽

Elizabeth Wylie ◽

William Lotter ◽

Alison Pearce ◽

Stacy M Carter ◽

...

Keyword(s):

Breast Cancer ◽

Artificial Intelligence ◽

Cancer Screening ◽

Breast Cancer Screening ◽

Cancer Detection ◽

Screening Programme ◽

Ethics Committee ◽

Population Screening ◽

Interval Cancers ◽

Double Reading

IntroductionArtiﬁcial intelligence (AI) algorithms for interpreting mammograms have the potential to improve the effectiveness of population breast cancer screening programmes if they can detect cancers, including interval cancers, without contributing substantially to overdiagnosis. Studies suggesting that AI has comparable or greater accuracy than radiologists commonly employ ‘enriched’ datasets in which cancer prevalence is higher than in population screening. Routine screening outcome metrics (cancer detection and recall rates) cannot be estimated from these datasets, and accuracy estimates may be subject to spectrum bias which limits generalisabilty to real-world screening. We aim to address these limitations by comparing the accuracy of AI and radiologists in a cohort of consecutive of women attending a real-world population breast cancer screening programme.Methods and analysisA retrospective, consecutive cohort of digital mammography screens from 109 000 distinct women was assembled from BreastScreen WA (BSWA), Western Australia’s biennial population screening programme, from November 2016 to December 2017. The cohort includes 761 screen-detected and 235 interval cancers. Descriptive characteristics and results of radiologist double-reading will be extracted from BSWA outcomes data collection. Mammograms will be reinterpreted by a commercial AI algorithm (DeepHealth). AI accuracy will be compared with that of radiologist single-reading based on the diﬀerence in the area under the receiver operating characteristic curve. Cancer detection and recall rates for combined AI–radiologist reading will be estimated by pairing the first radiologist read per screen with the AI algorithm, and compared with estimates for radiologist double-reading.Ethics and disseminationThis study has ethical approval from the Women and Newborn Health Service Ethics Committee (EC00350) and the Curtin University Human Research Ethics Committee (HRE2020-0316). Findings will be published in peer-reviewed journals and presented at national and international conferences. Results will also be disseminated to stakeholders in Australian breast cancer screening programmes and policy makers in population screening.

Download Full-text