Independent Double Reading Research Articles

Introduction of one-view tomosynthesis in population-based mammography screening: Impact on detection rate, interval cancer rate and false-positive rate.

To assess performance endpoints of a combination of digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) compared with FFDM only in breast cancer screening. This was a prospective population-based screening study, including eligible (50-69 years) women attending the Capital Region Mammography Screening Program in Denmark. All attending women were offered FFDM. A subgroup was consecutively allocated to a screening room with DBT. All FFDM and DBT underwent independent double reading, and all women were followed up for 2 years after screening date or until next screening date, whichever came first. 6353 DBT + FFDM and 395 835 FFDM were included in the analysis and were undertaken in 196 267 women in the period from 1 November 2012 to 12 December 2018. Addition of DBT increased sensitivity: 89.9% (95% confidence interval (CI): 81.0-95.5) for DBT + FFDM and 70.1% (95% CI: 68.6-71.6) for FFDM only, p < 0.001. Specificity remained similar: 98.2% (95% CI: 97.9-98.5) for DBT + FFDM and 98.3% (95% CI: 98.2-98.3) for FFDM only, p = 0.9. Screen-detected cancer rate increased statistically significantly: 11.18/1000 for DBT + FFDM and 6.49/1000 for FFDM only, p < 0.001. False-positive rate was unchanged: 1.75% for DBT + FFDM and 1.73% for FFDM only, p = 0.9. Positive predictive value for recall was 39.0% (95% CI: 31.9-46.5) for DBT + FFDM and 27.3% (95% CI: 26.4-28.2), for FFDM only, p < 0.0005. The interval cancer rate decreased: 1.26/1000 for DBT + FFDM and 2.76/1000 for FFDM only, p = 0.02. DBT + FFDM yielded a statistically significant increase in cancer detection and program sensitivity.

AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions

Although the value of adding AI as a surrogate second reader in various scenarios has been investigated, it is unknown whether implementing an AI tool within double reading practice would capture additional subtle cancers missed by both radiologists who independently assessed the mammograms. This paper assesses the effectiveness of two state-of-the-art Artificial Intelligence (AI) models in detecting retrospectively-identified missed cancers within a screening program employing double reading practices. The study also explores the agreement between AI and radiologists in locating the lesions, considering various levels of concordance among the radiologists in locating the lesions. The Globally-aware Multiple Instance Classifier (GMIC) and Global–Local Activation Maps (GLAM) models were fine-tuned for our dataset. We evaluated the sensitivity of both models on missed cancers retrospectively identified by a panel of three radiologists who reviewed prior examinations of 729 cancer cases detected in a screening program with double reading practice. Two of these experts annotated the lesions, and based on their concordance levels, cases were categorized as 'almost perfect,' 'substantial,' 'moderate,' and 'poor.' We employed Similarity or Histogram Intersection (SIM) and Kullback–Leibler Divergence (KLD) metrics to compare saliency maps of malignant cases from the AI model with annotations from radiologists in each category. In total, 24.82% of cancers were labeled as “missed.” The performance of GMIC and GLAM on the missed cancer cases was 82.98% and 79.79%, respectively, while for the true screen-detected cancers, the performances were 89.54% and 87.25%, respectively (p-values for the difference in sensitivity < 0.05). As anticipated, SIM and KLD from saliency maps were best in ‘almost perfect,’ followed by ‘substantial,’ ‘moderate,’ and ‘poor.’ Both GMIC and GLAM (p-values < 0.05) exhibited greater sensitivity at higher concordance. Even in a screening program with independent double reading, adding AI could potentially identify missed cancers. However, the challenging-to-locate lesions for radiologists impose a similar challenge for AI.

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

ObjectivesTo 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.MethodsIn 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.ResultsAll 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.ConclusionAI 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 statementIn 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.

Breast cancer screening with digital breast tomosynthesis: Is independent double reading still required?

The European guidelines recommend independent double reading in mammography screening programs. The prospective randomized controlled trial TOSYMA tested the superiority of digital breast tomosynthesis and synthetic mammography (DBT+SM) over digital mammography (DM) for invasive breast cancer detection. This sub-analysis compares the true-positive readings of screening-detected breast cancers resulting from independent double readings in the two trial arms. The 1:1 randomized TOSYMA trial was executed in 17 screening units between 07/2018 and 12/2020. This sub-analysis included 49,762 women in the test arm (DBT+SM) and 49,796 women in the control arm (DM). The true-positive reading results (invasive breast cancers and ductal carcinoma in situ) from 83 readers were determined and merged in a double reading result. DBT+SM screening detected 416 women with breast cancer and DM screening detected 306. Double readings of DBT+SM examinations led to a single true-positive together with a single false-negative result in 26.9 % of cancer cases (112/416), and in 22.2 % of cases (68/306) in the DM examinations. The cancer detection rate with discordant reading results was 2.3 per 1,000 women screened with DBT+SM and 1.4 per 1,000 with DM. Discordant reading results occurred most often for invasive breast cancers [DBT+SM 75.9 % (85/112), DM 67.6 % (46/68)], category T1 [DBT+SM 67.9 % (76/112), DM 55.9 % (38/68)], and category 4a [DBT+SM: 67.6 % (73/112); DM: 84.6 % (55/68)]. The higher breast cancer detection rate with DBT screening includes a relevant percentage of breast cancers that were only detected by one reader in an independent double reading. As in digital mammography, independent double reading continues to be justified in screening with digital breast tomosynthesis. · The percentages of discordant cancer reading results were 26.9 % and 22.2 % for DBT+SM and DM, respectively.. · The single true-positive detection rate was 2.3 ‰ for DBT+ SM and 1.4 ‰ for DM.. · A relevant proportion of screening-detected cancers resulted from a single true-positive reading.. · Weigel S, Hense HW, Weyer-Elberich V et al. Breast cancer screening with digital breast tomosynthesis: Is independent double reading still required?. Fortschr Röntgenstr 2024; DOI: 10.1055/a-2216-1109.

Impact of systematic dynamic maneuvers during computed tomography scan on the T classification of head and neck cancers

ObjectivesTo evaluate the impact of systematic dynamic maneuvers during CT scan on the T-staging of head and neck cancer (HNC). Materials and methodsCT scans from the initial workup of 443 consecutive patients treated for HNC in our institution were retrospectively analyzed. CT scans were performed in both expert centers (comprehensive cancer center and university hospital) and non-expert centers. We noted whether dynamic maneuvers (DM) were performed, in 3 categories, namely: DM not done (DMND), done and inadequate (DMDI), done and adequate (DMDA). In the group with DMDA, T-stage was evaluated without and with DM. Interobserver agreement for T staging was assessed after independent double reading of CT scans with and without DM by two radiologists in a random sample. ResultsAmong the 443 CT scans, DMND was observed in 36.3%, DMDI in 9.3% and DMDA in 54.4%. DMDA were significantly more frequent in expert than in non-expert centers (93.4 vs 6.6%, p < 0.001). In CT scans with DMDA, analysis of the 141 scans rated as T1, T2, T3, or T4 without DM showed agreement of 88.7% with scans with DM, corresponding to a reclassification rate of 11.3% (kappa = 0.85, 95%CI [0.78;0.92]). Among lesions initially classed as Tx without DM (N = 100), the reclassification rate was 76% including DM. ConclusionThe performance of systematic DM integrated into CT protocols is useful to reclassify the T stage in HNC and is essential in case of lesions initially classified as Tx without DM. DM should be performed routinely in expert and nonexpert centers.

Discordant and false-negative interpretations at digital breast tomosynthesis in the prospective Oslo Tomosynthesis Screening Trial (OTST) using independent double reading

ObjectivesTo analyze discordant and false-negatives of double reading digital breast tomosynthesis (DBT) versus digital mammography (DM) including reading times in the Oslo Tomosynthesis Screening Trial (OTST), and reclassify these in a retrospective reader study as missed, minimal sign, or true-negatives.MethodsThe prospective OTST comparing double reading DBT vs. DM had paired design with four parallel arms: DM, DM + computer aided detection, DBT + DM, and DBT + synthetic mammography. Eight radiologists interpreted images in batches using a 5-point scale. Reading time was automatically recorded. A retrospective reader study including four radiologists classified screen-detected cancers with at least one false-negative score and screening examinations of interval cancers as negative, non-specific minimal sign, significant minimal sign, and missed; the two latter groups are defined “actionable.” Statistics included chi-square, Fisher’s exact, McNemar’s, and Mann–Whitney U tests.ResultsDiscordant rate (cancer missed by one reader) for screen-detected cancers was overall comparable (DBT (31% [71/227]) and DM (30% [52/175]), p = .81), significantly lower at DBT for spiculated cancers (DBT, 19% [20/106] vs. DM, 36% [38/106], p = .003), but high (28/49 = 57%, p = 0.001) for DBT-only detected spiculated cancers. Reading time and sensitivity varied among readers. False-negative DBT-only detected spiculated cancers had shorter reading time than true-negatives in 46% (13/28). Retrospective evaluation classified the following DBT exams “actionable”: three missed by both readers, 95% (39/41) of discordant cancers detected by both modes, all 30 discordant DBT-only cancers, 25% (13/51) of interval cancers.ConclusionsDiscordant rate was overall comparable for DBT and DM, significantly lower at DBT for spiculated cancers, but high for DBT-only detected spiculated lesions. Most false-negative screen-detected DBT were classified as “actionable.”Clinical relevance statementRetrospective evaluation of false-negative interpretations from the Oslo Tomosynthesis Screening Trial shows that most discordant and several interval cancers could have been detected at screening. This underlines the potential for modern AI-based reading aids and triage, as high-volume screening is a demanding task.Key Points• Digital breast tomosynthesis (DBT) screening is more sensitive and has higher specificity compared to digital mammography screening, but high-volume DBT screening is a demanding task which can result in high discordance rate among readers.• Independent double reading DBT screening had overall comparable discordance rate as digital mammography, lower for spiculated masses seen on both modalities, and higher for small spiculated cancer seen only on DBT.• Almost all discordant digital breast tomosynthesis-detected cancers (72 of 74) and 25% (13 of 51) of the interval cancers in the Oslo Tomosynthesis Screening Trial were retrospectively classified as actionable and could have been detected by the readers.

Prevalence of smoking during pregnancy and associated social inequalities in developed countries over the 1995-2020 period: A systematic review.

Smoking during pregnancy (SDP) is an important source of preventable morbidity and mortality for both mother and child. The aim of this study was to describe changes in the prevalence of SDP over the last 25 years in developed countries (Human Development Index >0.8 in 2020) and associated social inequalities. A systematic review was conducted based on a search in PubMed, Embase and PsycInfo databases and government sources. Published studies between January 1995 and March 2020, for which the primary outcome was to assess the national prevalence of SDP and the secondary outcome was to describe related socio-economic data were included in the analysis. The selected articles had to be written in English, Spanish, French or Italian. The articles were selected after successive reading of the titles, abstracts and full-length text. An independent double reading with intervention of a third reader in case of disagreement allowed including 35 articles from 14 countries in the analysis. The prevalence of SDP differed across the countries studied despite comparable levels of development. After 2015, the prevalence of SDP ranged between 4.2% in Sweden and 16.6% in France. It was associated with socio-economic factors. The prevalence of SDP slowly decreased over time, but this overall trend masked inequalities within populations. In Canada, France and the United States, the prevalence decreased more rapidly in women of higher socio-economic status, and inequalities in maternal smoking were more marked in these countries. In the other countries, inequalities tended to decrease but remained significant. During pregnancy, that is a period described as a window of opportunity, smoking and social vulnerability factors need to be detected to implement targeted prevention strategies aiming at reducing related social inequalities.

Screening outcome for interpretation by the first and second reader in a population-based mammographic screening program with independent double reading.

Double reading of screening mammograms is associated with a higher rate of screen-detected cancer than single reading, but different strategies exist regarding reader pairing and blinding. Knowledge about these aspects is important when considering strategies for future use of artificial intelligence in mammographic screening. To investigate screening outcome, histopathological tumor characteristics, and mammographic features stratified by the first and the second reader in a population based screening program for breast cancer. The study sample consisted of data from 3,499,048 screening examinations from 834,691 women performed during 1996-2018 in BreastScreen Norway. All examinations were interpreted independently by two radiologists, 272 in total. We analyzed interpretation score, recall, and cancer detection, as well as histopathological tumor characteristics and mammographic features of the cancers, stratified by the first and second readers. For Reader 1, the rate of positive interpretations was 4.8%, recall 2.3%, and cancer detection 0.5%. The corresponding percentages for Reader 2 were 4.9%, 2.5%, and 0.5% (P < 0.05 compared with Reader 1). No statistical difference was observed for histopathological tumor characteristics or mammographic features when stratified by Readers 1 and 2. Recall and cancer detection were statistically higher and histopathological tumor characteristics less favorable for cases detected after concordant positive compared with discordant interpretations. Despite reaching statistical significance, mainly due to the large study sample, we consider the differences in interpretation scores, recall, and cancer detection between the first and second readers to be clinically negligible. For practical and clinical purposes, double reading in BreastScreen Norway is independent.

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

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

Possible strategies for use of artificial intelligence in screen-reading of mammograms, based on retrospective data from 122,969 screening examinations

ObjectivesArtificial intelligence (AI) has shown promising results when used on retrospective data from mammographic screening. However, few studies have explored the possible consequences of different strategies for combining AI and radiologists in screen-reading.MethodsA total of 122,969 digital screening examinations performed between 2009 and 2018 in BreastScreen Norway were retrospectively processed by an AI system, which scored the examinations from 1 to 10; 1 indicated low suspicion of malignancy and 10 high suspicion. Results were merged with information about screening outcome and used to explore consensus, recall, and cancer detection for 11 different scenarios of combining AI and radiologists.ResultsRecall was 3.2%, screen-detected cancer 0.61% and interval cancer 0.17% after independent double reading and served as reference values. In a scenario where examinations with AI scores 1–5 were considered negative and 6–10 resulted in standard independent double reading, the estimated recall was 2.6% and screen-detected cancer 0.60%. When scores 1–9 were considered negative and score 10 double read, recall was 1.2% and screen-detected cancer 0.53%. In these two scenarios, potential rates of screen-detected cancer could be up to 0.63% and 0.56%, if the interval cancers selected for consensus were detected at screening. In the former scenario, screen-reading volume would be reduced by 50%, while the latter would reduce the volume by 90%.ConclusionSeveral theoretical scenarios with AI and radiologists have the potential to reduce the volume in screen-reading without affecting cancer detection substantially. Possible influence on recall and interval cancers must be evaluated in prospective studies.Key Points• Different scenarios using artificial intelligence in combination with radiologists could reduce the screen-reading volume by 50% and result in a rate of screen-detected cancer ranging from 0.59% to 0.60%, compared to 0.61% after standard independent double reading• The use of artificial intelligence in combination with radiologists has the potential to identify negative screening examinations with high precision in mammographic screening and to reduce the rate of interval cancer

Should tomosynthesis replace mammography for breast cancer screening?

A decade has passed since the first prospective trials showed that the mammography technology, digital breast tomosynthesis, increased the rate of cancer detection compared with digital mammography. 1 Ciatto S Houssami N Bernardi D et al. Integration of 3D digital mammography with tomosynthesis for population breast-cancer screening (STORM): a prospective comparison study. Lancet Oncol. 2013; 14: 583-589 Summary Full Text Full Text PDF PubMed Scopus (608) Google Scholar , 2 Skaane P Bandos AI Gullien R et al. Prospective trial comparing full-field digital mammography (FFDM) versus combined FFDM and tomosynthesis in a population-based screening programme using independent double reading with arbitration. Eur Radiol. 2013; 23: 2061-2071 Crossref PubMed Scopus (170) Google Scholar A large body of evidence, comprising prospective non-randomised studies and retrospective studies, 3 Marinovich ML Hunter KE Macaskill P Houssami N Breast cancer screening using tomosynthesis or mammography: a meta-analysis of cancer detection and recall. J Natl Cancer Inst. 2018; 110: 942-949 Crossref PubMed Scopus (108) Google Scholar has since accumulated; however, evidence from randomised controlled trials is scarce. In The Lancet Oncology, Walter Heindel and colleagues report the results of the TOmosynthesis plus SYnthesised MAmmography Study (TOSYMA), 4 Heindel W Weigel W Gerß J et al. Digital breast tomosynthesis plus synthesised mammography versus digital screening mammography for the detection of invasive breast cancer (TOSYMA): a multicentre, open-label, randomised, controlled, superiority trial. Lancet Oncol. 2022; (published online April 12.)https://doi.org/10.1016/S1470-2045(22)00194-2 Summary Full Text Full Text PDF PubMed Scopus (1) Google Scholar a multicentre trial embedded in the German population-wide mammography screening programme. TOSYMA is the largest of three randomised controlled trials providing evidence on breast tomosynthesis versus mammography screening. 4 Heindel W Weigel W Gerß J et al. Digital breast tomosynthesis plus synthesised mammography versus digital screening mammography for the detection of invasive breast cancer (TOSYMA): a multicentre, open-label, randomised, controlled, superiority trial. Lancet Oncol. 2022; (published online April 12.)https://doi.org/10.1016/S1470-2045(22)00194-2 Summary Full Text Full Text PDF PubMed Scopus (1) Google Scholar , 5 Hofvind S Holen AS Aase HS et al. Two-view digital breast tomosynthesis versus digital mammography in a population-based breast cancer screening programme (To-Be): a randomised, controlled trial. Lancet Oncol. 2019; 20: 795-805 Summary Full Text Full Text PDF PubMed Scopus (38) Google Scholar , 6 Pattacini P Nitrosi A Giorgi RP et al. A randomized trial comparing breast cancer incidence and interval cancers after tomosynthesis plus mammography versus mammography alone. Radiology. 2022; (published online Feb 1.)https://doi.org/10.1148/radiol.211132 Crossref PubMed Scopus (3) Google Scholar Heindel and colleagues persevered with TOSYMA despite the COVID-19 pandemic stalling recruitment, resulting in a marginally lower sample size than planned in their adaptive design. 4 Heindel W Weigel W Gerß J et al. Digital breast tomosynthesis plus synthesised mammography versus digital screening mammography for the detection of invasive breast cancer (TOSYMA): a multicentre, open-label, randomised, controlled, superiority trial. Lancet Oncol. 2022; (published online April 12.)https://doi.org/10.1016/S1470-2045(22)00194-2 Summary Full Text Full Text PDF PubMed Scopus (1) Google Scholar Digital breast tomosynthesis plus synthesised mammography versus digital screening mammography for the detection of invasive breast cancer (TOSYMA): a multicentre, open-label, randomised, controlled, superiority trialThe results from this study indicate that the detection rate for invasive breast cancer was significantly higher with digital breast tomosynthesis plus s2D mammography than digital mammography alone. Evaluation of interval cancer rates in the follow-up study will further help to investigate incremental long-term benefits of digital breast tomosynthesis screening. Full-Text PDF

Screen-detected and interval breast cancer after concordant and discordant interpretations in a population based screening program using independent double reading

ObjectivesTo analyze rates, odds ratios (OR), and characteristics of screen-detected and interval cancers after concordant and discordant initial interpretations and consensus in a population-based screening program.MethodsData were extracted from the Cancer Registry of Norway for 487,118 women who participated in BreastScreen Norway, 2006–2017, with 2 years of follow-up. All mammograms were independently interpreted by two radiologists, using a score from 1 (negative) to 5 (high suspicion of cancer). A score of 2+ by one of the two radiologists was defined as discordant and 2+ by both radiologists as concordant positive. Consensus was performed on all discordant and concordant positive, with decisions of recall for further assessment or dismiss. OR was estimated with logistic regression with 95% confidence interval (CI), and histopathological tumor characteristics were analyzed for screen-detected and interval cancer.ResultsAmong screen-detected cancers, 23.0% (697/3024) had discordant scores, while 12.8% (117/911) of the interval cancers were dismissed at index screening. Adjusted OR was 2.4 (95% CI: 1.9–2.9) for interval cancer and 2.8 (95% CI: 2.5–3.2) for subsequent screen-detected cancer for women dismissed at consensus compared to women with concordant negative scores. We found 3.4% (4/117) of the interval cancers diagnosed after being dismissed to be DCIS, compared to 20.3% (12/59) of those with false-positive result after index screening.ConclusionTwenty-three percent of the screen-detected cancers was scored negative by one of the two radiologists. A higher odds of interval and subsequent screen-detected cancer was observed among women dismissed at consensus compared to concordant negative scores. Our findings indicate a benefit of personalized follow-up.Key Points• In this study of 487,118 women participating in a screening program using independent double reading with consensus, 23% screen-detected cancers were detected by only one of the two radiologists.• The adjusted odds ratio for interval cancer was 2.4 (95% confidence interval: 1.9, 2.9) for cases dismissed at consensus using concordant negative interpretations as the reference.• Interval cancers diagnosed after being dismissed at consensus or after concordant negative scores had clinically less favorable prognostic tumor characteristics compared to those diagnosed after false-positive results.

Artificial Intelligence Evaluation of 122 969 Mammography Examinations from a Population-based Screening Program.

Background Artificial intelligence (AI) has shown promising results for cancer detection with mammographic screening. However, evidence related to the use of AI in real screening settings remain sparse. Purpose To compare the performance of a commercially available AI system with routine, independent double reading with consensus as performed in a population-based screening program. Furthermore, the histopathologic characteristics of tumors with different AI scores were explored. Materials and Methods In this retrospective study, 122 969 screening examinations from 47 877 women performed at four screening units in BreastScreen Norway from October 2009 to December 2018 were included. The data set included 752 screen-detected cancers (6.1 per 1000 examinations) and 205 interval cancers (1.7 per 1000 examinations). Each examination had an AI score between 1 and 10, where 1 indicated low risk of breast cancer and 10 indicated high risk. Threshold 1, threshold 2, and threshold 3 were used to assess the performance of the AI system as a binary decision tool (selected vs not selected). Threshold 1 was set at an AI score of 10, threshold 2 was set to yield a selection rate similar to the consensus rate (8.8%), and threshold 3 was set to yield a selection rate similar to an average individual radiologist (5.8%). Descriptive statistics were used to summarize screening outcomes. Results A total of 653 of 752 screen-detected cancers (86.8%) and 92 of 205 interval cancers (44.9%) were given a score of 10 by the AI system (threshold 1). Using threshold 3, 80.1% of the screen-detected cancers (602 of 752) and 30.7% of the interval cancers (63 of 205) were selected. Screen-detected cancer with AI scores not selected using the thresholds had favorable histopathologic characteristics compared to those selected; opposite results were observed for interval cancer. Conclusion The proportion of screen-detected cancers not selected by the artificial intelligence (AI) system at the three evaluated thresholds was less than 20%. The overall performance of the AI system was promising according to cancer detection. © RSNA, 2022.

Artificial Intelligence Detection of Missed Cancers at Digital Mammography That Were Detected at Digital Breast Tomosynthesis

To investigate how an artificial intelligence (AI) system performs at digital mammography (DM) from a screening population with ground truth defined by digital breast tomosynthesis (DBT), and whether AI could detect breast cancers at DM that had originally only been detected at DBT. In this secondary analysis of data from a prospective study, DM examinations from 14 768 women (mean age, 57 years), examined with both DM and DBT with independent double reading in the Malmӧ Breast Tomosynthesis Screening Trial (MBTST) (ClinicalTrials.gov: NCT01091545; data collection, 2010-2015), were analyzed with an AI system. Of 136 screening-detected cancers, 95 cancers were detected at DM and 41 cancers were detected only at DBT. The system identifies suspicious areas in the image, scored 1-100, and provides a risk score of 1 to 10 for the whole examination. A cancer was defined as AI detected if the cancer lesion was correctly localized and scored at least 62 (threshold determined by the AI system developers), therefore resulting in the highest examination risk score of 10. Data were analyzed with descriptive statistics, and detection performance was analyzed with receiver operating characteristics. The highest examination risk score was assigned to 10% (1493 of 14 786) of the examinations. With 90.8% specificity, the AI system detected 75% (71 of 95) of the DM-detected cancers and 44% (18 of 41) of cancers at DM that had originally been detected only at DBT. The majority were invasive cancers (17 of 18). Almost half of the additional DBT-only screening-detected cancers in the MBTST were detected at DM with AI. AI did not reach double reading performance; however, if combined with double reading, AI has the potential to achieve a substantial portion of the benefit of DBT screening.Keywords: Computer-aided Diagnosis, Mammography, Breast, Diagnosis, Classification, Application DomainClinical trial registration no. NCT01091545© RSNA, 2021.

Interstitial Lung Abnormalities Detected by CT in Asbestos-Exposed Subjects Are More Likely Associated to Age.

Objective: the aim of this study was to evaluate the association between interstitial lung abnormalities, asbestos exposure and age in a population of retired workers previously occupationally exposed to asbestos. Methods: previously occupationally exposed former workers to asbestos eligible for a survey conducted between 2003 and 2005 in four regions of France, underwent chest CT examinations and pulmonary function testing. Industrial hygienists evaluated asbestos exposure and calculated for each subject a cumulative exposure index (CEI) to asbestos. Smoking status information was also collected in this second round of screening. Expert radiologists performed blinded independent double reading of chest CT-scans and classified interstitial lung abnormalities into: no abnormality, minor interstitial findings, interstitial findings inconsistent with UIP, possible or definite UIP. In addition, emphysema was assessed visually (none, minor: emphysema <25%, moderate: between 25 and 50% and severe: >50% of the lung). Logistic regression models adjusted for age and smoking were used to assess the relationship between interstitial lung abnormalities and occupational asbestos exposure. Results: the study population consisted of 2157 male subjects. Interstitial lung abnormalities were present in 365 (16.7%) and emphysema in 444 (20.4%). Significant positive association was found between definite or possible UIP pattern and age (OR adjusted =1.08 (95% CI: 1.02–1.13)). No association was found between interstitial abnormalities and CEI or the level of asbestos exposure. Conclusion: presence of interstitial abnormalities at HRCT was associated to aging but not to cumulative exposure index in this cohort of former workers previously occupationally exposed to asbestos.

Breast cancer detection: Comparison of digital mammography and digital breast tomosynthesis across non-dense and dense breasts

IntroductionBreast density is associated with an increase in breast cancer risk and limits early detection of the disease. This study assesses the diagnostic performance of mammogram readers in digital mammography (DM) and digital breast tomosynthesis (DBT). MethodsEleven breast readers with 1–39 years of experience reading mammograms and 0–4 years of experience reading DBT participated in the study. All readers independently interpreted 60 DM cases (40 normal/20 abnormal) and 35 DBT cases (20 normal/15 abnormal). Sensitivity, specificity, ROC AUC, and diagnostic confidence were calculated and compared between DM and DBT. ResultsDBT significantly improved diagnostic confidence in both dense breasts (p = 0.03) and non-dense breasts (p = 0.003) but not in other diagnostic performance metrics. Specificity was higher in DM for readers with >7 years' experience (p = 0.03) in reading mammography, non-radiologists (p = 0.04), readers who had completed a 3–6 months training fellowship in breast imaging (p = 0.04), and those with ≤2 years’ experience in reading DBT (p = 0.02), particularly in non-dense breasts. ConclusionDiagnostic confidence was higher in DBT when compared to DM. In contrast, other performance metrics appeared to be similar or better with DM and may be influenced by the lack of experience of the reader cohort in reading DBT. Implications for practiceThe benefits of DBT may not be entirely accrued until radiologists attain expertise in DBT interpretation. Specificity of DBT varied according to reader characteristics, and these characteristics may be useful for optimising pairing strategies in independent double reading of DBT as practiced in Australia to reduce false positive diagnostic errors.

Lung cancer screening by low-dose CT among asbestos-exposed workers: first results of a pilot program

Abstract Background Occupational asbestos exposure (OAE) is a risk factor for lung cancer (LC) and can cause malignant diseases decades after exposure. Lung cancer screening with low-dose computed tomography (LCS) in heavy smokers has shown LC-mortality reductions in two large trials. Recent guidelines advocate LCS in high-risk populations with OAE and additional smoking history. Methods A structured pilot program on LCS in three German regions has been implemented from 2014 to 2018. Eligibility criteria are: OAE ≥10 years starting before 1985 or diagnosis of OAE-related lung disease other than cancer, age ≥55 years and smoking history ≥30 pack years. Eligible persons are centrally invited for LCS on a voluntary basis in 12 months intervals. All persons willing to participate receive obligatory physician counselling before LCS. CT scans are performed according to a standardized protocol. The program provides technical quality assurance as well as independent double reading of all suspicious findings and of a random sample of all CT scans. Results Of 2715 and 1534 persons invited to first and second LCS, 1571 (57.9%) and 715 (46.6%) agreed to participate, respectively. Main reason for disagreement was principal refusal of LCS (15.5% in first and 22.2% in second LCS), whereas 8.5% and 6.9%, respectively, refused after counselling. Additionally, 12.9% and 5.7% did not respond at all. Effectively, 68.8% and 70.6% of those who initially agreed, received first and second LCS, respectively. Variations between regions were observed (range 61.0% to 79.8%). First preliminary outcome assessment shows detection rates of 0.019 and 0.011 in first and second LCS, respectively. Conclusions A substantial group of eligible persons with OAE participated in LCS after physician counselling. Participation remained stable over two screening rounds. First results show detection of LC in the expected range. The effectiveness of early detection of LC in OAE needs to be evaluated further. Key messages Participation over the first two screening rounds in structured lung cancer screening remained stable among eligible persons with OAE and smoking history who were counselled by physicians. Detection of lung cancer in a structured pilot screening program in three German regions seems to be within the range to be expected from previous research.

Influence of Mammography Volume on Radiologists' Performance: Results from BreastScreen Norway.

Background Several European screening mammography programs that use independent double reading with consensus recommend an annual minimum reading volume of 5000 mammograms per radiologist. This recommendation is based only on expert opinion, and the influence of reading volume on performance in such programs is unknown. Purpose To examine the influence of annual and cumulative reading volume on radiologists' reading performance for digital mammography in a screening program that uses independent double reading with consensus. Materials and Methods This retrospective study included data from digital mammographic examinations in BreastScreen Norway obtained from 2006 to 2016. Multilevel mixed-effects models were used to determine how sensitivity, rate of screening-detected breast cancer (SDC), and false-positive rate (FPR) before and after consensus meeting related to annual and cumulative reading volume. Results The study included 2 373 433 readings performed by 121 radiologists. The median annual reading volume ranged from 153 to 19 500 mammograms, and the median cumulative reading volume was 30 566 mammograms. Sensitivity and SDC rate were relatively stable at 87% to 90% and 4.9 to 4.7 per 1000 readings (0.49% and 0.47%), respectively, between 100 and 10 000 annual readings and at 88% to 89% and 4.8 to 4.9 per 1000 readings (0.48% and 0.49%) between 500 and 100 000 cumulative readings. There was a decreasing trend with higher annual volumes (P for trend < .001 for both) to a sensitivity of 81% and SDC rate of 3.9 per 1000 readings (0.39%) at 18 000 readings. There was a decreasing trend in FPR before and after consensus with higher annual and cumulative volumes (P for trend < .001 for all). FPRs before consensus meeting were 5.3% at 100 annual readings and 4.0% at 4000 annual readings and were 6.7% at 500 cumulative readings and 3.6% at 20 000 cumulative readings. FPRs after consensus meeting were 2.5% at 100 annual readings and 2.3% at 4000 annual readings and were 2.7% at 500 cumulative readings and 2.2% at 20 000 cumulative readings. Conclusion Annual reading volumes between 4000 and 10 000 mammograms and cumulative reading volumes greater than 20 000 mammograms may be the most optimal volumes for achieving high reading performance in a screening program with independent double reading. © RSNA, 2019 See also the editorial by Rosenberg and Seidenwurm in this issue.

Benefits of Independent Double Reading in Digital Mammography: A Theoretical Evaluation of All Possible Pairing Methodologies

To establish the efficacy of pairing readers randomly and evaluate the merits of developing optimal pairing methodologies. Sensitivity, specificity, and proportion correct were computed for three different case sets that were independently read by 16 radiologists. Performance of radiologists as single readers was compared to expected double reading performance. We theoretically evaluated all possible pairing methodologies. Bootstrap resampling methods were used for statistical analyses. Significant improvements in expected performance for double versus single reading (ie, delta performance) were shown for all performance measures and case-sets (p ≤ .003), with overall delta performance across all theoretically possible pairing schemes (n = 10,395) ranging between .05 and .08. Delta performance for the 20 best pairing schemes was significant (p < .001) and ranged between .07 and .10. Delta performance for 20 random pairing schemes was also significant (p ≤ .003) and ranged between .05 and .08. Delta performance for the 20 worst pairing schemes ranged between .03 and .06, reaching significance in delta proportion correct (p ≤ .021) for all three case-sets and in delta specificity for two case-sets (p ≤ .033) but not for a third case-set (p = .131), and not reaching significance in delta sensitivity for any of the three case-sets (.098 ≥ p ≥ .067). Significant benefits accrue from double reading, and while random reader pairing achieves most double reading benefits, a strategic pairing approach may maximize the benefits of double reading.

Optimizing performance of BreastScreen Norway using value of information in graphical models.

This study proposes a method to optimize the performance of BreastScreen Norway through a stratified recommendation of tests including independent double or single reading of the screening mammograms and additional imaging with or without core needle biopsy. This is carefully evaluated by a value of information analysis. An estimated graphical probabilistic model describing the relationship between a set of risk factors and the corresponding risk of breast cancer is used for this analysis, together with a Bayesian network modeling screening test results conditional on the true (but unknown) breast cancer status of a woman. This study contributes towards evaluating a possibility of improving the efficiency of the screening program, where all women aged 50 to 69 are invited every second year, regardless of individual risk factors. Our stratified recommendation of tests is dependent on the probability that an asymptomatic woman has developed breast cancer at the time she is invited to a screening.