Reading Of Mammograms Research Articles

Australian women's judgements about using artificial intelligence to read mammograms in breast cancer screening.

Mammographic screening for breast cancer is an early use case for artificial intelligence (AI) in healthcare. This is an active area of research, mostly focused on the development and evaluation of individual algorithms. A growing normative literature argues that AI systems should reflect human values, but it is unclear what this requires in specific AI implementation scenarios. Our objective was to understand women's values regarding the use of AI to read mammograms in breast cancer screening. We ran eight online discussion groups with a total of 50 women, focused on their expectations and normative judgements regarding the use of AI in breast screening. Although women were positive about the potential of breast screening AI, they argued strongly that humans must remain as central actors in breast screening systems and consistently expressed high expectations of the performance of breast screening AI. Women expected clear lines of responsibility for decision-making, to be able to contest decisions, and for AI to perform equally well for all programme participants. Women often imagined both that AI might replace radiographers and that AI implementation might allow more women to be screened: screening programmes will need to communicate carefully about these issues. To meet women's expectations, screening programmes should delay implementation until there is strong evidence that the use of AI systems improves screening performance, should ensure that human expertise and responsibility remain central in screening programmes, and should avoid using AI in ways that exacerbate inequities.

Radiographers Could Help With Double Reading of Mammograms

Radiographers Could Help With Double Reading of Mammograms

Performance of Radiologists and Radiographers in Double Reading Mammograms: The UK National Health Service Breast Screening Program.

Background Double reading can be used in screening mammography, but it is labor intensive. There is limited evidence on whether trained radiographers (ie, technologists) may be used to provide double reading. Purpose To compare the performance of radiologists and radiographers double reading screening mammograms, considering reader experience level. Materials and Methods In this retrospective study, performance and experience data were obtained for radiologists and radiographer readers of all screening mammograms in England from April 2015 to March 2016. Cancer detection rate (CDR), recall rate (RR), and positive predictive value (PPV) of recall based on biopsy-proven findings were calculated for first readers. Performance metrics were analyzed according to reader professional group and years of reading experience using the analysis of variance test. P values less than .05 were considered to indicate statistically significant difference. Results During the study period, 401 readers (224 radiologists and 177 radiographers) double read 1 404 395 screening digital mammograms. There was no difference in CDR between radiologist and radiographer readers (mean, 7.84 vs 7.53 per 1000 examinations, respectively; P = .08) and no difference for readers with more than 10 years of experience compared with 5 years or fewer years of experience, regardless of professional group (mean, 7.75 vs 7.71 per 1000 examinations respectively, P = .87). No difference in the mean RR was observed between radiologists and radiographer readers (5.0% vs 5.2%, respectively, P = .63). A lower RR was seen for readers with more than 10 years of experience compared with 5 years or fewer, regardless of professional group (mean, 4.8% vs 5.8%, respectively; P = .001). No variation in PPV was observed between them (P = .42), with PPV values of 17.1% for radiologists versus 16.1% for radiographers. A higher PPV was seen for readers with more than 10 years of experience compared with 5 years or less, regardless of professional group (mean, 17.5% and 14.9%, respectively; P = .02). Conclusion No difference in performance was observed between radiographers and radiologists reading screening mammograms in a program that used double reading. Published under a CC BY 4.0 license Online supplemental material is available for this article. See also the editorial by Hooley and Durand in this issue.

Evaluating the effectiveness of abbreviated breast MRI (abMRI) interpretation training for mammogram readers: a multi-centre study assessing diagnostic performance, using an enriched dataset

BackgroundAbbreviated breast MRI (abMRI) is being introduced in breast screening trials and clinical practice, particularly for women with dense breasts. Upscaling abMRI provision requires the workforce of mammogram readers to learn to effectively interpret abMRI.The purpose of this study was to examine the diagnostic accuracy of mammogram readers to interpret abMRI after a single day of standardised small-group training and to compare diagnostic performance of mammogram readers experienced in full-protocol breast MRI (fpMRI) interpretation (Group 1) with that of those without fpMRI interpretation experience (Group 2).MethodsMammogram readers were recruited from six NHS Breast Screening Programme sites. Small-group hands-on workstation training was provided, with subsequent prospective, independent, blinded interpretation of an enriched dataset with known outcome. A simplified form of abMRI (first post-contrast subtracted images (FAST MRI), displayed as maximum-intensity projection (MIP) and subtracted slice stack) was used. Per-breast and per-lesion diagnostic accuracy analysis was undertaken, with comparison across groups, and double-reading simulation of a consecutive screening subset.Results37 readers (Group 1: 17, Group 2: 20) completed the reading task of 125 scans (250 breasts) (total = 9250 reads). Overall sensitivity was 86% (95% confidence interval (CI) 84–87%; 1776/2072) and specificity 86% (95%CI 85–86%; 6140/7178). Group 1 showed significantly higher sensitivity (843/952; 89%; 95%CI 86–91%) and higher specificity (2957/3298; 90%; 95%CI 89–91%) than Group 2 (sensitivity = 83%; 95%CI 81–85% (933/1120) p < 0.0001; specificity = 82%; 95%CI 81–83% (3183/3880) p < 0.0001). Inter-reader agreement was higher for Group 1 (kappa = 0.73; 95%CI 0.68–0.79) than for Group 2 (kappa = 0.51; 95%CI 0.45–0.56). Specificity improved for Group 2, from the first 55 cases (81%) to the remaining 70 (83%) (p = 0.02) but not for Group 1 (90–89% p = 0.44), whereas sensitivity remained consistent for both Group 1 (88–89%) and Group 2 (83–84%).ConclusionsSingle-day abMRI interpretation training for mammogram readers achieved an overall diagnostic performance within benchmarks published for fpMRI but was insufficient for diagnostic accuracy of mammogram readers new to breast MRI to match that of experienced fpMRI readers. Novice MRI reader performance improved during the reading task, suggesting that additional training could further narrow this performance gap.

Characterisation of graphite-based material for dosimetry in the mammographic energy range

Present work explores the use of carbon-based materials as novel material for in-vivo radiation dosimetry during routine screening mammography, in part to reliably predict the average glandular dose (AGD) imparted to the patient. The study herein proposes the use of highly uniform 0.3 mm of 2B and HB grade polymer pencil-lead graphite (PPLG) i.e. approximately 95 wt % and 61 wt % graphite content, respectively and also using graphite produced commercially in the form of 50 μm thick sheets, addressing variation in lattice structure and defects resulting from low x-ray doses. Comparison was made with highly-oriented pyrolytic graphite (HOPG), a pure ordered synthetic form of graphite. Due to their small size and distinctive shape, these samples can be placed on the body surface in the field of view during the examination without compromising the mammogram reading. Investigations of thermo- and photoluminescence dose dependence, as well as changes in Raman spectroscopic features, have been conducted with a focus on the relationship between absorbed radiation energy and induced material changes within the dose range 3–11 mGy. The influences, are readily understood to relate to defect density, structural alterations and radiation-driven thermal annealing, all irradiation alterations occurring at the microscopic level. Within the doses study, all graphite samples demonstrated excellent linear response in respect of thermoluminescence yield per unit mass. In terms of sensitivity, 2B samples outperformed HB, graphite sheet (GS), and HOPG. In mammographic studies graphite sheets show particular promise as a probe of skin dose, with negligible prospect for interference with the breast image an individual patient during routine screening, closely matching the effective atomic number of soft tissues, additionally providing the basis of a low-cost yet highly effective system for studies of radiation-driven changes in carbon.

Integrating mammography screening programmes into specialist breast centres in Italy: insights from a national survey of Senonetwork breast centres

BackgroundDespite recommendations, mammography screening is often insufficiently integrated into specialist breast centres. A national, cross-sectional, voluntary, online survey on this issue was carried out among the Italian breast centres associated with Senonetwork, the Italian network of breast cancer services.MethodsA 73-item questionnaire was created, pre-tested and piloted. Centres integrating and not integrating a screening programme were compared using the unified theory of acceptance and use of technology (UTAUT) model. Centres’ clustering was performed using the Gower’s distance metric. Groups and clusters were compared with the equality-of-means test.ResultsThe response rate was 82/128 (65%). Overall, 84% (69/82) breast centres reported a collaboration with a screening programme in performing and/or reading mammograms and in the diagnostic work-up of women with abnormal screening results. The same proportion was observed among those centres responding to all questions (62/74). Performance expectancies (or the perceived usefulness of integration in terms of clinical quality, patient convenience, ease of job, and professional growth), satisfaction and motivation were higher in those centres collaborating with the screening programme. Effort expectancy indicators (or the degree to which the respondents believe that the integration is easy to implement) and those concerning the existence of facilitating conditions were lower both in centres collaborating and not collaborating with the screening programme. Among the former, six clusters of centres, distributed from ‘no integration’ to ‘high’, were identified. In cluster analysis, the highest level of integration was associated with higher agreement that integration eases the job, offers better opportunities for professional growth, and makes the working environment more satisfactory. The least integrated cluster assigned the lowest score to the statement that local health authority made available the resources needed.ConclusionsWhile confirming the positive effects of integrating screening programmes into breast centres, this survey has brought to light specific difficulties that must be faced. The results provide insights into the importance of integration focusing on the perspectives of professional career and motivation. The deficiency of facilitating conditions to integration is modifiable. Screening professionals’ societies may have a role as initiators of the integration. Other supporting actions may be included in health laws at the national and regional level.

Radiologist Self-training: a Study of Cancer Detection when Reading Mammograms at Work Clinics or Workshops

Provision of online and remote specialist education and general continued professional education in medicine is a growing field. For radiology specifically, the ability to access web-based platforms that house high resolution medical images, and the high fidelity of simulated activities is increasingly growing due to positive changes in technology. This study investigates the differences in providing a self-directed specialist radiology education system in two modes: at clinics and in-person workshops. 335 Australian radiologists completed 562 readings of mammogram test sets through the web-based interactive BREAST platform with 325 at conference workshops and 237 at their workplaces. They engaged with test sets with each comprising of 60 mammogram cases (20 cancer and 40 normal). Radiologists marked the location of any cancers and had their performance measured via 5 metrics of diagnostic accuracy. Results show that the location of engagement with BREAST did not yield any significant difference in the performances of all radiologists and the same radiologists between two reading modes (P > 0.05). Radiologists who read screening mammograms for BreastScreen Australia performed better when they completed the test sets at designated workshops (P < 0.05), as was also the case for radiologists who read > 100 cases per week (P < 0.05). In contrast, radiologists who read less mammograms frequently recorded better performances in specificity and JAFROC at clinics (P < 0.05). Findings show that remotely accessed online education for specialised training and core skills building in radiology can provide a similar learning opportunity for breast radiologists when compared to on-site dedicated workshops at scientific meetings. For readers with high volumes of mammograms, a workshop setting may provide a superior experience while clinic setting is more helpful to less experienced readers.

An Artificial Intelligence-based Mammography Screening Protocol for Breast Cancer: Outcome and Radiologist Workload.

Background Developments in artificial intelligence (AI) systems to assist radiologists in reading mammograms could improve breast cancer screening efficiency. Purpose To investigate whether an AI system could detect normal, moderate-risk, and suspicious mammograms in a screening sample to safely reduce radiologist workload and evaluate across Breast Imaging Reporting and Data System (BI-RADS) densities. Materials and Methods This retrospective simulation study analyzed mammographic examination data consecutively collected from January 2014 to December 2015 in the Danish Capital Region breast cancer screening program. All mammograms were scored from 0 to 10, representing the risk of malignancy, using an AI tool. During simulation, normal mammograms (score < 5) would be excluded from radiologist reading and suspicious mammograms (score > recall threshold [RT]) would be recalled. Two radiologists read the remaining mammograms. The RT was fitted using another independent cohort (same institution) by matching to the radiologist sensitivity. This protocol was further applied to each BI-RADS density. Screening outcomes were measured using the sensitivity, specificity, workload, and false-positive rate. The AI-based screening was tested for noninferiority sensitivity compared with radiologist screening using the Farrington-Manning test. Specificities were compared using the McNemar test. Results The study sample comprised 114 421 screenings for breast cancer in 114 421 women, resulting in 791 screen-detected, 327 interval, and 1473 long-term cancers and 2107 false-positive screenings. The mean age of the women was 59 years ± 6 (SD). The AI-based screening sensitivity was 69.7% (779 of 1118; 95% CI: 66.9, 72.4) and was noninferior (P = .02) to the radiologist screening sensitivity of 70.8% (791 of 1118; 95% CI: 68.0, 73.5). The AI-based screening specificity was 98.6% (111 725 of 113 303; 95% CI: 98.5, 98.7), which was higher (P < .001) than the radiologist specificity of 98.1% (111 196 of 113 303; 95% CI: 98.1, 98.2). The radiologist workload was reduced by 62.6% (71 585 of 114 421), and 25.1% (529 of 2107) of false-positive screenings were avoided. Screening results were consistent across BI-RADS densities, although not significantly so for sensitivity. Conclusion Artificial intelligence (AI)-based screening could detect normal, moderate-risk, and suspicious mammograms in a breast cancer screening program, which may reduce the radiologist workload. AI-based screening performed consistently across breast densities. © RSNA, 2022 Online supplemental material is available for this article.

The optimal use of computer aided detection to find low prevalence cancers

People miss a high proportion of targets that only appear rarely. This low prevalence (LP) effect has implications for applied search tasks such as the clinical reading of mammograms. Computer aided detection (CAD) has been used to help radiologists search mammograms by highlighting areas likely to contain a cancer. Previous research has found a benefit in search when CAD cues were correct but a cost to search when CAD cues were incorrect. The current research investigated whether there is an optimal way to present CAD to ensure low error rates when CAD is both correct and incorrect. Experiment 1 compared an automatic condition, where CAD appeared simultaneously with the display to an interactive condition, where participants could choose to use CAD. Experiment 2 compared the automatic condition to a confirm condition, where participants searched the display first before being shown the CAD cues. The results showed that miss errors were reduced overall in the confirm condition, with no cost to false alarms. Furthermore, having CAD be interactive, resulted in a low uptake where it was only used in 34% of trials. The results showed that the presentation mode of CAD can affect decision-making in LP search.

Strengths and challenges of the artificial intelligence in the assessment of dense breasts.

High breast density is a risk factor for breast cancer and overlapping of glandular tissue can mask lesions thus lowering mammographic sensitivity. Also, dense breasts are more vulnerable to increase recall rate and false-positive results. New generations of artificial intelligence (AI) have been introduced to the realm of mammography. We aimed to assess the strengths and challenges of adopting artificial intelligence in reading mammograms of dense breasts. This study included 6600 mammograms of dense patterns "c" and "d" and presented 4061 breast abnormalities. All the patients were subjected to full-field digital mammography, breast ultrasound, and their mammographic images were scanned by AI software (Lunit INSIGHT MMG). Diagnostic indices of the sono-mammography: a sensitivity of 98.71%, a specificity of 88.04%, a positive-predictive value of 80.16%, a negative-predictive value of 99.29%, and a diagnostic accuracy of 91.5%. AI-aided mammograms presented sensitivity of 88.29%, a specificity of 96.34%, a positive-predictive value of 92.2%, a negative-predictive value of 94.4%, and a diagnostic accuracy of 94.5% in its ability to read dense mammograms. Dense breasts scanned with AI showed a notable reduction of mammographic misdiagnosis. Knowledge of such software challenges would enhance its application as a decision support tool to mammography in the diagnosis of cancer. Dense breast is challenging for radiologists and renders low sensitivity mammogram. Mammogram scanned by AI could be used to overcome such limitation, enhance the discrimination between benign and malignant breast abnormalities and the early detection of breast cancer.

Breast cancer detection across dense and non-dense breasts: Markers of diagnostic confidence and efficacy.

BackgroundThe impact of radiologists’ characteristics has become a major focus of recent research. However, the markers of diagnostic efficacy and confidence in dense and non-dense breasts are poorly understood.PurposeThis study aims to assess the relationship between radiologists’ characteristics and diagnostic performance across dense and non-dense breasts.Materials and methodsRadiologists specialising in breast imaging (n = 128) who had 0.5–40 (13±10.6) years of experience reading mammograms were recruited. Participants independently interpreted a test set containing 60 digital mammograms (40 normal and 20 abnormal) with similarly distributed breast densities. Diagnostic performance measures were analysed via Jamovi software (version 1.6.22).ResultsIn dense breasts, breast-imaging fellowship completion significantly improved specificity (p = 0.004), location sensitivity (p = 0.01) and the area under the curve (AUC) of the receiver operating characteristic (p = 0.03). Only participation in BreastScreen reading significantly improved all performance metrics: specificity (p = 0.04), sensitivity (p = 0.005), location sensitivity (p < 0.001) and AUC (p < 0.001). Reading > 100 mammograms weekly significantly improved sensitivity (p = 0.03), location sensitivity (p = 0.001), and AUC (p = 0.03).In non-dense breasts, breast fellowship completion significantly improved sensitivity (p = 0.02), location sensitivity (p = 0.04) and AUC (p = 0.002). Participation in BreastScreen reading and reading > 100 mammograms weekly significantly improved only sensitivity (p = 0.002 and p = 0.003, respectively) and location sensitivity (p < 0.001 and p < 0.001, respectively).ConclusionParticipating in screening programs, breast fellowships and reading > 100 mammograms weekly are important indicators of the diagnostic performance of radiologists across dense and non-dense breasts. In dense breasts, optimal performance resulted from participation in a breast screening program.

Variations in breast cancer detection rates during mammogram-reading sessions: does experience have an impact?

To examine whether radiologists' performances are consistent throughout a reading session and whether any changes in performance over the reading task differ depending on experience of the reader. The performance of ten radiologists reading a test set of 60 mammographic cases without breaks was assessed using an ANOVA, 2 × 3 factorial design. Participants were categorized as more (≥2,000 mammogram readings per year) or less (<2,000 readings per year) experienced. Three series of 20 cases were chosen to ensure comparable difficulty and presented in the same sequence to all readers. It usually takes around 30 min for a radiologist to complete each of the 20-case series, resulting in a total of 90 min for the 60 mammographic cases. The sensitivity, specificity, lesion sensitivity, and area under the ROC curve were calculated for each series. We hypothesized that the order in which a series was read (i.e. fixed-series sequence) would have a significant main effect on the participants' performance. We also determined if significant interactions exist between the fixed-series sequence and radiologist experience. Significant linear interactions were found between experience and the fixed sequence of the series for sensitivity (F[1] =5.762, p = .04, partial η2 = .41) and lesion sensitivity. (F[1] =6.993, p = .03, partial η2 = .46). The two groups' mean scores were similar for the first series but progressively diverged. By the end of the third series, significant differences in sensitivity and lesion sensitivity were evident, with the more experienced individuals demonstrating improving and the less experienced declining performance. Neither experience nor series sequence significantly affected the specificity or the area under the ROC curve. Radiologists' performance may change considerably during a reading session, apparently as a function of experience, with less experienced radiologists declining in sensitivity and lesion sensitivity while more experienced radiologists actually improve. With the increasing demands on radiologists to undertake high-volume reporting, we suggest that junior radiologists be made aware of possible sensitivity and lesion sensitivity deterioration over time so they can schedule breaks during continuous reading sessions that are appropriate to them, rather than try to emulate their more experienced colleagues. Less-experienced radiologists demonstrated a reduction in mammographic diagnostic accuracy in later stages of the reporting sessions. This may suggest that extending the duration of reporting sessions to compensate for increasing workloads may not represent the optimal solution for less-experienced radiologists.

The Impact of Radiologist Screening Mammogram Reading Volume on Performance in the Ontario Breast Screening Program.

Although some studies have shown increasing radiologists' mammography volumes improves performance, there is a lack of evidence specific to digital mammography and breast screening program performance targets. This study evaluates the relationship between digital screening volume and meeting performance targets. This retrospective cohort study included 493 radiologists in the Ontario Breast Screening Program who interpreted 1,762,173 screening mammograms in participants ages 50-90 between 2014 and 2016. Associations between annual screening volume and meeting performance targets for abnormal call rate, positive predictive value (PPV), invasive cancer detection rate (CDR), sensitivity, and specificity were modeled using mixed-effects multivariate logistic regression. Most radiologists read 500-999 (36.7%) or 1,000-1,999 (31.0%) screens annually, and 18.5% read ≥2,000. Radiologists who read ≥2,000 annually were more likely to meet abnormal call rate (OR = 3.85; 95% CI: 1.17-12.61), PPV (OR = 5.36; 95% CI: 2.53-11.34), invasive CDR (OR = 4.14; 95% CI: 1.50-11.46), and specificity (OR = 4.07; 95% CI: 1.89-8.79) targets versus those who read 100-499 screens. Radiologists reading 1,000-1,999 screens annually were more likely to meet PPV (OR = 2.32; 95% CI: 1.22-4.40), invasive CDR (OR = 3.36; 95% CI: 1.49-7.59) and specificity (OR = 2.00; 95% CI: 1.04-3.84) targets versus those who read 100-499 screens. No significant differences were observed for sensitivity. Annual reading volume requirements of 1,000 in Canada are supported as screening volume above 1,000 was strongly associated with achieving performance targets for nearly all measures. Increasing the minimum volume to 2,000 may further reduce the potential limitations of screening due to false positives, leading to improvements in overall breast screening program quality.

Using deep learning to assist readers during the arbitration process: a lesion-based retrospective evaluation of breast cancer screening performance

ObjectivesTo evaluate if artificial intelligence (AI) can discriminate recalled benign from recalled malignant mammographic screening abnormalities to improve screening performance.MethodsA total of 2257 full-field digital mammography screening examinations, obtained 2011–2013, of women aged 50–69 years which were recalled for further assessment of 295 malignant out of 305 truly malignant lesions and 2289 benign lesions after independent double-reading with arbitration, were included in this retrospective study. A deep learning AI system was used to obtain a score (0–95) for each recalled lesion, representing the likelihood of breast cancer. The sensitivity on the lesion level and the proportion of women without false-positive ratings (non-FPR) resulting under AI were estimated as a function of the classification cutoff and compared to that of human readers.ResultsUsing a cutoff of 1, AI decreased the proportion of women with false-positives from 89.9 to 62.0%, non-FPR 11.1% vs. 38.0% (difference 26.9%, 95% confidence interval 25.1–28.8%; p < .001), preventing 30.1% of reader-induced false-positive recalls, while reducing sensitivity from 96.7 to 91.1% (5.6%, 3.1–8.0%) as compared to human reading. The positive predictive value of recall (PPV-1) increased from 12.8 to 16.5% (3.7%, 3.5–4.0%). In women with mass-related lesions (n = 900), the non-FPR was 14.2% for humans vs. 36.7% for AI (22.4%, 19.8–25.3%) at a sensitivity of 98.5% vs. 97.1% (1.5%, 0–3.5%).ConclusionThe application of AI during consensus conference might especially help readers to reduce false-positive recalls of masses at the expense of a small sensitivity reduction. Prospective studies are needed to further evaluate the screening benefit of AI in practice.Key Points• Integrating the use of artificial intelligence in the arbitration process reduces benign recalls and increases the positive predictive value of recall at the expense of some sensitivity loss.• Application of the artificial intelligence system to aid the decision to recall a woman seems particularly beneficial for masses, where the system reaches comparable sensitivity to that of the readers, but with considerably reduced false-positives.• About one-fourth of all recalled malignant lesions are not automatically marked by the system such that their evaluation (AI score) must be retrieved manually by the reader. A thorough reading of screening mammograms by readers to identify suspicious lesions therefore remains mandatory.

What do experts look at and what do experts find when reading mammograms?

Purpose: Radiologists sometimes fail to report clearly visible, clinically significant findings. Eye tracking can provide insight into the causes of such errors. Approach: We tracked eye movements of 17 radiologists, searching for masses in 80 mammograms (60 with masses). Results: Errors were classified using the Kundel etal. (1978) taxonomy: search errors (target never fixated), recognition errors (fixated ), or decision errors (fixated ). Error proportions replicated Krupinski (1996): search 25%, recognition 25%, and decision 50%. Interestingly, we found few differences between experts and residents in accuracy or eye movement metrics. Error categorization depends on the definition of the useful field of view (UFOV) around fixation. We explored different UFOV definitions, based on targeting saccades and search saccades. Targeting saccades averaged slightly longer than search saccades. Of most interest, we found that the probability that the eyes would move to the target on the next saccade or even on one of the next three saccades was strikingly low ( , even when the eyes were from the target). This makes it clear that observers do not fully process everything within a UFOV. Using a probabilistic UFOV, we find, unsurprisingly, that observers cover more of the image when no target is present than when it is found. Interestingly, we do not find evidence that observers cover too little of the image on trials when they miss the target. Conclusions: These results indicate that many errors in mammography reflect failed deployment of attention; not failure to fixate clinically significant locations.

Does it matter for the radiologists\u2019 performance whether they read short or long batches in organized mammographic screening?

ObjectiveTo analyze the association between radiologists’ performance and image position within a batch in screen reading of mammograms in Norway.MethodWe described true and false positives and true and false negatives by groups of image positions and batch sizes for 2,937,312 screen readings performed from 2012 to 2018. Mixed-effects models were used to obtain adjusted proportions of true and false positive, true and false negative, sensitivity, and specificity for different image positions. We adjusted for time of day and weekday and included the individual variation between the radiologists as random effects. Time spent reading was included in an additional model to explore a possible mediation effect.ResultTrue and false positives were negatively associated with image position within the batch, while the rates of true and false negatives were positively associated. In the adjusted analyses, the rate of true positives was 4.0 per 1000 (95% CI: 3.8–4.2) readings for image position 10 and 3.9 (95% CI: 3.7–4.1) for image position 60. The rate of true negatives was 94.4% (95% CI: 94.0–94.8) for image position 10 and 94.8% (95% CI: 94.4–95.2) for image position 60. Per 1000 readings, the rate of false negative was 0.60 (95% CI: 0.53–0.67) for image position 10 and 0.62 (95% CI: 0.55–0.69) for image position 60.ConclusionThere was a decrease in the radiologists’ sensitivity throughout the batch, and although this effect was small, our results may be clinically relevant at a population level or when multiplying the differences with the number of screen readings for the individual radiologists.Key Points• True and false positive reading scores were negatively associated with image position within a batch.• A decreasing trend of positive scores indicated a beneficial effect of a certain number of screen readings within a batch.• False negative scores increased throughout the batch but the association was not statistically significant.

Reducing racial disparities in time to breast cancer diagnosis: Impact of immediate screening mammogram reads during the COVID pandemic.

6508 Background: During the COVID-19 pandemic, barriers to access screening mammography along with goals to reduce visits supported immediate reading of screening mammograms. Typically, screening mammograms are reported after patients have left the facility. If imaging is abnormal, then an additional visit is needed for diagnostic imaging, introducing delays and potential disparities .Thus, we implemented an immediate-read screening mammography program and measured its impact on racial/ethnic disparities in time to diagnostic imaging after an abnormal screening mammogram. Methods: Responding to the COVID-19 pandemic, we implemented an immediate read screening program in late May 2020. Patients were provided imaging results before discharge and if the exam was abnormal, efforts were made to perform diagnostic imaging during that visit. We identified consecutive screening mammograms performed weekdays 8:00am-4:30pm and Saturdays 9:00am-4:00pm pre-implementation (6/1/19-10/31/19) and post-implementation (6/1/2020-10/31/2020). Exams left unread while awaiting comparison studies, due to technical factors, or for more than 10 days were excluded. Patient demographics and time from screening exam completion to report finalized were obtained from the electronic medical record. Cancer detection rate (CDR), abnormal interpretation rate (AIR), and positive predictive value (PPV) were calculated. Multivariable linear and logistic regression models were used to compare time from screening exam to report, same-day diagnostic imaging, and screening performance metrics pre- and post-implementation overall and by patient subgroups. Results: After 963 exams met exclusion criteria, a total of 8,222 pre- and 7,235 post-implementation exams were included. Median time to report finalization decreased from 61minutes (interquartile range [IQR]:24, 152) to 4 minutes (IQR:2, 7) for pre- and post-implementation periods (p &lt; 0.001). During the pre-implementation period, non-white patients had lower odds of having same-day diagnostic imaging after an abnormal screening exam (age-adjusted odds ratio: 0.28; 95% CI: 0.10, 0.78 p = 0.015). There was no evidence of this disparity post-implementation. AIR was higher in the pre- versus post-implementation period (6.3% versus 5.0%; p &lt; 0.001). There was no evidence of a difference in CDR (5.8 versus 4.2 cancers/1,000 exams) and PPV (9.2% versus 8.4%) for pre- versus post-implementation periods. Conclusions: An immediate read screening mammography program reduces racial/ethnic disparities in time to diagnostic imaging after an abnormal screening mammogram, thus promoting equity in access to care.[Table: see text]

Improving radiologist's ability in identifying particular abnormal lesions on mammograms through training test set with immediate feedback

It has been shown that there are differences in diagnostic accuracy of cancer detection on mammograms, from below 50% in developing countries to over 80% in developed world. One previous study reported that radiologists from a population in Asia displayed a low mammographic cancer detection of 48% compared with over 80% in developed countries, and more importantly, that most lesions missed by these radiologists were spiculated masses or stellate lesions. The aim of this study was to explore the performance of radiologists after undertaking a training test set which had been designed to improve the capability in detecting a specific type of cancers on mammograms. Twenty-five radiologists read two sets of 60 mammograms in a standardized mammogram reading room. The first test set focused on stellate or spiculated masses. When radiologists completed the first set, the system displayed immediate feedback to the readers comparing their performances in each case with the truth of cancer cases and cancer types so that the readers could identify individual-based errors. Later radiologists were asked to read the second set of mammograms which contained different types of cancers including stellate/spiculated masses, asymmetric density, calcification, discrete mass and architectural distortion. Case sensitivity, lesion sensitivity, specificity, receiver operating characteristics (ROC) and Jackknife alternative free-response receiver operating characteristics (JAFROC) were calculated for each participant and their diagnostic accuracy was compared between two sessions. Results showed significant improvement among radiologists in case sensitivity (+ 11.4%; P < 0.05), lesion sensitivity (+ 18.7%; P < 0.01) and JAFROC (+ 11%; P < 0.01) in the second set compared with the first set. The increase in diagnostic accuracy was also recorded in the detection of stellate/spiculated mass (+ 20.6%; P < 0.05). This indicated that the performance of radiologists in detecting malignant lesions on mammograms can be improved if an appropriate training intervention is applied after the readers’ weakness and strength are identified.

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.

Women’s attitudes to the use of AI image readers: a case study from a national breast screening programme

BackgroundResearchers and developers are evaluating the use of mammogram readers that use artificial intelligence (AI) in clinical settings.ObjectivesThis study examines the attitudes of women, both current and future users of...