Mammography Reading Research Articles

Artificial intelligence as an initial reader for double reading in breast cancer screening: a prospective initial study of 32,822 mammograms of the Egyptian population

BackgroundAlthough artificial intelligence (AI) has potential in the field of screening of breast cancer, there are still issues. It is vital to make sure AI does not overlook cancer or cause needless recalls. The aim of this work was to investigate the effectiveness of indulging AI in combination with one radiologist in the routine double reading of mammography for breast cancer screening. The study prospectively analyzed 32,822 screening mammograms. Reading was performed in a blind-paired style by (i) two radiologists and (ii) one radiologist paired with AI. A heatmap and abnormality scoring percentage were provided by AI for abnormalities detected on mammograms. Negative mammograms and benign-looking lesions that were not biopsied were confirmed by a 2-year follow-up.ResultsDouble reading by the radiologist and AI detected 1324 cancers (6.4%); on the other side, reading by two radiologists revealed 1293 cancers (6.2%) and presented a relative proportion of 1·02 (p < 0·0001). At the recall stage, suspicion and biopsy recommendation were more presented by the AI plus one radiologist combination than by the two radiologists. The interpretation of the mammogram by AI plus only one radiologist showed a sensitivity of 94.03%, a specificity of 99.75%, a positive predictive value of 96.571%, a negative predictive value of 99.567%, and an accuracy of 99.369% (from 99.252 to 99.472%). The positive likelihood ratio was 387.260, negative likelihood ratio was 0.060, and AUC “area under the curve” was 0.969 (0.967–0.971).ConclusionsAI could be used as an initial reader for the evaluation of screening mammography in routine workflow. Implementation of AI enhanced the opportunity to reduce false negative cases and supported the decision to recall or biopsy.

Take a break: should breaks be enforced during digital breast tomosynthesis reading sessions?

ObjectivesDigital breast tomosynthesis (DBT) can improve diagnostic accuracy compared to 2D mammography, but DBT reporting is time-consuming and potentially more fatiguing. Changes in diagnostic accuracy and subjective and objective fatigue were evaluated over a DBT reporting session, and the impact of taking a reporting break was assessed.Materials and methodsForty-five National Health Service (NHS) mammography readers from 6 hospitals read a cancer-enriched set of 40 DBT cases whilst eye tracked in this prospective cohort study, from December 2020 to April 2022. Eye-blink metrics were assessed as objective fatigue measures. Twenty-one readers had a reporting break, 24 did not. Subjective fatigue questionnaires were completed before and after the session. Diagnostic accuracy and subjective and objective fatigue measures were compared between the cohorts using parametric and non-parametric significance testing.ResultsReaders had on average 10 years post-training breast screening experience and took just under 2 h (105.8 min) to report all cases. Readers without a break reported greater levels of subjective fatigue (44% vs. 33%, p = 0.04), which related to greater objective fatigue: an increased average blink duration (296 ms vs. 286 ms, p < 0.001) and a reduced eye-opening velocity (76 mm/s vs. 82 mm/s, p < 0.001). Objective fatigue increased as the trial progressed for the no break cohort only (ps < 0.001). No difference was identified in diagnostic accuracy between the groups (accuracy: 87% vs. 87%, p = 0.92).ConclusionsImplementing a break during a 2-h DBT reporting session resulted in lower levels of subjective and objective fatigue. Breaks did not impact diagnostic accuracy, which may be related to the extensive experience of the readers.Clinical relevance statementDBT is being incorporated into many mammography screening programmes. Recognising that reporting breaks are required when reading large volumes of DBT studies ensures this can be factored in when setting up reading sessions.Trial registrationClinical trials registration number: NCT03733106Key Points• Use of digital breast tomosynthesis (DBT) in breast screening programmes can cause significant reader fatigue.• The effectiveness of incorporating reading breaks into DBT reporting sessions, to reduce mammography reader fatigue, was investigated using eye tracking.• Integrating breaks into DBT reporting sessions reduced reader fatigue; however, diagnostic accuracy was unaffected.

Using Radiomics-Based Machine Learning to Create Targeted Test Sets to Improve Specific Mammography Reader Cohort Performance: A Feasibility Study.

Mammography interpretation is challenging with high error rates. This study aims to reduce the errors in mammography reading by mapping diagnostic errors against global mammographic characteristics using a radiomics-based machine learning approach. A total of 36 radiologists from cohort A (n = 20) and cohort B (n = 16) read 60 high-density mammographic cases. Radiomic features were extracted from three regions of interest (ROIs), and random forest models were trained to predict diagnostic errors for each cohort. Performance was evaluated using sensitivity, specificity, accuracy, and AUC. The impact of ROI placement and normalization on prediction was investigated. Our approach successfully predicted both the false positive and false negative errors of both cohorts but did not consistently predict location errors. The errors produced by radiologists from cohort B were less predictable compared to those in cohort A. The performance of the models did not show significant improvement after feature normalization, despite the mammograms being produced by different vendors. Our novel radiomics-based machine learning pipeline focusing on global radiomic features could predict false positive and false negative errors. The proposed method can be used to develop group-tailored mammographic educational strategies to help improve future mammography reader performance.

Multi-vendor evaluation of artificial intelligence as an independent reader for double reading in breast cancer screening on 275,900 mammograms

BackgroundDouble reading (DR) in screening mammography increases cancer detection and lowers recall rates, but has sustainability challenges due to workforce shortages. Artificial intelligence (AI) as an independent reader (IR) in DR may provide a cost-effective solution with the potential to improve screening performance. Evidence for AI to generalise across different patient populations, screening programmes and equipment vendors, however, is still lacking.MethodsThis retrospective study simulated DR with AI as an IR, using data representative of real-world deployments (275,900 cases, 177,882 participants) from four mammography equipment vendors, seven screening sites, and two countries. Non-inferiority and superiority were assessed for relevant screening metrics.ResultsDR with AI, compared with human DR, showed at least non-inferior recall rate, cancer detection rate, sensitivity, specificity and positive predictive value (PPV) for each mammography vendor and site, and superior recall rate, specificity, and PPV for some. The simulation indicates that using AI would have increased arbitration rate (3.3% to 12.3%), but could have reduced human workload by 30.0% to 44.8%.ConclusionsAI has potential as an IR in the DR workflow across different screening programmes, mammography equipment and geographies, substantially reducing human reader workload while maintaining or improving standard of care.Trial registrationISRCTN18056078 (20/03/2019; retrospectively registered).

Visual hindsight bias for abnormal mammograms in radiologists.

Hindsight bias-where people falsely believe they can accurately predict something once they know about it-is a pervasive decision-making phenomenon, including in the interpretation of radiological images. Evidence suggests it is not only a decision-making phenomenon but also a visual perception one, where prior information about an image enhances our visual perception of the contents of that image. The current experiment investigates to what extent expert radiologists perceive mammograms with visual abnormalities differently when they know what the abnormality is (a visual hindsight bias), above and beyond being biased at a decision level. experienced mammography readers were presented with a series of unilateral abnormal mammograms. After each case, they were asked to rate their confidence on a 6-point scale that ranged from confident mass to confident calcification. We used the random image structure evolution method, where the images repeated in an unpredictable order and with varied noise, to ensure any biases were visual, not cognitive. Radiologists who first saw an original image with no noise were more accurate in the max noise level condition [area under the curve ] than those who first saw the degraded images (; difference: ), suggesting that radiologists' visual perception of medical images is enhanced by prior visual experience with the abnormality. Overall, these results provide evidence that expert radiologists experience not only decision level but also visual hindsight bias, and have potential implications for negligence lawsuits.

Automation Bias in Mammography: The Impact of Artificial Intelligence BI-RADS Suggestions on Reader Performance.

Background Automation bias (the propensity for humans to favor suggestions from automated decision-making systems) is a known source of error in human-machine interactions, but its implications regarding artificial intelligence (AI)-aided mammography reading are unknown. Purpose To determine how automation bias can affect inexperienced, moderately experienced, and very experienced radiologists when reading mammograms with the aid of an artificial intelligence (AI) system. Materials and Methods In this prospective experiment, 27 radiologists read 50 mammograms and provided their Breast Imaging Reporting and Data System (BI-RADS) assessment assisted by a purported AI system. Mammograms were obtained between January 2017 and December 2019 and were presented in two randomized sets. The first was a training set of 10 mammograms, with the correct BI-RADS category suggested by the AI system. The second was a set of 40 mammograms in which an incorrect BI-RADS category was suggested for 12 mammograms. Reader performance, degree of bias in BI-RADS scoring, perceived accuracy of the AI system, and reader confidence in their own BI-RADS ratings were assessed using analysis of variance (ANOVA) and repeated-measures ANOVA followed by post hoc tests and Kruskal-Wallis tests followed by the Dunn post hoc test. Results The percentage of correctly rated mammograms by inexperienced (mean, 79.7% ± 11.7 [SD] vs 19.8% ± 14.0; P < .001; r = 0.93), moderately experienced (mean, 81.3% ± 10.1 vs 24.8% ± 11.6; P < .001; r = 0.96), and very experienced (mean, 82.3% ± 4.2 vs 45.5% ± 9.1; P = .003; r = 0.97) radiologists was significantly impacted by the correctness of the AI prediction of BI-RADS category. Inexperienced radiologists were significantly more likely to follow the suggestions of the purported AI when it incorrectly suggested a higher BI-RADS category than the actual ground truth compared with both moderately (mean degree of bias, 4.0 ± 1.8 vs 2.4 ± 1.5; P = .044; r = 0.46) and very (mean degree of bias, 4.0 ± 1.8 vs 1.2 ± 0.8; P = .009; r = 0.65) experienced readers. Conclusion The results show that inexperienced, moderately experienced, and very experienced radiologists reading mammograms are prone to automation bias when being supported by an AI-based system. This and other effects of human and machine interaction must be considered to ensure safe deployment and accurate diagnostic performance when combining human readers and AI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Baltzer in this issue.

Use of Artificial Intelligence for Reducing Unnecessary Recalls at Screening Mammography: A Simulation Study.

To conduct a simulation study to determine whether artificial intelligence (AI)-aided mammography reading can reduce unnecessary recalls while maintaining cancer detection ability in women recalled after mammography screening. A retrospective reader study was performed by screening mammographies of 793 women (mean age ± standard deviation, 50 ± 9 years) recalled to obtain supplemental mammographic views regarding screening mammography-detected abnormalities between January 2016 and December 2019 at two screening centers. Initial screening mammography examinations were interpreted by three dedicated breast radiologists sequentially, case by case, with and without AI aid, in a single session. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and recall rate for breast cancer diagnosis were obtained and compared between the two reading modes. Fifty-four mammograms with cancer (35 invasive cancers and 19 ductal carcinomas in situ) and 739 mammograms with benign or negative findings were included. The reader-averaged AUC improved after AI aid, from 0.79 (95% confidence interval [CI], 0.74-0.85) to 0.89 (95% CI, 0.85-0.94) (p < 0.001). The reader-averaged specificities before and after AI aid were 41.9% (95% CI, 39.3%-44.5%) and 53.9% (95% CI, 50.9%-56.9%), respectively (p < 0.001). The reader-averaged sensitivity was not statistically different between AI-unaided and AI-aided readings: 89.5% (95% CI, 83.1%-95.9%) vs. 92.6% (95% CI, 86.2%-99.0%) (p = 0.053), although the sensitivities of the least experienced radiologists before and after AI aid were 79.6% (43 of 54 [95% CI, 66.5%-89.4%]) and 90.7% (49 of 54 [95% CI, 79.7%-96.9%]), respectively (p = 0.031). With AI aid, the reader-averaged recall rate decreased by from 60.4% (95% CI, 57.8%-62.9%) to 49.5% (95% CI, 46.5%-52.4%) (p < 0.001). AI-aided reading reduced the number of recalls and improved the diagnostic performance in our simulation using women initially recalled for supplemental mammographic views after mammography screening.

Mammography self-evaluation online test for screening readers: an Italian Society of Medical Radiology (SIRM) initiative.

To report and analyse the characteristics and performance of the first cohort of Italian radiologists completing the national mammography self-evaluation online test established by the Italian Society of Medical Radiology (SIRM). A specifically-built dataset of 132 mammograms (24 with screen-detected cancers and 108 negative cases) was preliminarily tested on 48 radiologists to define pass thresholds (62% sensitivity and 86% specificity) and subsequently made available online to SIRM members during a 13-month timeframe between 2018 and 2019. Associations between participants' characteristics, pass rates, and diagnostic accuracy were then investigated with descriptive statistics and univariate and multivariable regression analyses. A total of 342 radiologists completed the test, 151/342 (44.2%) with success. All individual variables, except gender, showed a significant correlation with pass rates and diagnostic sensitivity, confirmed by univariate logistic regression, while only involvement in organised screening programs and number of mammograms read per year showed a positive association with specificity at univariate logistic regression. In the multivariable regression analysis, fewer variables remained significant: > 3000 mammograms read per year for success rate; female gender, public practice setting, and higher experience self-judgement for sensitivity; no variables were significantly associated with specificity. This national self-evaluation test effectively differentiated multiple aspects of mammographic reading experience, but specific breast imaging experience was shown not to strictly guarantee good diagnostic accuracy. Due to its easy use and the validity of obtained results, this test could be extended to all Italian breast radiologists, regardless of their experience, also as a Breast Unit accreditation criterion. • This self-evaluation test was found to be able to differentiate various degrees of mammographic interpretation experience. • Breast cancer screening readers should undergo a self-assessment test, since experience parameters alone do not guarantee diagnostic ability.

The relationship between missed breast cancers on mammography in a test-set based assessment scheme and real-life performance in a National Breast Screening Programme

PurposeThis retrospective study determined whether a test-set based assessment scheme (PERFORMS) used in a national breast screening programme could be used to predict real-life performance by investigating if the number of cancers missed by mammography readers in real-life related to the number of cancers missed in the PERFORMS test-set and whether real-life reading volumes affected performance. MethodData was obtained from consenting readers in the screening programme in England (NHSBSP) where double reading is standard. The rate of cancers missed by individual first readers but correctly identified by second readers was compared with the number of cancers missed in the PERFORMS test-set over a 3-year period. NHSBSP readers are required to interpret at least 1500 cases per year as a first reader, so results were compared between readers who exceeded this target and those that did not. Parametric and non-parametric correlations were calculated. ResultsAmongst the 536 readers, there was a highly significant positive correlation between the real-life and PERFORMS test-set missed cancer metrics (Pearson Correlation = 0.228, n = 536, p < .0001, Spearman's rho = 0.265, n = 536, p < .0001). There was no significant difference in rates of missed cancers between the 452 readers who exceeded the 1500 first read per year target and those who did not (t(94.2) = −1.87, p = .0643, r = 0.19). ConclusionsThe use of a test-set based assessment scheme accurately reflects real-life mammography reading performance, indicating that it can be a useful tool in identifying poor reader performance.

Effectiveness of Tomosynthesis Versus Digital Mammography in the Diagnosis of Suspicious Lesions for Breast Cancer in an Asymptomatic Population.

IntroductionThe most frequent malignant tumor in women is breast cancer. A dense breast may mask lesions within the tissue. The constant improvement in diagnosis techniques has made the diagnosis more accurate. Digital mammography loses sensitivity in dense breasts as lesions may be masked by the over-position of tissue. Tomosynthesis increases sensitivity and specificity over diagnostic mammography. In this study, we examine the effectiveness of tomosynthesis versus digital mammography in asymptomatic patients.Materials and methodsA cohort study of 1,499 Mexican patients that came for screening at a private health service from January to December 2015. A Breast Imaging Reporting and Database System (BI-RADS) classification was given by a breast radiologist with the digital mammography reading. Later, a second breast radiologist reviewed the same patients with tomosynthesis and assigned a second BI-RADS category.ResultsPatients were divided into three age groups. The one with the most had patients between 40-49 years (51.3%), where re-staging to a higher BI-RADS occurred in 40 patients. Re-staging to a lower category was most common in the group of age above 50, where 30 patients were assigned BI-RADS 2 after tomosynthesis. Dense breast (C and D) represented 38%. After tomosynthesis, 28 patients were classified as BI-RADS 4 or 5. The prevalence of diseases in groups BI-RADS 4 and BI-RADS 5 after re-staging and a breast cancer result was 0.024, with a sensitivity of 54% and a specificity of 88%. When re-staging 2D mammography with 3D tomosynthesis for suspicious lesions classified BI-RADS 3, 4, or 5, the prevalence was 0.23, with a sensitivity of 45% and a specificity of 98%.In this study, patients were asymptomatic, yet 20 breast cancers were detected, with a sensitivity of 54% and a specificity of 88%, exceeding the specificity of diagnostic mammography. Moreover, when re-staging to a BI-RADS of suspicious findings, the sensitivity was 45%, with a specificity of as high as 98%.

Optimum screening mammography reading volumes: evidence from the NHS Breast Screening Programme.

Minimum caseload standards for professionals examining breast screening mammograms vary from 480 (US) to 5000 (Europe). We measured the relationship between the number of women's mammograms examined per year and reader performance. We extracted routine records from the English NHS Breast Screening Programme for readers examining between 1000 and 45,000 mammograms between April 2014 and March 2017. We measured the relationship between the volume of cases read and screening performance (cancer detection rate, recall rate, positive predictive value of recall (PPV) and discrepant cancers) using linear logistic regression. We also examined the effect of reader occupational group on performance. In total, 759 eligible mammography readers (445 consultant radiologists, 235 radiography advanced practitioners, 79 consultant radiographers) examined 6.1 million women's mammograms during the study period. PPV increased from 12.9 to 14.4 to 17.0% for readers examining 2000, 5000 and 10000 cases per year respectively. This was driven by decreases in recall rates from 5.8 to 5.3 to 4.5 with increasing volume read, and no change in cancer detection rate (from 7.6 to 7.6 to 7.7). There was no difference in cancer detection rate with reader occupational group. Consultant radiographers had higher recall rate and lower PPV compared to radiologists (OR 1.105, p = 0.012; OR 0.874, p = 0.002, unadjusted). Positive predictive value of screening increases with the total volume of cases examined per reader, through decreases in numbers of cases recalled with no concurrent change in numbers of cancers detected. • In the English Breast Screening Programme, readers who examined a larger number of cases per year had a higher positive predictive value, because they recalled fewer women for further tests but detected the same number of cancers. • Reader type did not affect cancer detection rate, but consultant radiographers had a higher recall rate and lower positive predictive value than consultant radiologists, although this was not adjusted for length of experience.

The Relationship between Mammography Readers' Real-Life Performance and Performance in a Test Set-based Assessment Scheme in a National Breast Screening Program.

To compare an individual's Personal Performance in Mammographic Screening (PERFORMS) score with their Breast Screening Information System (BSIS) real-life performance data and determine which parameters in the PERFORMS scheme offer the best reflection of BSIS real-life performance metrics. In this retrospective study, the BSIS real-life performance metrics of individual readers (n = 452) in the National Health Service Breast Screening Program (NHSBSP) in England were compared with performance in the test set-based assessment scheme over a 3-year period from 2013 to 2016. Cancer detection rate (CDR), recall rate, and positive predictive value (PPV) were calculated for each reader, for both real-life screening and the PERFORMS test. For each metric, real-life and test set versions were compared using a Pearson correlation. The real-life CDR, recall rate, and PPV of outliers were compared against other readers (nonoutliers) using analysis of variance. BSIS real-life CDRs, recall rates, and PPVs showed positive correlations with the equivalent PERFORMS measures (P < .001, P = .002, and P < .001, respectively). The mean real-life CDR of PERFORMS outliers was 7.2 per 1000 women screened and was significantly lower than other readers (nonoutliers) where the real-life CDR was 7.9 (P = .002). The mean real-life screening PPV of PERFORMS outliers was 0.14% and was significantly lower than the nonoutlier group who had a mean PPV of 0.17% (P = .006). The use of test set-based assessment schemes in a breast screening program has the potential to predict and identify poor performance in real life.© RSNA, 2020Keywords: Breast, ScreeningSee also the commentary by Thigpen and Rapelyea in this issue.

External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms

A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening. To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. This retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). Positive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). The median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. To our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers.

Impact of time of day on radiology image interpretations

To examine the impact of the time of day on radiologists' mammography reading performance. Retrospective mammographic reading assessment data were collected from the BreastScreen Reader Assessment Strategy database and included timestamps of the readings and reader-specific demographic data of 197 radiologists. The radiologists performed the readings in a workshop setting with test case sets enriched with malignancies (one-third of cases were malignant). The collected data were evaluated with an analysis of covariance to determine whether time of day influenced radiologists' specificity, lesion sensitivity or the jackknife alternative free-response receiver operating characteristic (JAFROC). After adjusting for radiologist experience and fellowship, specificity varied significantly by time of day (p=0.027), but there was no evidence of any significant impact on lesion sensitivity (p=0.441) or JAFROC (p=0.120). The collected data demonstrated that specificity during the late morning (10.00-12.00) was 71.7%; this was significantly lower than in the early morning (08.00-10.00) and mid-afternoon (14.00-16.00), which were 82.74% (p=0.003) and 81.39% (p=0.031), respectively. Specificity during the late afternoon (16.00-18.00) was 73.95%; this was significantly lower than in the early morning (08.00-10.00) and mid-afternoon (14.00-16.00), which were 82.74% (p=0.003) and 81.39% (p=0.031), respectively. The results indicated that the time of day may influence radiologists' performance, specifically their ability to identify normal images correctly.

Quality of mammography and breast cancer screening in ArgentinaQualidade da mamografia e prevenção do câncer de mama na Argentina

RESUMENSe presentan los resultados del Plan de calidad en mamografía del Programa Nacional del Cáncer de Mama del Instituto Nacional del Cáncer de la República Argentina, enfocado en mejorar la calidad de la mamografía en el sector público de salud e implementar el tamizaje de cáncer de mama por este método diagnóstico. El Plan se comenzó a ejecutar en 2011 con base en la premisa de que una mamografía de mala calidad impide el diagnóstico temprano del cáncer de mama. En ese momento, en Argentina existía poca conciencia sobre la importancia de los controles de calidad, y los continuos cambios en los niveles jerárquicos del sistema de salud tendían a obstaculizar el desarrollo organizado del programa. El Plan consistió en la revisión y el control de calidad de las instalaciones de mamografía, la capacitación de recursos humanos técnicos y médicos y la puesta en marcha de un sistema de acreditación de los servicios de mamografía por parte del Instituto Nacional del Cáncer. La percepción de la importancia de la calidad en el personal involucrado ha mejorado y se obtuvo un panorama general del estado de la mamografía a nivel nacional en cuanto a la calidad, la tecnología, la cantidad de equipos y las posibilidades de implementación del tamizaje. Se capacitó al personal técnico y médico mediante el uso de diferentes metodologías y se impulsó la unificación de la lectura mamográfica en las provincias intervinientes.

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.

Characteristics of screen-detected cancers following concordant or discordant recalls at blinded double reading in biennial digital screening mammography.

To analyse which mammographic and tumour characteristics led to concordant versus discordant recalls at blinded double reading to further optimise our breast cancer screening programme. We included a consecutive series of 99,013 screening mammograms obtained between July 2013 and January 2015. All mammograms were double read in a blinded fashion. Discordant readings were routinely recalled without consensus or arbitration. During the 2-year follow-up, relevant data of the recalled women were collected. We compared mammographic characteristics, screening outcome and tumour characteristics between concordant and discordant recalls. There were 2,543 concordant recalls (71.4%) and 997 discordant recalls (28.0%). The positive predictive value of a concordant recall was significantly higher (23.5% vs. 10.0%, p < 0.001). The proportion of BI-RADS 0 was significantly higher in the discordant recall group (75.7% vs. 56.3%, p < 0.001). Discordant recalls were more often an asymmetry or architectural distortion (21.8% vs. 13.2% and 9.3% vs. 6.5%, respectively, p < 0.001). There were no differences in the distribution of DCIS and invasive cancers and tumour characteristics were comparable for the two groups, except for a more favourable tumour grade in the discordant recall group (54.7% vs. 39.9% grade I tumours, p = 0.022). Screen-detected cancers detected by a discordant reading show a more favourable tumour grade than cancers diagnosed after a concordant recall. The higher proportion of asymmetries and architectural distortions in this group provide a possible target for improving screening programmes by additional training of screening radiologists and the implementation of digital breast tomosynthesis. • With blinded double reading of screening mammograms, screen-detected cancers detected by a discordant reading show a more favourable tumour grade than cancers diagnosed after a concordant recall. • The proportions of asymmetries and architectural distortions are higher in case of a discordant reading. • Possible improvement strategies could target additional training of screening radiologists and the implementation of digital breast tomosynthesis in breast cancer screening programmes.

Deep Gaze Velocity Analysis During Mammographic Reading for Biometric Identification of Radiologists

Several studies have confirmed that the gaze velocity of the human eye can be utilized as a behavioral biometric or personalized biomarker. In this study, we leverage the local feature representation capacity of convolutional neural networks (CNNs) for eye gaze velocity analysis as the basis for biometric identification of radiologists performing breast cancer screening. Using gaze data collected from 10 radiologists reading 100 mammograms of various diagnoses, we compared the performance of a CNN-based classification algorithm with two deep learning classifiers, deep neural network and deep belief network, and a previously presented hidden Markov model classifier. The study showed that the CNN classifier is superior compared to alternative classification methods based on macro F1-scores derived from 10-fold cross-validation experiments. Our results further support the efficacy of eye gaze velocity as a biometric identifier of medical imaging experts.

Assessment of Jordanian Radiologist Performance in the Detection of Breast Cancers

This study aims to monitor diagnostic accuracy amongst Jordanian mammography readers and identify parameters linked to higher levels of performance. In this study, we have used the Breast Screen Reader Assessment Strategy (BREAST) platform to facilitate 27 radiologists in reading a case set of 60 digital mammograms, 20 of which included cancers. Each case consisted of the four standard cranio-caudal (CC) and medio-lateral oblique (MLO) projections. All radiologists were registered to read mammograms at their workplace by the Jordanian Ministry of Health. Each reader was asked to locate any malignancies, provide a confidence rating using a scale of 1 - 5, and identify the type of appearance. All images were displayed using 8 MP monitor, supported by radiology workstations with full image manipulation facilities. Results were evaluated using Jackknife Alternative Free-Response Receiver Operating Characteristic (JAFROC). Demographics obtained from each radiologist regarding their experience, qualifications and breast-reading activities were correlated against JAFROC scores using Spearman techniques. The results showed that the mean JAFROC score was 0. 52 (95% confidence interval (CI): 0.46, 0.58); location sensitivity score was 0. 41 (95% CI: 0.41, 0.56); specificity score was 0.73 (95% CI: 0.68, 0.83). Higher performance in term of JAFROC scores was directly related to number of years since professional qualification (r = 0.433; p = 0.024), number of years reading breast images (r = 0.62; r = 0.001) and number of mammography images read per year (r = 0.69; p = 0.001). On the other hand, higher performance was inversely linked to the frequency of reading other modalities per week (r = -0.48; p = 0.010). No other statistical differences were significant. Finally, higher radiologists’ performance in cancer detection is correlated with increasing the number of mammograms reads per week.

Accuracy of Double Mammography Reading in Population-based Screening

Accuracy of Double Mammography Reading in Population-based Screening