RESUMEN
Background The high volume of data in digital breast tomosynthesis (DBT) and the lack of agreement on how to best implement it in screening programs makes its use challenging. Purpose To compare radiologist performance when reading single-view wide-angle DBT images with and without an artificial intelligence (AI) system for decision and navigation support. Materials and Methods A retrospective observer study was performed with bilateral mediolateral oblique examinations and corresponding synthetic two-dimensional images acquired between June 2016 and February 2018 with a wide-angle DBT system. Fourteen breast screening radiologists interpreted 190 DBT examinations (90 normal, 26 with benign findings, and 74 with malignant findings), with the reference standard being verified by using histopathologic analysis or at least 1 year of follow-up. Reading was performed in two sessions, separated by at least 4 weeks, with a random mix of examinations being read with and without AI decision and navigation support. Forced Breast Imaging Reporting and Data System (categories 1-5) and level of suspicion (1-100) scores were given per breast by each reader. The area under the receiver operating characteristic curve (AUC) and the sensitivity and specificity were compared between conditions by using the public-domain iMRMC software. The average reading times were compared by using the Wilcoxon signed rank test. Results The 190 women had a median age of 54 years (range, 48-63 years). The examination-based reader-averaged AUC was higher when interpreting results with AI support than when reading unaided (0.88 [95% CI: 0.84, 0.92] vs 0.85 [95% CI: 0.80, 0.89], respectively; P = .01). The average sensitivity increased with AI support (64 of 74, 86% [95% CI: 80%, 92%] vs 60 of 74, 81% [95% CI: 74%, 88%]; P = .006), whereas no differences in the specificity (85 of 116, 73.3% [95% CI: 65%, 81%] vs 83 of 116, 71.6% [95% CI: 65%, 78%]; P = .48) or reading time (48 seconds vs 45 seconds; P = .35) were detected. Conclusion Using a single-view digital breast tomosynthesis (DBT) and artificial intelligence setup could allow for a more effective screening program with higher performance, especially in terms of an increase in cancers detected, than using single-view DBT alone. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Chan and Helvie in this issue.
Asunto(s)
Inteligencia Artificial , Neoplasias de la Mama/diagnóstico por imagen , Competencia Clínica , Técnicas de Apoyo para la Decisión , Interpretación de Imagen Asistida por Computador/métodos , Mamografía/métodos , Aprendizaje Profundo , Detección Precoz del Cáncer , Femenino , Humanos , Tamizaje Masivo , Persona de Mediana Edad , Estudios Retrospectivos , Sensibilidad y EspecificidadRESUMEN
OBJECTIVES: To describe a randomized controlled trial (RCT) of digital breast tomosynthesis including synthesized two-dimensional mammograms (DBT) versus digital mammography (DM) in a population-based screening program for breast cancer and to compare selected secondary screening outcomes for the two techniques. METHODS: This RCT, performed in Bergen as part of BreastScreen Norway, was approved by the Regional Committees for Medical Health Research Ethics. All screening attendees in Bergen were invited to participate, of which 89% (14,274/15,976) concented during the first year, and were randomized to DBT (n = 7155) or DM (n = 7119). Secondary screening outcomes were stratified by mammographic density and compared using two-sample t-tests, chi-square tests, ANOVA, negative binomial regression and tests of proportions (z tests). RESULTS: Mean reading time was 1 min 11 s for DBT and 41 s for DM (p < 0.01). Mean time spent at consensus was 3 min 12 s for DBT and 2 min 12 s for DM (p < 0.01), while the rate of cases discussed at consensus was 6.4% and 7.4%, respectively for DBT and DM (p = 0.03). The recall rate was 3.0% for DBT and 3.6% for DM (p = 0.03). For women with non-dense breasts, recall rate was 2.2% for DBT versus 3.4% for DM (p = 0.04). The rate did not differ for women with dense breasts (3.6% for both). Mean glandular dose per examination was 2.96 mGy for DBT and 2.95 mGy for DM (p = 0.433). CONCLUSIONS: Interim analysis of a screening RCT showed that DBT took longer to read than DM, but had significantly lower recall rate than DM. We found no differences in radiation dose between the two techniques. KEY POINTS: ⢠In this RCT, DBT was associated with longer interpretation time than DM ⢠Recall rates were lower for DBT than for DM ⢠Mean glandular radiation dose did not differ between DBT and DM.
Asunto(s)
Densidad de la Mama , Neoplasias de la Mama/diagnóstico , Mamografía/métodos , Tamizaje Masivo/métodos , Vigilancia de la Población/métodos , Anciano , Neoplasias de la Mama/epidemiología , Femenino , Humanos , Incidencia , Persona de Mediana Edad , Noruega/epidemiologíaRESUMEN
BACKGROUND: The main aim of mammographic screening is to reduce the mortality from breast cancer. However, use of ionizing radiation is considered a potential harm due to the possible risk of inducing cancer in healthy women. PURPOSE: To estimate the potential number of radiation-induced breast cancers, radiation-induced breast cancer deaths, and lives saved due to implementation of organized mammographic screening as performed in Norway. MATERIAL AND METHODS: We used a previously published excess absolute risk model which assumes a linear no-threshold dose-response. The estimates were calculated for 100,000 women aged 50-69 years, a screening interval of 2 years, and with an assumed follow-up until the age of 85 or 105 years. Radiation doses of 0.7, 2.5, and 5.7 mGy per screening examination, a latency time of 5 or 10 years, and a dose and dose-rate effectiveness factor (DDREF) of 1 or 2 were applied. RESULTS: The total lifetime risk of radiation-induced breast cancers per 100,000 women was 10 (95% CI: 4-25) if the women were followed from the ages of 50 to 85 years, for a dose of 2.5 mGy, a latency time of 10 years, and a DDREF of 1. For the same parameter values the number of radiation-induced breast cancer death was 1 (95% CI: 0-2). The assumed number of lives saved is approximately 350. CONCLUSION: The risk of radiation-induced breast cancer and breast cancer death due to mammographic screening is minimal. Women should not be discouraged from attending screening due to fear of radiation-induced breast cancer death.
Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/epidemiología , Detección Precoz del Cáncer/estadística & datos numéricos , Mamografía/estadística & datos numéricos , Tamizaje Masivo/estadística & datos numéricos , Neoplasias Inducidas por Radiación/epidemiología , Factores de Edad , Anciano , Femenino , Estudios de Seguimiento , Humanos , Mamografía/efectos adversos , Mamografía/métodos , Tamizaje Masivo/efectos adversos , Persona de Mediana Edad , Neoplasias Inducidas por Radiación/etiología , Noruega/epidemiología , Dosis de Radiación , Medición de Riesgo/estadística & datos numéricosRESUMEN
Objective: To compare breast characteristics, compression parameters, and early performance measures (rates of recall, screen-detected and interval breast cancer, and histopathologic tumour characteristics) for mammographic screening at a stationary versus mobile screening unit. Methods: Results from 92,408 mammographic screening examinations performed as part of BreastScreen Norway during 20082017 at either a stationary (n = 52,620) or mobile (n = 39,788) unit in Hordaland county were compared using descriptive statistics and generalized estimating equations. A generalized estimating equation for a binary outcome was used to estimate crude and adjusted odds ratios with 95% confidence intervals for the outcomes of interest. Adjusted generalized estimating equation models included age, breast volume, and density grade as covariates. Results: Screening at the stationary unit was performed on smaller breasts with higher mammographic density, using lower compression force but higher pressure than at the mobile unit. Using the stationary screening unit as reference, for women screened at the mobile unit, the adjusted odds ratio was: for recall 0.94 (95% CI: 0.87--1.01), screen-detected breast cancer 0.92 (95% CI: 0.78--1.10), and interval breast cancer 1.17 (95% CI: 0.831.64). Conclusions: The quality of care did not differ for women screened at the stationary versus the mobile unit, but there were differences between the women who attended the two units. Sociodemographic factors should be included in future analyses to fully understand the risk of breast cancer among women residing in urban versus rural areas.
Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Mama/diagnóstico por imagen , Mamografía , Unidades Móviles de Salud , Adulto , Anciano , Instituciones de Atención Ambulatoria , Mama/anatomía & histología , Densidad de la Mama , Detección Precoz del Cáncer , Femenino , Humanos , Mamografía/métodos , Persona de Mediana Edad , NoruegaRESUMEN
PURPOSE: Evaluate the utility of tests in a proposed protocol for constancy control of digital mammography systems. METHODS: The protocol contained tests for image acquisition, mechanical function and safety, monitors and printers, and viewing conditions. Nine sites with digital systems from four equipment manufacturers were recruited. Dedicated PMMA test objects and Excel spreadsheets were developed. Quantitative measurements were done on processed images for systems where these images were the ones most readily available. For daily assessment of the automatic exposure control system, a homogeneous PMMA phantom was exposed under clinical conditions. The mAs and signal to noise ratio (SNR) were recorded, the deviation from a target value calculated, and the resulting image inspected for artifacts. For thickness tracking, the signal difference to noise ratio obtained for three thicknesses was calculated. Detector uniformity was assessed through comparison of SNR values for regions of interest in the center and corners of an image of a homogeneous test object. Mechanical function and safety control included a compression test, a checklist for mechanical aspects, and control of field alignment. Monitor performance was evaluated by visual inspection of the AAPM TG 18 QC test image [E. Samei et al., "Assessment of display performance for medical imaging systems," Task Group 18 (Madison, WI, April 2005)]. RESULTS: For quantitative parameters, target values and tolerance limits were established. Test results exceeding the limits were registered. Most systems exhibited stable mAs values, indicating that the tolerance limit of +/- 10% was readily achievable. The SNR also showed little variation, indicating that the tolerance limit of +/- 20% was too wide. At one site, a defective grid caused artifacts that were visible in the test images. The monitor controls proved more difficult to implement due to both difficulties importing and displaying the test image, and the radiographic technologists not getting necessary access to the reading stations. CONCLUSIONS: The proposed tests could easily be performed by trained radiographic technologists and within a time frame comparable to similar programs for analog systems. Tests with quantitative measures were more readily performed than procedures that required a subjective evaluation. Several of the proposed tests revealed equipment performance that required intervention, and which would otherwise have gone unnoticed. They therefore defend a place in a vendor-independent constancy control protocol.
Asunto(s)
Mamografía/normas , Intensificación de Imagen Radiográfica/normas , Fantasmas de Imagen , Control de Calidad , Factores de TiempoRESUMEN
This article aims to present the protocol on Quality Controls in Digital Mammography published online in 2015 by the European Federation of Organisations for Medical Physics (EFOMP) which was developed by a Task Force under the Mammo Working Group. The main objective of this protocol was to define a minimum set of easily implemented quality control tests on digital mammography systems that can be used to assure the performance of a system within a set and acceptable range. Detailed step-by-step instructions have been provided, limiting as much as possible any misinterpretations or variations by the person performing. It is intended that these tests be implemented as part of the daily routine of medical physicists and system users throughout Europe in a harmonised way so allowing results to be compared. In this paper the main characteristics of the protocol are illustrated, including examples, together with a brief summary of the contents of each chapter. Finally, instructions for the download of the full protocol and of the related software tools are provided.