Background Artificial intelligence (AI) systems performing at radiologist-like levels in the evaluation of digital mammography (DM) would improve breast cancer screening accuracy and efficiency. We aimed to compare the stand-alone performance of an AI system to that of radiologists in detecting breast cancer in DM. Methods Nine multi-reader, multi-case study datasets previously used for different research purposes in seven countries were collected. Each dataset consisted of DM exams acquired with systems from four different vendors, multiple radiologists’ assessments per exam, and ground truth verified by histopathological analysis or follow-up, yielding a total of 2652 exams (653 malignant) and interpretations by 101 radiologists (28 296 independent interpretations). An AI system analyzed these exams yielding a level of suspicion of cancer present between 1 and 10. The detection performance between the radiologists and the AI system was compared using a noninferiority null hypothesis at a margin of 0.05. Results The performance of the AI system was statistically noninferior to that of the average of the 101 radiologists. The AI system had a 0.840 (95% confidence interval [CI] = 0.820 to 0.860) area under the ROC curve and the average of the radiologists was 0.814 (95% CI = 0.787 to 0.841) (difference 95% CI = −0.003 to 0.055). The AI system had an AUC higher than 61.4% of the radiologists. Conclusions The evaluated AI system achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting. Although promising, the performance and impact of such a system in a screening setting needs further investigation.

To compare breast cancer detection performance of radiologists reading mammographic examinations unaided versus supported by an artificial intelligence (AI) system. Materials and Methods: An enriched retrospective, fully crossed, multireader, multicase, HIPAA-compliant study was performed. Screening digital mammographic examinations from 240 women (median age, 62 years; range, 39-89 years) performed between 2013 and 2017 were included. The 240 examinations (100 showing cancers, 40 leading to false-positive recalls, 100 normal) were interpreted by 14 Mammography Quality Standards Act-qualified radiologists, once with and once without AI support. The readers provided a Breast Imaging Reporting and Data System score and probability of malignancy. AI support provided radiologists with interactive decision support (clicking on a breast region yields a local cancer likelihood score), traditional lesion markers for computer-detected abnormalities, and an examination-based cancer likelihood score. The area under the receiver operating characteristic curve (AUC), specificity and sensitivity, and reading time were compared between conditions by using mixed-models analysis dof variance and generalized linear models for multiple repeated measurements. Results: On average, the AUC was higher with AI support than with unaided reading (0.89 vs 0.87, respectively; P = .002). Sensitivity increased with AI support (86% [86 of 100] vs 83% [83 of 100]; P = .046), whereas specificity trended toward improvement (79% [111 of 140]) vs 77% [108 of 140]; P = .06). Reading time per case was similar (unaided, 146 seconds; supported by AI, 149 seconds; P = .15). The AUC with the AI system alone was similar to the average AUC of the radiologists (0.89 vs 0.87). Conclusion: Radiologists improved their cancer detection at mammography when using an artificial intelligence system for support, without requiring additional reading time. Published under a CC BY 4.0 license.

Mammography is a very well-established imaging modality for the early detection and diagnosis of breast cancer. However, since the introduction of digital imaging to the realm of radiology, more advanced, and especially tomographic imaging methods have been made possible. One of these methods, breast tomosynthesis, has finally been introduced to the clinic for routine everyday use, with potential to in the future replace mammography for screening for breast cancer. In this two part paper, the extensive research performed during the development of breast tomosynthesis is reviewed, with a focus on the research addressing the medical physics aspects of this imaging modality. This first paper will review the research performed on the issues relevant to the image acquisition process, including system design, optimization of geometry and technique, x-ray scatter, and radiation dose. The companion to this paper will review all other aspects of breast tomosynthesis imaging, including the reconstruction process.

Tomosynthesis of the breast is currently a topic of intense interest as a logical next step in the evolution of digital mammography. This study reports on the computation of glandular radiation dose in digital tomosynthesis of the breast. Previously, glandular dose estimations in tomosynthesis have been performed using data from studies of radiation dose in conventional planar mammography. This study evaluates, using Monte Carlo methods, the normalized glandular dose (D g N) to the breast during a tomosynthesis study, and characterizes its dependence on breast size, tissue composition, and x-ray spectrum. The conditions during digital tomosynthesis imaging of the breast were simulated using a computer program based on the Geant4 toolkit. With the use of simulated breasts of varying size, thickness and tissue composition, the D g N to the breast tissue was computed for varying x-ray spectra and tomosynthesis projection angle. Tomosynthesis projections centered about both the cranio-caudal (CC) and medio-lateral oblique (MLO) views were simulated. For each projection angle, the ratio of the glandular dose for that projection to the glandular dose for the zero degree projection was a Electronic mail: akarell@emory.edu. computed. This ratio was denoted the relative glandular dose (RGD) coefficient, and its variation under different imaging parameters was analyzed. Within mammographic energies, the RGD was found to have a weak dependence on glandular fraction and x-ray spectrum for both views. A substantial dependence on breast size and thickness was found for the MLO view, and to a lesser extent for the CC view. Although RGD values deviate substantially from unity as a function of projection angle, the RGD averaged over all projections in a complete tomosynthesis study varies from 0.91 to 1.01. The RGD results were fit to mathematical functions and the resulting equations are provided. NIH Public Access