In contrast to conventional analog screen-film mammography new flat detectors have a high dynamic range and a linear characteristic curve. Hence, the radiographic technique can be optimized ...independently of the receptor exposure. It can be exclusively focused on the improvement of the image quality and the reduction of the patient dose. In this paper we measure the image quality by a physical quantity, the signal difference-to-noise ratio (SDNR), and the patient risk by the average glandular dose (AGD). Using these quantities, we compare the following different setups through simulations and phantom studies regarding the detection of microcalcifications and tumors for different breast thicknesses and breast compositions: Monochromatic radiation, three different anode/filter combinations: Molybdenum/molybdenum
(
Mo
∕
Mo
)
, molybdenum/rhodium
(
Mo
∕
Rh
)
, and tungsten/rhodium
(
W
∕
Rh
)
, different filter thicknesses, use of anti-scatter grids, and different tube voltages. For a digital mammography system based on an amorphous selenium detector it turned out that, first, the
W
∕
Rh
combination is the best choice for all detection tasks studied. Second, monochromatic radiation can further reduce the AGD by a factor of up to 2.3, maintaining the image quality in comparison with a real polychromatic spectrum of an x-ray tube. And, third, the use of an anti-scatter grid is only advantageous for breast thicknesses larger than approximately
5
cm
.
A three-dimensional (3D) linear model for digital breast tomosynthesis (DBT) was developed to investigate the effects of different imaging system parameters on the reconstructed image quality. In the ...present work, experimental validation of the model was performed on a prototype DBT system equipped with an amorphous selenium (a-Se) digital mammography detector and filtered backprojection (FBP) reconstruction methods. The detector can be operated in either full resolution with
85
μ
m
pixel size or
2
×
1
pixel
binning mode to reduce acquisition time. Twenty-five projection images were acquired with a nominal angular range of
±
20
°
. The images were reconstructed using a slice thickness of
1
mm
with
0.085
×
0.085
mm
in-plane pixel dimension. The imaging performance was characterized by spatial frequency-dependent parameters including a 3D noise power spectrum (NPS) and in-plane modulation transfer function (MTF). Scatter-free uniform x-ray images were acquired at four different exposure levels for noise analysis. An aluminum (Al) edge phantom with
0.2
mm
thickness was imaged to measure the in-plane presampling MTF. The measured in-plane MTF and 3D NPS were both in good agreement with the model. The dependence of DBT image quality on reconstruction filters was investigated. It was found that the slice thickness (ST) filter, a Hanning window to limit the high-frequency components in the slice thickness direction, reduces noise aliasing and improves 3D DQE. An ACR phantom was imaged to investigate the effects of angular range and detector operational modes on reconstructed image quality. It was found that increasing the angular range improves the MTF at low frequencies, resulting in better detection of large-area, low-contrast mass lesions in the phantom. There is a trade-off between noise and resolution for pixel binning and full resolution modes, and the choice of detector mode will depend on radiation dose and the targeted lesion.
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.
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.
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.
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.
Purpose
To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload.
Methods ...and materials
A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis.
Results
Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (− 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > − 0.05) for any threshold except at the extreme AI score of 9.
Conclusion
It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload.
Key Points
• There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer.
• The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists’ breast cancer detection performance.
• When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.
Digital Breast Tomosynthesis: Technique and Cases is a comprehensive and timely introduction to a significant technological advance in breast cancer imaging. This state-of-the-art guide
explains the ...technique of digital breast tomosynthesis (DBT), describes results from available
clinical studies, offers recommendations for the use of DBT in routine practice, and discusses the latest developments and possible future trends in DBT. The main part of the book contains 45 highly illustrated case reports that allow readers to explore the practical aspects of DBT and deepen their knowledge of this important new modality in breast imaging.
The purpose of this study was to test the hypothesis whether two-view wide-angle digital breast tomosynthesis (DBT) can replace full-field digital mammography (FFDM) for breast cancer detection.
In a ...multireader multicase study, bilateral two-view FFDM and bilateral two-view wide-angle DBT images were independently viewed for breast cancer detection in two reading sessions separated by more than 1 month. From a pool of 764 patients undergoing screening and diagnostic mammography, 330 patient-cases were selected. The endpoints were the mean ROC AUC for the reader per breast (breast level), ROC AUC per patient (subject level), noncancer recall rates, sensitivity, and specificity.
Twenty-nine of 31 readers performed better with DBT than FFDM regardless of breast density. There was a statistically significant improvement in readers' mean diagnostic accuracy with DBT. The subject-level AUC increased from 0.765 (standard error SE, 0.027) for FFDM to 0.835 (SE, 0.027) for DBT (
= 0.002). Breast-level AUC increased from 0.818 (SE, 0.019) for FFDM to 0.861 (SE, 0.019) for DBT (
= 0.011). The noncancer recall rate per patient was reduced by 19% with DBT (
< 0.001). Masses and architectural distortions were detected more with DBT (
< 0.001); calcifications trended lower (
= 0.136). Accuracy for detection of invasive cancers was significantly greater with DBT (
< 0.001).
Reader performance in breast cancer detection is significantly higher with wide-angle two-view DBT independent of FFDM, verifying the robustness of DBT as a sole view. However, results of perception studies in the vision sciences support the inclusion of an overview image.
In this study, screening performance metrics and radiation dose were compared for two image acquisition modes for breast cancer screening with MAMMOMAT Inspiration (Siemens Healthcare GmbH, ...Forchheim, Germany). This mammography system can operate without an anti-scatter grid in place but using software scatter correction instead. This grid-less acquisition mode (PRIME) requires less patient dose due to the increase in primary radiation reaching the detector. This study retrospectively analyses data from the Region of Southern Denmark where the grid-less mode has been installed in November 2013 and replaced grid-based screening.
A total of 72,188 screening cases from the same geographical region in Denmark were included in the study. They were subdivided into two study populations: cases acquired before and after installation of the grid-less acquisition mode. Sensitivity and specificity of breast cancer screening were calculated for the two populations; thus representing the performance of grid-less and grid-based screening. To measure the entrance surface air kerma (ESAK) additional phantom tests were carried out. Polymethylmethacrylate (PMMA) attenuation plates with different thicknesses (20–70 mm in steps of 10 mm) simulated the compressed breast (21 mm–90 mm) and a solid-state dosimeter was used.
Statistical testing of the results showed that screening with grid-less acquisition provides equivalent performance with respect to sensitivity and specificity compared to grid-based screening. The specificity was 98.11% (95% confidence interval (CI) from 97.93% to 98.29%) and 97.96% (95% CI from 97.84% to 98.09%) for screening with grid-less acquisition and grid-based acquisition, respectively. The cancer detection rate as a measure for sensitivity was equal (0.55%) for grid-less screening and grid-based screening. An average glandular dose saving between 13.5% and 36.4% depending on breast thickness in grid-less acquisition was obtained compared to grid-based acquisition.
Statistically significant equivalence was shown with an equivalence margin of 0.12% points for cancer detection rate and with an equivalence margin of 0.40% points for specificity. A marked patient dose savings in grid-less acquisition of up to 36% compared to grid-based acquisition was achieved. It can be concluded that grid-less acquisition with software scatter correction is an alternative to grid-based acquisition in mammography.
The properties of the human visual system (HVS) relevant to the diagnostic process are described after a brief introduction on the general problems and advantages of using soft copy for primary ...radiology interpretations. At various spatial and temporal frequencies the contrast sensitivity defines the spatial resolution of the eye-brain system and the sensitivity to flicker. The adaptation to the displayed radiological scene and the ambient illumination determine the dynamic range for the operation of the HVS. Although image display devices are determined mainly by state-of-the-art technology, analysis of the HVS may suggest technical characteristics for electronic displays that will help to optimize the display to the operation of the HVS. These include display size, spatial resolution, contrast resolution, luminance range, and noise, from which further consequences for the technical components of a monitor follow. It is emphasized that routine monitor quality control must be available in clinical practice. These image quality measures must be simple enough to be applied as part of the daily routine. These test instructions might also serve as elements of technical acceptance and constancy tests.