Simulation of 3D objects into breast tomosynthesis images

Verification of the accuracy of a hybrid breast imaging simulation framework for virtual clinical trial applications

Purpose: The impact of system parameters on signal detectability can be studied with simulation platforms. We describe the steps taken to verify and confirm the accuracy of a local platform developed for the use in virtual clinical trials. Approach: The platform simulates specific targets into existing two-dimensional full-field digital mammography and digital breast tomosynthesis images acquired on a Siemens Inspiration system. There are three steps: (1) creation of voxel models or analytical objects; (2) generation of a realistic object template with accurate resolution, scatter, and noise properties; and (3) insertion and reconstruction. Four objects were simulated: a 0.5-mm aluminium (Al) sphere and a 0.2-mm-thick Al sheet in a PMMA stack, a 0.8-mm steel edge and a three-dimensional mass model in a structured background phantom. Simulated results were compared to acquired data. Results: Peak contrast and signal difference-to-noise ratio (SDNR) were in close agreement ( < 5 % error) for both sphere and sheet. The similarity of pixel value profiles for sphere and sheet in the x y direction and the artifact spread function for real and simulated spheres confirmed accurate geometric modeling. Absolute and relative average deviation between modulation transfer function measured from a real and simulated edges showed accurate sharpness modelling for spatial frequencies up to the Nyquist frequency. Real and simulated objects could not be differentiated visually. Conclusions: The results indicate that this simulation framework is a strong candidate for use in virtual clinical studies.

Lesion detectability in 2D-mammography and digital breast tomosynthesis using different targets and observers

This work investigates the detection performance of specialist and non-specialist observers for different targets in 2D-mammography and digital breast tomosynthesis (DBT) using the OPTIMAM virtual clinical trials (VCT) Toolbox and a 4-alternative forced choice (4AFC) assessment paradigm. Using 2D-mammography and DBT images of virtual breast phantoms, we compare the detection limits of simple uniform spherical targets and irregular solid masses. Target diameters of 4 mm and 6 mm have been chosen to represent target sizes close to the minimum detectable size found in breast screening, across a range of controlled contrast levels. The images were viewed by a set of specialist observers (five medical physicists and six experienced clinical readers) and five non-specialists. Combined results from both observer groups indicate that DBT has a significantly lower detectable threshold contrast than 2D-mammography for small masses (4 mm: 2.1% [DBT] versus 6.9% [2D]; 6 mm: 0.7% [DBT] versus 3.9% [2D]) and spheres (4 mm: 2.9% [DBT] versus 5.3% [2D]; 6 mm: 0.3% [DBT] versus 2.2% [2D]) (p  <  0.0001). Both observer groups found spheres significantly easier to detect than irregular solid masses for both sizes and modalities (p  <  0.0001) (except 4 mm DBT). The detection performances of specialist and non-specialist observers were generally found to be comparable, where each group marginally outperformed the other in particular detection tasks. Within the specialist group, the clinical readers performed better than the medical physicists with irregular masses (p  <  0.0001). The results indicate that using spherical targets in such studies may produce over-optimistic detection thresholds compared to more complex masses, and that the superiority of DBT for detecting masses over 2D-mammography has been quantified. The results also suggest specialist observers may be supplemented by non-specialist observers (with training) in some types of 4AFC studies.

Design and validation of realistic breast models for use in multiple alternative forced choice virtual clinical trials

A novel method has been developed for generating quasi-realistic voxel phantoms which simulate the compressed breast in mammography and digital breast tomosynthesis (DBT). The models are suitable for use in virtual clinical trials requiring realistic anatomy which use the multiple alternative forced choice (AFC) paradigm and patches from the complete breast image. The breast models are produced by extracting features of breast tissue components from DBT clinical images including skin, adipose and fibro-glandular tissue, blood vessels and Cooper's ligaments. A range of different breast models can then be generated by combining these components. Visual realism was validated using a receiver operating characteristic (ROC) study of patches from simulated images calculated using the breast models and from real patient images. Quantitative analysis was undertaken using fractal dimension and power spectrum analysis. The average areas under the ROC curves for 2D and DBT images were 0.51  ±  0.06 and 0.54  ±  0.09 demonstrating that simulated and real images were statistically indistinguishable by expert breast readers (7 observers); errors represented as one standard error of the mean. The average fractal dimensions (2D, DBT) for real and simulated images were (2.72  ±  0.01, 2.75  ±  0.01) and (2.77  ±  0.03, 2.82  ±  0.04) respectively; errors represented as one standard error of the mean. Excellent agreement was found between power spectrum curves of real and simulated images, with average β values (2D, DBT) of (3.10  ±  0.17, 3.21  ±  0.11) and (3.01  ±  0.32, 3.19  ±  0.07) respectively; errors represented as one standard error of the mean. These results demonstrate that radiological images of these breast models realistically represent the complexity of real breast structures and can be used to simulate patches from mammograms and DBT images that are indistinguishable from patches from the corresponding real breast images. The method can generate about 500 radiological patches (~30 mm  ×  30 mm) per day for AFC experiments on a single workstation. This is the first study to quantitatively validate the realism of simulated radiological breast images using direct blinded comparison with real data via the ROC paradigm with expert breast readers.

Impact of compressed breast thickness and dose on lesion detectability in digital mammography: FROC study with simulated lesions in real mammograms

PURPOSE

The aim of this work was twofold: (1) to examine whether, with standard automatic exposure control (AEC) settings that maintain pixel values in the detector constant, lesion detectability in clinical images decreases as a function of breast thickness and (2) to verify whether a new AEC setup can increase lesion detectability at larger breast thicknesses.

METHODS

Screening patient images, acquired on two identical digital mammography systems, were collected over a period of 2 yr. Mammograms were acquired under standard AEC conditions (part 1) and subsequently with a new AEC setup (part 2), programmed to use the standard AEC settings for compressed breast thicknesses ≤49 mm, while a relative dose increase was applied above this thickness. The images were divided into four thickness groups: T1 ≤ 29 mm, T2 = 30-49 mm, T3 = 50-69 mm, and T4 ≥ 70 mm, with each thickness group containing 130 randomly selected craniocaudal lesion-free images. Two measures of density were obtained for every image: a BI-RADS score and a map of volumetric breast density created with a software application (VolparaDensity, Matakina, NZ). This information was used to select subsets of four images, containing one image from each thickness group, matched to a (global) BI-RADS score and containing a region with the same (local) volpara volumetric density value. One selected lesion (a microcalcification cluster or a mass) was simulated into each of the four images. This process was repeated so that, for a given thickness group, half the images contained a single lesion and half were lesion-free. The lesion templates created and inserted in groups T3 and T4 for the first part of the study were then inserted into the images of thickness groups T3 and T4 acquired with higher dose settings. Finally, all images were visualized using the ViewDEX software and scored by four radiologists performing a free search study. A statistical jackknife-alternative free-response receiver operating characteristic analysis was applied.

RESULTS

For part 1, the alternative free-response receiver operating characteristic curves for the four readers were 0.80, 0.65, 0.55 and 0.56 in going from T1 to T4, indicating a decrease in detectability with increasing breast thickness. P-values and the 95% confidence interval showed no significant difference for the T3-T4 comparison (p = 0.78) while all the other differences were significant (p < 0.05). Separate analysis of microcalcification clusters presented the same results while for mass detection, the only significant difference came when comparing T1 to the other thickness groups. Comparing the scores of part 1 and part 2, results for the T3 group acquired with the new AEC setup and T3 group at standard AEC doses were significantly different (p = 0.0004), indicating improved detection. For this group a subanalysis for microcalcification detection gave the same results while no significant difference was found for mass detection.

CONCLUSIONS

These data using clinical images confirm results found in simple QA tests for many mammography systems that detectability falls as breast thickness increases. Results obtained with the AEC setup for constant detectability above 49 mm showed an increase in lesion detection with compressed breast thickness, bringing detectability of lesions to the same level.

VOLUMETRIC LOCALISATION OF DENSE BREAST TISSUE USING BREAST TOMOSYNTHESIS DATA

This study attempted to use combined data from reconstructed digital breast tomosynthesis (DBT) volumes and density estimation of projection images to localise dense tissue inside the breast, using the assumption that the breast can be treated as consisting of only two types of tissue: fibroglandular (dense) and adipose (fatty). To be able to verify results, software breast phantoms generated using fractal Perlin noise were employed. Projection images were created using the PENELOPE Monte Carlo package. Dense tissue volume was estimated from the central projection image. The density image was used to determine the number of dense voxels at each pixel location, which were then placed using the DBT image as a template. The method proved capable of accurately determining the composition of 75±5 % of voxels.

Development and validation of a modelling framework for simulating 2D-mammography and breast tomosynthesis images

Planar 2D x-ray mammography is generally accepted as the preferred screening technique used for breast cancer detection. Recently, digital breast tomosynthesis (DBT) has been introduced to overcome some of the inherent limitations of conventional planar imaging, and future technological enhancements are expected to result in the introduction of further innovative modalities. However, it is crucial to understand the impact of any new imaging technology or methodology on cancer detection rates and patient recall. Any such assessment conventionally requires large scale clinical trials demanding significant investment in time and resources. The concept of virtual clinical trials and virtual performance assessment may offer a viable alternative to this approach. However, virtual approaches require a collection of specialized modelling tools which can be used to emulate the image acquisition process and simulate images of a quality indistinguishable from their real clinical counterparts. In this paper, we present two image simulation chains constructed using modelling tools that can be used for the evaluation of 2D-mammography and DBT systems. We validate both approaches by comparing simulated images with real images acquired using the system being simulated. A comparison of the contrast-to-noise ratios and image blurring for real and simulated images of test objects shows good agreement ( < 9% error). This suggests that our simulation approach is a promising alternative to conventional physical performance assessment followed by large scale clinical trials.

The simulation of 3D mass models in 2D digital mammography and breast tomosynthesis

PURPOSE

This work proposes a new method of building 3D breast mass models with different morphological shapes and describes the validation of the realism of their appearance after simulation into 2D digital mammograms and breast tomosynthesis images.

METHODS

Twenty-five contrast enhanced MRI breast lesions were collected and each mass was manually segmented in the three orthogonal views: sagittal, coronal, and transversal. The segmented models were combined, resampled to have isotropic voxel sizes, triangularly meshed, and scaled to different sizes. These masses were referred to as nonspiculated masses and were then used as nuclei onto which spicules were grown with an iterative branching algorithm forming a total of 30 spiculated masses. These 55 mass models were projected into 2D projection images to obtain mammograms after image processing and into tomographic sequences of projection images, which were then reconstructed to form 3D tomosynthesis datasets. The realism of the appearance of these mass models was assessed by five radiologists via receiver operating characteristic (ROC) analysis when compared to 54 real masses. All lesions were also given a breast imaging reporting and data system (BIRADS) score. The data sets of 2D mammography and tomosynthesis were read separately. The Kendall's coefficient of concordance was used for the interrater observer agreement assessment for the BIRADS scores per modality. Further paired analysis, using the Wilcoxon signed rank test, of the BIRADS assessment between 2D and tomosynthesis was separately performed for the real masses and for the simulated masses.

RESULTS

The area under the ROC curves, averaged over all observers, was 0.54 (95% confidence interval [0.50, 0.66]) for the 2D study, and 0.67 (95% confidence interval [0.55, 0.79]) for the tomosynthesis study. According to the BIRADS scores, the nonspiculated and the spiculated masses varied in their degrees of malignancy from normal (BIRADS 1) to highly suggestive for malignancy (BIRADS 5) indicating the required variety of shapes and margins of these models. The assessment of the BIRADS scores for all observers indicated good agreement based on Kendall's coefficient for both the 2D and the tomosynthesis evaluations. The paired analysis of the BIRADS scores between 2D and tomosynthesis for each observer revealed consistent behavior for the real and simulated masses.

CONCLUSIONS

A database of 3D mass models, with variety of shapes and margins, was validated for the realism of their appearance for 2D digital mammography and for breast tomosynthesis. This database is suitable for use in future observer performance studies whether in virtual clinical trials or in patient images with simulated lesions.

Quantification of scattered radiation in projection mammography: four practical methods compared

PURPOSE

Four different practical methodologies of quantifying scattered radiation for two different digital mammographic systems are compared. The study considered both grid in and grid out geometries for two different antiscatter grid types, a typical linear grid and a cellular grid design. The aim was to find quick and reproducible methods that could be used in place of the beam stop technique.

METHODS

The scatter to primary ratio (SPR) and the scatter fraction (SF) were used to quantify scattered radiation as a function of poly(methyl methacrylate) (PMMA) thickness, grid position, and beam quality. The four scatter estimation methods applied were (1) the beam stop method, (2) a hybrid method that combined measured detector (scatter-free) modulation transfer function (MTF) data and a Monte Carlo simulation of the scatter point spread function, (3) from the low frequency drop data taken from the system MTF, and (4) from the edge spread function (ESF) measured in the presence of PMMA. Repeatability error was assessed for all methods.

RESULTS

SPR results acquired with the beam stop method ranged from 0.052 to 0.187 for the system with linear grid and from 0.012 to 0.064 for the cellular grid system, as PMMA thickness was increased from 20 to 80 mm. With the grid removed, beam stop SPR was similar for both systems, ranging between 0.268 and 1.124, for corresponding MTF thicknesses. The direct MTF method had a maximum difference of 24% from the beam stop SPR and SF data for all conditions except the cellular grid in geometry, where maximum difference in SPR was 0.044 (164%). The ESF technique gave large differences from the beam stops for both grid geometries but agreement was within 21% for the grid out geometry. Repeatability error with beam stops was between 1% and 5% for the grid out geometries, while for the grid in cases it was 13% and 87% for the linear and cellular grids, respectively. Repeatability error for the direct MTF method applied to both systems and grid geometries ranged between 3% and 12%.

CONCLUSIONS

All three alternative methods to the beam stop technique gave reasonable estimates of SPR without grid, with a maximum difference of 24% (mean difference 8%). For the grid in geometry, the direct MTF method gave a maximum difference of 24% for the linear grid system, while maximum percentage difference was 119% (absolute difference of 0.042) for the system with the cellular grid, where SPR values were low. Except for cases where the SPR is very low, the direct MTF method offers a quick and reproducible alternative to the beam stop technique.

The simulation of 3D microcalcification clusters in 2D digital mammography and breast tomosynthesis

PURPOSE

This work proposes a new method of building 3D models of microcalcification clusters and describes the validation of their realistic appearance when simulated into 2D digital mammograms and into breast tomosynthesis images.

METHODS

A micro-CT unit was used to scan 23 breast biopsy specimens of microcalcification clusters with malignant and benign characteristics and their 3D reconstructed datasets were segmented to obtain 3D models of microcalcification clusters. These models were then adjusted for the x-ray spectrum used and for the system resolution and simulated into 2D projection images to obtain mammograms after image processing and into tomographic sequences of projection images, which were then reconstructed to form 3D tomosynthesis datasets. Six radiologists were asked to distinguish between 40 real and 40 simulated clusters of microcalcifications in two separate studies on 2D mammography and tomosynthesis datasets. Receiver operating characteristic (ROC) analysis was used to test the ability of each observer to distinguish between simulated and real microcalcification clusters. The kappa statistic was applied to assess how often the individual simulated and real microcalcification clusters had received similar scores ("agreement") on their realistic appearance in both modalities. This analysis was performed for all readers and for the real and the simulated group of microcalcification clusters separately. "Poor" agreement would reflect radiologists' confusion between simulated and real clusters, i.e., lesions not systematically evaluated in both modalities as either simulated or real, and would therefore be interpreted as a success of the present models.

RESULTS

The area under the ROC curve, averaged over the observers, was 0.55 (95% confidence interval [0.44, 0.66]) for the 2D study, and 0.46 (95% confidence interval [0.29, 0.64]) for the tomosynthesis study, indicating no statistically significant difference between real and simulated lesions (p > 0.05). Agreement between allocated lesion scores for 2D mammography and those for the tomosynthesis series was poor.

CONCLUSIONS

The realistic appearance of the 3D models of microcalcification clusters, whether malignant or benign clusters, was confirmed for 2D digital mammography images and the breast tomosynthesis datasets; this database of clusters is suitable for use in future observer performance studies related to the detectability of microcalcification clusters. Such studies include comparing 2D digital mammography to breast tomosynthesis and comparing different reconstruction algorithms.