Assessment of task-based performance from five clinical DBT systems using an anthropomorphic breast phantom.

PURPOSE: Digital breast tomosynthesis (DBT) is a limited-angle tomographic breast imaging modality that can be used for breast cancer screening in conjunction with full-field digital mammography (FFDM) or synthetic mammography (SM). Currently, there are five commercial DBT systems that have been approved by the U.S. FDA for breast cancer screening, all varying greatly in design and imaging protocol. Because the systems are different in technical specifications, there is a need for a quantitative approach for assessing them. In this study, the DBT systems are assessed using a novel methodology with an inkjet-printed anthropomorphic phantom and four alternative forced choice (4AFC) study scheme. METHOD: A breast phantom was fabricated using inkjet printing and parchment paper. The phantom contained 5-mm spiculated masses fabricated with potassium iodide (KI)-doped ink and microcalcifications (MCs) made with calcium hydroxyapatite. Images of the phantom were acquired on all five systems with DBT, FFDM, and SM modalities where available using beam settings under automatic exposure control. A 4AFC study was conducted to assess reader performance with each signal under each modality. Statistical analysis was performed on the data to determine proportion correct (PC), standard deviations, and levels of significance. RESULTS: For masses, overall detection was highest with DBT. The difference in PC was statistically significant between DBT and SM for most systems. A relationship was observed between increasing PC and greater gantry span. For MCs, performance was highest with DBT and FFDM compared to SM. The difference between PC of DBT and PC of SM was statistically significant for all manufacturers. CONCLUSIONS: This methodology represents a novel approach for evaluating systems. This study is the first of its kind to use an inkjet-printed anthropomorphic phantom with realistic signals to assess performance of clinical DBT imaging systems.

Evaluation of data augmentation via synthetic images for improved breast mass detection on mammograms using deep learning.

We evaluated whether using synthetic mammograms for training data augmentation may reduce the effects of overfitting and increase the performance of a deep learning algorithm for breast mass detection. Synthetic mammograms were generated using in silico procedural analytic breast and breast mass modeling algorithms followed by simulated x-ray projections of the breast models into mammographic images. In silico breast phantoms containing masses were modeled across the four BI-RADS breast density categories, and the masses were modeled with different sizes, shapes, and margins. A Monte Carlo-based x-ray transport simulation code, MC-GPU, was used to project the three-dimensional phantoms into realistic synthetic mammograms. 2000 mammograms with 2522 masses were generated to augment a real data set during training. From the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) data set, we used 1111 mammograms (1198 masses) for training, 120 mammograms (120 masses) for validation, and 361 mammograms (378 masses) for testing. We used faster R-CNN for our deep learning network with pretraining from ImageNet using the Resnet-101 architecture. We compared the detection performance when the network was trained using different percentages of the real CBIS-DDSM training set (100%, 50%, and 25%), and when these subsets of the training set were augmented with 250, 500, 1000, and 2000 synthetic mammograms. Free-response receiver operating characteristic (FROC) analysis was performed to compare performance with and without the synthetic mammograms. We generally observed an improved test FROC curve when training with the synthetic images compared to training without them, and the amount of improvement depended on the number of real and synthetic images used in training. Our study shows that enlarging the training data with synthetic samples can increase the performance of deep learning systems.

Technical Note: In silico imaging tools from the VICTRE clinical trial.

PURPOSE: In silico imaging clinical trials are emerging alternative sources of evidence for regulatory evaluation and are typically cheaper and faster than human trials. In this Note, we describe the set of in silico imaging software tools used in the VICTRE (Virtual Clinical Trial for Regulatory Evaluation) which replicated a traditional trial using a computational pipeline. MATERIALS AND METHODS: We describe a complete imaging clinical trial software package for comparing two breast imaging modalities (digital mammography and digital breast tomosynthesis). First, digital breast models were developed based on procedural generation techniques for normal anatomy. Second, lesions were inserted in a subset of breast models. The breasts were imaged using GPU-accelerated Monte Carlo transport methods and read using image interpretation models for the presence of lesions. All in silico components were assembled into a computational pipeline. The VICTRE images were made available in DICOM format for ease of use and visualization. RESULTS: We describe an open-source collection of in silico tools for running imaging clinical trials. All tools and source codes have been made freely available. CONCLUSION: The open-source tools distributed as part of the VICTRE project facilitate the design and execution of other in silico imaging clinical trials. The entire pipeline can be run as a complete imaging chain, modified to match needs of other trial designs, or used as independent components to build additional pipelines.

A four-alternative forced choice (4AFC) methodology for evaluating microcalcification detection in clinical full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) systems using an inkjet-printed anthropomorphic phantom.

PURPOSE: The advent of three-dimensional breast imaging systems such as digital breast tomosynthesis (DBT) has great promise for improving the detection and diagnosis of breast cancer. With these new technologies comes an essential need for testing methods to assess the resultant image quality. Although randomized clinical trials are the gold standard for assessing image quality, phantom-based studies can provide a simpler and less burdensome approach. In this work, a complete framework is presented for task-based evaluation of microcalcification (MCs) detection performance for DBT imaging systems. METHODS: The framework consists of three parts. The first part is a realistic anthropomorphic physical breast phantom created through inkjet printing, with parchment paper and iodine-doped ink. The second is a method for inserting realistic MCs fabricated from calcium hydroxyapatite. The reproducibility and stability of the phantom materials were investigated through multiple samples of parchment and ink over 6 months. The final part is an analysis using a four-alternative forced choice (4AFC) reader study. To demonstrate the framework, a task-based 4AFC study was conducted using a clinical system to compare performance from DBT, synthetic mammography (SM), and full-field digital mammography (FFDM). Nine human observers read images containing MC clusters imaged with all three modalities and tried to correctly locate the MCs. The proportion correct (PC) was measured as the number of correctly detected clusters out of all trials. RESULTS: Overall, readers scored the highest with FFDM, (PC = 0.95 ± 0.03) then DBT (0.85 ± 0.04), and finally SM (0.44 ± 0.06). For the parchment and ink samples, the linear attenuation properties were very stable over 6 months. In addition, little difference was found between the various parchment and ink samples, indicating good reproducibility. CONCLUSIONS: This framework presents a promising methodology for evaluating diagnostic task performance of clinical breast DBT systems.

Advances in Computational Human Phantoms and Their Applications in Biomedical Engineering - A Topical Review.

Over the past decades, significant improvements have been made in the field of computational human phantoms (CHPs) and their applications in biomedical engineering. Their sophistication has dramatically increased. The very first CHPs were composed of simple geometric volumes, e.g., cylinders and spheres, while current CHPs have a high resolution, cover a substantial range of the patient population, have high anatomical accuracy, are poseable, morphable, and are augmented with various details to perform functionalized computations. Advances in imaging techniques and semi-automated segmentation tools allow fast and personalized development of CHPs. These advances open the door to quickly develop personalized CHPs, inherently including the disease of the patient. Because many of these CHPs are increasingly providing data for regulatory submissions of various medical devices, the validity, anatomical accuracy, and availability to cover the entire patient population is of utmost importance. The article is organized into two main sections: the first section reviews the different modeling techniques used to create CHPs, whereas the second section discusses various applications of CHPs in biomedical engineering. Each topic gives an overview, a brief history, recent developments, and an outlook into the future.

Evaluation of Digital Breast Tomosynthesis as Replacement of Full-Field Digital Mammography Using an In Silico Imaging Trial.

Importance: Expensive and lengthy clinical trials can delay regulatory evaluation of innovative technologies, affecting patient access to high-quality medical products. Simulation is increasingly being used in product development but rarely in regulatory applications. Objectives: To conduct a computer-simulated imaging trial evaluating digital breast tomosynthesis (DBT) as a replacement for digital mammography (DM) and to compare the results with a comparative clinical trial. Design, Setting, and Participants: The simulated Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) trial was designed to replicate a clinical trial that used human patients and radiologists. Images obtained with in silico versions of DM and DBT systems via fast Monte Carlo x-ray transport were interpreted by a computational reader detecting the presence of lesions. A total of 2986 synthetic image-based virtual patients with breast sizes and radiographic densities representative of a screening population and compressed thicknesses from 3.5 to 6 cm were generated using an analytic approach in which anatomical structures are randomly created within a predefined breast volume and compressed in the craniocaudal orientation. A positive cohort contained a digitally inserted microcalcification cluster or spiculated mass. Main Outcomes and Measures: The trial end point was the difference in area under the receiver operating characteristic curve between modalities for lesion detection. The trial was sized for an SE of 0.01 in the change in area under the curve (AUC), half the uncertainty in the comparative clinical trial. Results: In this trial, computational readers analyzed 31 055 DM and 27 960 DBT cases from 2986 virtual patients with the following Breast Imaging Reporting and Data System densities: 286 (9.6%) extremely dense, 1200 (40.2%) heterogeneously dense, 1200 (40.2%) scattered fibroglandular densities, and 300 (10.0%) almost entirely fat. The mean (SE) change in AUC was 0.0587 (0.0062) (P < .001) in favor of DBT. The change in AUC was larger for masses (mean [SE], 0.0903 [0.008]) than for calcifications (mean [SE], 0.0268 [0.004]), which was consistent with the findings of the comparative trial (mean [SE], 0.065 [0.017] for masses and -0.047 [0.032] for calcifications). Conclusions and Relevance: The results of the simulated VICTRE trial are consistent with the performance seen in the comparative trial. While further research is needed to assess the generalizability of these findings, in silico imaging trials represent a viable source of regulatory evidence for imaging devices.

A novel physical anthropomorphic breast phantom for 2D and 3D x-ray imaging.

PURPOSE: Physical phantoms are central to the evaluation of 2D and 3D breast-imaging systems. Currently, available physical phantoms have limitations including unrealistic uniform background structure, large expense, or excessive fabrication time. The purpose of this work is to outline a method for rapidly creating realistic, inexpensive physical anthropomorphic phantoms for use in full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT). METHODS: The phantom was first modeled using analytical expressions and then discretized into voxels of a specified size. The interior of the breast was divided into glandular and adipose tissue classes using Voronoi segmentation, and additional structures like blood vessels, chest muscle, and ligaments were added. The physical phantom was then fabricated from the virtual model in a slice by slice fashion through inkjet printing, using parchment paper and a radiopaque ink containing 33% (I33% ) or 25% (I25% ) iohexol by volume. Three types of parchment paper (P1, P2, and P3) were examined. The phantom materials were characterized in terms of their effective linear attenuation coefficients (µeff ) using full-field digital mammography (FFDM) and their energy-dependent linear attenuation coefficients (µ(E)) using a spectroscopic energy discriminating detector system. The printing method was further validated on the basis of accuracy, print consistency, and the reproducibility of ink batches. RESULTS: The µeff of two types of parchment paper were close to that of adipose tissue, with µeff = 0.61 ± 0.05 cm-1 for P1, 0.61 ± 0.04 cm-1 for P2, and 0.57 ± 0.03 cm-1 for adipose tissue. The addition of the iodinated ink increased the effective attenuation to that of glandular tissue, with µeff = 0.89 ± 0.06 cm-1 for P1 + I25% and 0.94 ± 0.06 cm-1 for P1 + I33% compared to 0.90 ± 0.03 cm-1 for glandular tissue. Spectroscopic measurements showed a good match between the parchment paper and reference values for adipose and glandular tissues across photon energies. Good accuracy was found between the model and the printed phantom by comparing a FFDM of the virtual model simulated through Monte Carlo with a real FFDM of the fully printed phantom. High consistency was found over multiple prints, with 3% variability in mean ink signal across various samples. Reproducibility of ink consistency was very high with <1% variation signal from multiple batches of ink. Imaging of the phantom using FFDM and DBT systems showed promising utility for 2D and 3D imaging. CONCLUSIONS: A novel, realistic breast phantom can be created using an analytically defined breast model and readily available materials. The work provides a method to fabricate any virtual phantom in a manner that is accurate, inexpensive, easily accessible, and can be made with different materials or breast models.

Compressive sensing in medical imaging.

The promise of compressive sensing, exploitation of compressibility to achieve high quality image reconstructions with less data, has attracted a great deal of attention in the medical imaging community. At the Compressed Sensing Incubator meeting held in April 2014 at OSA Headquarters in Washington, DC, presentations were given summarizing some of the research efforts ongoing in compressive sensing for x-ray computed tomography and magnetic resonance imaging systems. This article provides an expanded version of these presentations. Sparsity-exploiting reconstruction algorithms that have gained popularity in the medical imaging community are studied, and examples of clinical applications that could benefit from compressive sensing ideas are provided. The current and potential future impact of compressive sensing on the medical imaging field is discussed.

Correcting partial volume effects in biexponential T2 estimation of small lesions.

PURPOSE: T2 mapping provides a quantitative approach for focal liver lesion characterization. For small lesions, a biexponential model should be used to account for partial volume effects (PVE). However, conventional biexponential fitting suffers from large uncertainty of the fitted parameters when noise is present. The purpose of this work is to develop a more robust method to correct for PVE affecting small lesions. METHODS: We developed a region of interest-based joint biexponential fitting (JBF) algorithm to estimate the T2 of lesions affected by PVE. JBF takes advantage of the lesion fraction variation among voxels within a region of interest. JBF is compared to conventional approaches using Cramér-Rao lower bound analysis, numerical simulations, phantom, and in vivo data. RESULTS: JBF provides more accurate and precise T2 estimates in the presence of PVE. Furthermore, JBF is less sensitive to region of interest drawing. Phantom and in vivo results show that JBF can be combined with a reconstruction method for highly undersampled data, enabling the characterization of small abdominal lesions from data acquired in a single breath hold. CONCLUSION: The JBF algorithm provides more accurate and stable T2 estimates for small structures than conventional techniques when PVE is present. It should be particularly useful for the characterization of small abdominal lesions.

T2 mapping from highly undersampled data by reconstruction of principal component coefficient maps using compressed sensing.

Recently, there has been an increased interest in quantitative MR parameters to improve diagnosis and treatment. Parameter mapping requires multiple images acquired with different timings usually resulting in long acquisition times. While acquisition time can be reduced by acquiring undersampled data, obtaining accurate estimates of parameters from undersampled data is a challenging problem, in particular for structures with high spatial frequency content. In this work, principal component analysis is combined with a model-based algorithm to reconstruct maps of selected principal component coefficients from highly undersampled radial MRI data. This novel approach linearizes the cost function of the optimization problem yielding a more accurate and reliable estimation of MR parameter maps. The proposed algorithm--reconstruction of principal component coefficient maps using compressed sensing--is demonstrated in phantoms and in vivo and compared with two other algorithms previously developed for undersampled data.

The ideal observer objective assessment metric for magnetic resonance imaging: application to signal detection tasks.

The ideal Bayesian observer is a mathematical construct which makes optimal use of all statistical information about the object and imaging system to perform a task. Its performance serves as an upper bound on any observer's task performance. In this paper a methodology based on the ideal observer for assessing magnetic resonance (MR) acquisition sequences and reconstruction algorithms is developed. The ideal observer in the context of MR imaging is defined and expressions for ideal observer performance metrics are derived. Comparisons are made between the raw-data ideal observer and image-based ideal observer to elucidate the effect of image reconstruction on task performance. Lesion detection tasks are studied in detail via analytical expressions and simulations. The effect of imaging sequence parameters on lesion detectability is shown and the advantages of this methodology over image quality metrics currently in use in MR imaging is demonstrated.