Synthetic breast phantoms from patient based eigenbreasts

Power-law spectrum-based objective function to train a generative adversarial network with transfer learning for the synthetic breast CT image

Objective.This paper proposes a new objective function to improve the quality of synthesized breast CT images generated by the GAN and compares the GAN performances on transfer learning datasets from different image domains.Approach.The proposed objective function, named beta loss function, is based on the fact that x-ray-based breast images follow the power-law spectrum. Accordingly, the exponent of the power-law spectrum (beta value) for breast CT images is approximately two. The beta loss function is defined in terms of L1 distance between the beta value of synthetic images and validation samples. To compare the GAN performances for transfer learning datasets from different image domains, ImageNet and anatomical noise images are used in the transfer learning dataset. We employ styleGAN2 as the backbone network and add the proposed beta loss function. The patient-derived breast CT dataset is used as the training and validation dataset; 7355 and 212 images are used for network training and validation, respectively. We use the beta value evaluation and Fréchet inception distance (FID) score for quantitative evaluation.Main results.For qualitative assessment, we attempt to replicate the images from the validation dataset using the trained GAN. Our results show that the proposed beta loss function achieves a more similar beta value to real images and a lower FID score. Moreover, we observe that the GAN pretrained with anatomical noise images achieves better equality than ImageNet for beta value evaluation and FID score. Finally, the beta loss function with anatomical noise as the transfer learning dataset achieves the lowest FID score.Significance.Overall, the GAN using the proposed beta loss function with anatomical noise images as the transfer learning dataset provides the lowest FID score among all tested cases. Hence, this work has implications for developing GAN-based breast image synthesis methods for medical imaging applications.

Observer-study-based approaches to quantitatively evaluate the realism of synthetic medical images

Objective.Synthetic images generated by simulation studies have a well-recognized role in developing and evaluating imaging systems and methods. However, for clinically relevant development and evaluation, the synthetic images must be clinically realistic and, ideally, have the same distribution as that of clinical images. Thus, mechanisms that can quantitatively evaluate this clinical realism and, ideally, the similarity in distributions of the real and synthetic images, are much needed.Approach.We investigated two observer-study-based approaches to quantitatively evaluate the clinical realism of synthetic images. In the first approach, we presented a theoretical formalism for the use of an ideal-observer study to quantitatively evaluate the similarity in distributions between the real and synthetic images. This theoretical formalism provides a direct relationship between the area under the receiver operating characteristic curve, AUC, for an ideal observer and the distributions of real and synthetic images. The second approach is based on the use of expert-human-observer studies to quantitatively evaluate the realism of synthetic images. In this approach, we developed a web-based software to conduct two-alternative forced-choice (2-AFC) experiments with expert human observers. The usability of this software was evaluated by conducting a system usability scale (SUS) survey with seven expert human readers and five observer-study designers. Further, we demonstrated the application of this software to evaluate a stochastic and physics-based image-synthesis technique for oncologic positron emission tomography (PET). In this evaluation, the 2-AFC study with our software was performed by six expert human readers, who were highly experienced in reading PET scans, with years of expertise ranging from 7 to 40 years (median: 12 years, average: 20.4 years).Main results.In the ideal-observer-study-based approach, we theoretically demonstrated that the AUC for an ideal observer can be expressed, to an excellent approximation, by the Bhattacharyya distance between the distributions of the real and synthetic images. This relationship shows that a decrease in the ideal-observer AUC indicates a decrease in the distance between the two image distributions. Moreover, a lower bound of ideal-observer AUC = 0.5 implies that the distributions of synthetic and real images exactly match. For the expert-human-observer-study-based approach, our software for performing the 2-AFC experiments is available athttps://apps.mir.wustl.edu/twoafc. Results from the SUS survey demonstrate that the web application is very user friendly and accessible. As a secondary finding, evaluation of a stochastic and physics-based PET image-synthesis technique using our software showed that expert human readers had limited ability to distinguish the real images from the synthetic images.Significance.This work addresses the important need for mechanisms to quantitatively evaluate the clinical realism of synthetic images. The mathematical treatment in this paper shows that quantifying the similarity in the distribution of real and synthetic images is theoretically possible by using an ideal-observer-study-based approach. Our developed software provides a platform for designing and performing 2-AFC experiments with human observers in a highly accessible, efficient, and secure manner. Additionally, our results on the evaluation of the stochastic and physics-based image-synthesis technique motivate the application of this technique to develop and evaluate a wide array of PET imaging methods.

Dataset of patient-derived digital breast phantoms for in silico studies in breast computed tomography, digital breast tomosynthesis, and digital mammography

PURPOSE

To present a dataset of computational digital breast phantoms derived from high-resolution three-dimensional (3D) clinical breast images for the use in virtual clinical trials in two-dimensional (2D) and 3D x-ray breast imaging.

ACQUISITION AND VALIDATION METHODS

Uncompressed computational breast phantoms for investigations in dedicated breast CT (BCT) were derived from 150 clinical 3D breast images acquired via a BCT scanner at UC Davis (California, USA). Each image voxel was classified in one out of the four main materials presented in the field of view: fibroglandular tissue, adipose tissue, skin tissue, and air. For the image classification, a semi-automatic software was developed. The semi-automatic classification was compared via manual glandular classification performed by two researchers. A total of 60 compressed computational phantoms for virtual clinical trials in digital mammography (DM) and digital breast tomosynthesis (DBT) were obtained from the corresponding uncompressed phantoms via a software algorithm simulating the compression and the elastic deformation of the breast, using the tissue's elastic coefficient. This process was evaluated in terms of glandular fraction modification introduced by the compression procedure. The generated cohort of 150 uncompressed computational breast phantoms presented a mean value of the glandular fraction by mass of 12.3%; the average diameter of the breast evaluated at the center of mass was 105 mm. Despite the slight differences between the two manual segmentations, the resulting glandular tissue segmentation did not consistently differ from that obtained via the semi-automatic classification. The difference between the glandular fraction by mass before and after the compression was 2.1% on average. The 60 compressed phantoms presented an average glandular fraction by mass of 12.1% and an average compressed thickness of 61 mm.

DATA FORMAT AND ACCESS

The generated digital breast phantoms are stored in DICOM files. Image voxels can present one out of four values representing the different classified materials: 0 for the air, 1 for the adipose tissue, 2 for the glandular tissue, and 3 for the skin tissue. The generated computational phantoms datasets were stored in the Zenodo public repository for research purposes (http://doi.org/10.5281/zenodo.4529852, http://doi.org/10.5281/zenodo.4515360).

POTENTIAL APPLICATIONS

The dataset developed within the INFN AGATA project will be used for developing a platform for virtual clinical trials in x-ray breast imaging and dosimetry. In addition, they will represent a valid support for introducing new breast models for dose estimates in 2D and 3D x-ray breast imaging and as models for manufacturing anthropomorphic physical phantoms.

Three-layer heterogeneous mammographic phantoms for Monte Carlo simulation of normalized glandular dose coefficients in mammography

Normalized glandular dose (DgN) coefficients obtained using homogeneous breast phantoms are commonly used in breast dosimetry for mammography. However, glandular tissue is heterogeneously distributed in the breast. This study aimed to construct three-layer heterogeneous mammographic phantoms (THEPs) to examine the effect of glandular distribution on DgN coefficient. Each layer of THEPs was set to 25%, 50%, or 75% glandular fraction to emulate heterogeneous glandular distribution. Monte Carlo simulation was performed to attain mean glandular dose (MGD) and air kerma at 22-36 kVp and W/Al, W/Rh, and W/Ag target-filter combinations. The heterogeneous DgN coefficient was calculated as functions of the mean glandular fraction (MGF), breast thickness, tube voltage, and half-value layer. At 50% MGF, the heterogeneous DgN coefficients for W/Al, W/Rh, and W/Ag differed by 40.3%, 36.7%, and 31.2%. At 9-cm breast thickness, the DgN values of superior and inferior glandular distributions were 25.4% higher and 29.2% lower than those of uniform distribution. The proposed THEPs can be integrated with conventional breast dosimetry to consider the heterogeneous glandular distribution in clinical practice.

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.