Development of 3D patient-based super-resolution digital breast phantoms using machine learning

Multiscale X-ray phase-contrast tomography: From breast CT to micro-CT for virtual histology

Phase-contrast imaging techniques address the issue of poor soft-tissue contrast encountered in traditional X-ray imaging. This can be accomplished with the propagation-based phase-contrast technique by employing a coherent photon beam, which is available at synchrotron facilities, as well as long sample-to-detector distances. This study demonstrates the optimization of propagation-based phase-contrast computed tomography (CT) techniques for multiscale X-ray imaging of the breast at the Elettra synchrotron facility (Trieste, Italy). Two whole breast mastectomy samples were acquired with propagation-based breast-CT using a monochromatic synchrotron beam at a pixel size of 60 µm. Paraffin-embedded blocks sampled from the same tissues were scanned with propagation-based micro-CT imaging using a polychromatic synchrotron beam at a pixel size of 4 µm. Images of both methodologies and of the same sample were spatially registered. The resulting images showed the transition from whole breast imaging with propagation-based breast-CT methodology to virtual histology with propagation-based micro-CT imaging of the same sample. Additionally, conventional histological images were matched to virtual histology images. Phase-contrast images offer a high resolution with low noise, which allows for a highly precise match between virtual and conventional histology. Furthermore, those techniques allow a clear discernment of breast structures, lesions, and microcalcifications, being a promising clinically-compatible tool for breast imaging in a multiscale approach, to either assist in the detection of cancer in full volume breast samples or to complement structure identification in paraffin-embedded breast tissue samples.

Towards using a multi-material, pellet-fed additive manufacturing platform to fabricate novel imaging phantoms

The design freedom afforded by additive manufacturing (AM) is now being leveraged across multiple applications, including many in the fields of imaging for personalised medicine. This study utilises a pellet-fed, multi-material AM machine as a route to fabricating new imaging phantoms, used for developing and refining algorithms for the detection of subtle soft tissue anomalies. Traditionally comprising homogeneous materials, higher-resolution scanning now allows for heterogeneous, multi-material phantoms. Polylactic acid (PLA), a thermoplastic urethane (TPU) and a thermoplastic elastomer (TPE) were investigated as potential materials. Manufacturing accuracy and precision were assessed relative to the digital design file, whilst the potential to achieve structural heterogeneity was evaluated by quantifying infill density via micro-computed tomography. Hounsfield units (HU) were also captured via a clinical scanner. The PLA builds were consistently too small, by 0.2 - 0.3%. Conversely, TPE parts were consistently larger than the digital file, though by only 0.1%. The TPU components had negligible differences relative to the specified sizes. The accuracy and precision of material infill were inferior, with PLA exhibiting greater and lower densities relative to the digital file, across the 3 builds. Both TPU and TPE produced infills that were too dense. The PLA material produced repeatable HU values, with poorer precision across TPU and TPE. All HU values tended towards, and some exceeded, the reference value for water (0 HU) with increasing infill density. These data have demonstrated that pellet-fed AM can produce accurate and precise structures, with the potential to include multiple materials providing an opportunity for more realistic and advanced phantom designs. In doing so, this will enable clinical scientists to develop more sensitive applications aimed at detecting ever more subtle variations in tissue, confident that their calibration models reflect their intended designs.

Patient-derived heterogeneous breast phantoms for advanced dosimetry in mammography and tomosynthesis

Background

Understanding the magnitude and variability of the radiation dose absorbed by the breast fibroglandular tissue during mammography and digital breast tomosynthesis (DBT) is of paramount importance to assess risks versus benefits. Although homogeneous breast models have been proposed and used for decades for this purpose, they do not accurately reflect the actual heterogeneous distribution of the fibroglandular tissue in the breast, leading to biases in the estimation of dose from these modalities.

Purpose

To develop and validate a method to generate patient‐derived, heterogeneous digital breast phantoms for breast dosimetry in mammography and DBT.

Methods

The proposed phantoms were developed starting from patient‐based models of compressed breasts, generated for multiple thicknesses and representing the two standard views acquired in mammography and DBT, that is, cranio‐caudal (CC) and medio‐lateral‐oblique (MLO). Internally, the breast phantoms were defined as consisting of an adipose/fibroglandular tissue mixture, with a nonspatially uniform relative concentration. The parenchyma distributions were obtained from a previously described model based on patient breast computed tomography data that underwent simulated compression. Following these distributions, phantoms with any glandular fraction (1%–100%) and breast thickness (12–125 mm) can be generated, for both views. The phantoms were validated, in terms of their accuracy for average normalized glandular dose (D_gN) estimation across samples of patient breasts, using 88 patient‐specific phantoms involving actual patient distribution of the fibroglandular tissue in the breast, and compared to that obtained using a homogeneous model similar to those currently used for breast dosimetry.

Results

The average D_gN estimated for the proposed phantoms was concordant with that absorbed by the patient‐specific phantoms to within 5% (CC) and 4% (MLO). These D_gN estimates were over 30% lower than those estimated with the homogeneous models, which overestimated the average D_gN by 43% (CC), and 32% (MLO) compared to the patient‐specific phantoms.

Conclusions

The developed phantoms can be used for dosimetry simulations to improve the accuracy of dose estimates in mammography and DBT.

Optimization of a customized simultaneous algebraic reconstruction technique algorithm for phase-contrast breast computed tomography

Objective. To introduce the optimization of a customized GPU-based simultaneous algebraic reconstruction technique (cSART) in the field of phase-contrast breast computed tomography (bCT). The presented algorithm features a 3D bilateral regularization filter that can be tuned to yield optimal performance for clinical image visualization and tissues segmentation. Approach. Acquisitions of a dedicated test object and a breast specimen were performed at Elettra, the Italian synchrotron radiation (SR) facility (Trieste, Italy) using a large area CdTe single-photon counting detector. Tomographic images were obtained at 5 mGy of mean glandular dose, with a 32 keV monochromatic x-ray beam in the free-space propagation mode. Three independent algorithms parameters were optimized by using contrast-to-noise ratio (CNR), spatial resolution, and noise texture metrics. The results obtained with the cSART algorithm were compared with conventional SART and filtered back projection (FBP) reconstructions. Image segmentation was performed both with gray scale-based and supervised machine-learning approaches. Main results. Compared to conventional FBP reconstructions, results indicate that the proposed algorithm can yield images with a higher CNR (by 35% or more), retaining a high spatial resolution while preserving their textural properties. Alternatively, at the cost of an increased image ‘patchiness’, the cSART can be tuned to achieve a high-quality tissue segmentation, suggesting the possibility of performing an accurate glandularity estimation potentially of use in the realization of realistic 3D breast models starting from low radiation dose images. Significance. The study indicates that dedicated iterative reconstruction techniques could provide significant advantages in phase-contrast bCT imaging. The proposed algorithm offers great flexibility in terms of image reconstruction optimization, either toward diagnostic evaluation or image segmentation.

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.

Towards 4D dedicated breast CT perfusion imaging of cancer: development and validation of computer simulated images

Dedicated breast CT is a fully tomographic breast imaging modality with potential for various applications throughout breast cancer care. If implemented to perform dynamic contrast-enhanced (CE) imaging (4D breast CT), it could be useful to obtain functional information at high combined spatio-temporal resolution. Before developing a 4D dedicated breast CT system, a computer simulation method for breast CT perfusion imaging is proposed. The simulation uses previously developed patient-based 4D digital breast phantoms, and generates realistic images with the selected acquisition parameters, allowing to investigate the effect of different acquisition settings on image quality. The simulation pipeline includes all steps of the image generation process, from ray tracing and scatter map generation, to the addition of realistic resolution losses and noise models. The pipeline was validated against experimental measurements performed on physical phantoms with a dedicated breast CT system, in terms of average error compared to ground truth projections (6.0%  ±  1.65%), Hounsfield unit (HU) values in a homogeneous phantom (acquired: -149 HU  ±  2 HU; simulated:  -140 HU  ±  2 HU), signal-to-noise ratio (SNR) (average error 6.7%  ±  4.2%), noise power spectra (NPS) (average error 4.3%  ±  2.5%), modulation transfer function (MTF) (average error 8.4%  ±  7.2%), and attenuation of different adipose/glandular equivalent mixtures (average error 6.9%  ±  4.0%) and glandular plus iodinated contrast medium concentrations equivalent mixtures (average error of 9.1%  ±  9.0%). 4D patient images were then simulated for different 4D digital breast phantoms at different air kerma levels to determine the effect of noise on the extracted tumor perfusion curves. In conclusion, the proposed pipeline could simulate images with a good level of realism, resulting in a tool that can be used for the design, development, and optimization of a 4D dedicated breast CT system.

Development of breast lesions models database

PURPOSE

We present the development and the current state of the MaXIMA Breast Lesions Models Database, which is intended to provide researchers with both segmented and mathematical computer-based breast lesion models with realistic shape.

METHODS

The database contains various 3D images of breast lesions of irregular shapes, collected from routine patient examinations or dedicated scientific experiments. It also contains images of simulated tumour models. In order to extract the 3D shapes of the breast cancers from patient images, an in-house segmentation algorithm was developed for the analysis of 50 tomosynthesis sets from patients diagnosed with malignant and benign lesions. In addition, computed tomography (CT) scans of three breast mastectomy cases were added, as well as five whole-body CT scans. The segmentation algorithm includes a series of image processing operations and region-growing techniques with minimal interaction from the user, with the purpose of finding and segmenting the areas of the lesion. Mathematically modelled computational breast lesions, also stored in the database, are based on the 3D random walk approach.

RESULTS

The MaXIMA Imaging Database currently contains 50 breast cancer models obtained by segmentation of 3D patient breast tomosynthesis images; 8 models obtained by segmentation of whole body and breast cadavers CT images; and 80 models based on a mathematical algorithm. Each record in the database is supported with relevant information. Two applications of the database are highlighted: inserting the lesions into computationally generated breast phantoms and an approach in generating mammography images with variously shaped breast lesion models from the database for evaluation purposes. Both cases demonstrate the implementation of multiple scenarios and of an unlimited number of cases, which can be used for further software modelling and investigation of breast imaging techniques. The created database interface is web-based, user friendly and is intended to be made freely accessible through internet after the completion of the MaXIMA project.

CONCLUSIONS

The developed database will serve as an imaging data source for researchers, working on breast diagnostic imaging and on improving early breast cancer detection techniques, using existing or newly developed imaging modalities.