Library based x-ray scatter correction for dedicated cone beam breast CT

Artificial Intelligence in Breast X-Ray Imaging

This topical review is focused on the clinical breast x-ray imaging applications of the rapidly evolving field of artificial intelligence (AI). The range of AI applications is broad. AI can be used for breast cancer risk estimation that could allow for tailoring the screening interval and the protocol that are woman-specific and for triaging the screening exams. It also can serve as a tool to aid in the detection and diagnosis for improved sensitivity and specificity and as a tool to reduce radiologists' reading time. AI can also serve as a potential second 'reader' during screening interpretation. During the last decade, numerous studies have shown the potential of AI-assisted interpretation of mammography and to a lesser extent digital breast tomosynthesis; however, most of these studies are retrospective in nature. There is a need for prospective clinical studies to evaluate these technologies to better understand their real-world efficacy. Further, there are ethical, medicolegal, and liability concerns that need to be considered prior to the routine use of AI in the breast imaging clinic.

Deep learning for x-ray scatter correction in dedicated breast CT

BACKGROUND

Accurate correction of x-ray scatter in dedicated breast computed tomography (bCT) imaging may result in improved visual interpretation and is crucial to achieve quantitative accuracy during image reconstruction and analysis.

PURPOSE

To develop a deep learning (DL) model to correct for x-ray scatter in bCT projection images.

METHODS

A total of 115 patient scans acquired with a bCT clinical system were segmented into the major breast tissue types (skin, adipose, and fibroglandular tissue). The resulting breast phantoms were divided into training (n = 110) and internal validation cohort (n = 5). Training phantoms were augmented by a factor of four by random translation of the breast in the image field of view. Using a previously validated Monte Carlo (MC) simulation algorithm, 12 primary and scatter bCT projection images with a 30-degree step were generated from each phantom. For each projection, the thickness map and breast location in the field of view were also calculated. A U-Net based DL model was developed to estimate the scatter signal based on the total input simulated image and trained single-projection-wise, with the thickness map and breast location provided as additional inputs. The model was internally validated using MC-simulated projections and tested using an external data set of 10 phantoms derived from images acquired with a different bCT system. For this purpose, the mean relative difference (MRD) and mean absolute error (MAE) were calculated. To test for accuracy in reconstructed images, a full bCT acquisition was mimicked with MC-simulations and then assessed by calculating the MAE and the structural similarity (SSIM). Subsequently, scatter was estimated and subtracted from the bCT scans of three patients to obtain the scatter-corrected image. The scatter-corrected projections were reconstructed and compared with the uncorrected reconstructions by evaluating the correction of the cupping artifact, increase in image contrast, and contrast-to-noise ratio (CNR).

RESULTS

The mean MRD and MAE across all cases (min, max) for the internal validation set were 0.04% (-1.1%, 1.3%) and 2.94% (2.7%, 3.2%), while for the external test set they were -0.64% (-1.6%, 0.2%) and 2.84% (2.3%, 3.5%), respectively. For MC-simulated reconstruction slices, the computed SSIM was 0.99 and the MAE was 0.11% (range: 0%, 0.35%) with a single outlier slice of 2.06%. For the three patient bCT reconstructed images, the correction increased the contrast by a mean of 25% (range: 20%, 30%), and reduced the cupping artifact. The mean CNR increased by 0.32 after scatter correction, which was not found to be significant (95% confidence interval: [-0.01, 0.65], p = 0.059). The time required to correct the scatter in a single bCT projection was 0.2 s on an NVIDIA GeForce GTX 1080 GPU.

CONCLUSION

The developed DL model could accurately estimate scatter in bCT projection images and could enhance contrast and correct for cupping artifact in reconstructed patient images without significantly affecting the CNR. The time required for correction would allow its use in daily clinical practice, and the reported accuracy will potentially allow quantitative reconstructions.

Cone-beam breast CT using an offset detector: effect of detector offset and image reconstruction algorithm

Objective.A dedicated cone-beam breast computed tomography (BCT) using a high-resolution, low-noise detector operating in offset-detector geometry has been developed. This study investigates the effects of varying detector offsets and image reconstruction algorithms to determine the appropriate combination of detector offset and reconstruction algorithm.Approach.Projection datasets (300 projections in 360°) of 30 breasts containing calcified lesions that were acquired using a prototype cone-beam BCT system comprising a 40 × 30 cm flat-panel detector with 1024 × 768 detector pixels were reconstructed using Feldkamp-Davis-Kress (FDK) algorithm and served as the reference. The projection datasets were retrospectively truncated to emulate cone-beam datasets with sinograms of 768×768 and 640×768 detector pixels, corresponding to 5 cm and 7.5 cm lateral offsets, respectively. These datasets were reconstructed using the FDK algorithm with appropriate weights and an ASD-POCS-based Fast, total variation-Regularized, Iterative, Statistical reconstruction Technique (FRIST), resulting in a total of 4 offset-detector reconstructions (2 detector offsets × 2 reconstruction methods). Signal difference-to-noise ratio (SDNR), variance, and full-width at half-maximum (FWHM) of calcifications in two orthogonal directions were determined from all reconstructions. All quantitative measurements were performed on images in units of linear attenuation coefficient (1/cm).Results.The FWHM of calcifications did not differ (P > 0.262) among reconstruction algorithms and detector formats, implying comparable spatial resolution. For a chosen detector offset, the FRIST algorithm outperformed FDK in terms of variance and SDNR (P < 0.0001). For a given reconstruction method, the 5 cm offset provided better results.Significance.This study indicates the feasibility of using the compressed sensing-based, FRIST algorithm to reconstruct sinograms from offset-detectors. Among the reconstruction methods and detector offsets studied, FRIST reconstructions corresponding to a 30 cm × 30 cm with 5 cm lateral offset, achieved the best performance. A clinical prototype using such an offset geometry has been developed and installed for clinical trials.

A novel hardware duo of beam modulation and shielding to reduce scatter acquisition and dose in cone-beam breast CT

PURPOSE

In cone-beam breast CT, scattered photons form a large portion of the acquired signal, adversely impacting image quality throughout the frequency response of the imaging system. Prior simulation studies provided proof of concept for utilization of a hardware solution to prevent scatter acquisition. Here, we report the design, implementation, and characterization of an auxiliary apparatus of fluence modulation and scatter shielding that does indeed lead to projections with a reduced level of scatter.

METHODS

An apparatus was designed for permanent installation within an existing cone-beam CT system. The apparatus is composed of two primary assemblies: a "Fluence Modulator" (FM) and a "Scatter Shield" (SS). The design of the assemblies enables them to operate in synchrony during image acquisition, converting the sourced x-rays into a moving narrow beam. During a projection, this narrow beam sweeps the entire fan angle coverage of the imaging system. As the two assemblies are contingent on one another, their joint implementation is described in the singular as apparatus FM-SS. The FM and the SS assemblies are each comprised a metal housing, a sensory system, and a robotic system. A controller unit handles their relative movements. A series of comparative studies were conducted to evaluate the performance of a cone-beam CT system in two "modes" of operation: with and without FM-SS installed, and to compare the results of physical implementation with those previously simulated. The dynamic range requirements of the utilized detector in the cone-beam CT imaging system were first characterized, independent of the mode of operation. We then characterized and compared the spatial resolution of the imaging system with, and without, FM-SS. A physical breast phantom, representative of an average size breast, was developed and imaged. Actual differences in signal level obtained with, versus without, FM-SS were then compared to the expected level gains based on previously reported simulations. Following these initial assessments, the scatter acquisition in each projection in both modes of operation was investigated. Finally, as an initial study of the impact of FM-SS on radiation dose in an average size breast, a series of Monte Carlo simulations were coupled with physical measurements of air kerma, with and without FM-SS.

RESULTS

With implementation of FM-SS, the detector's required dynamic range was reduced by a factor of 5.5. Substantial reduction in the acquisition of the scattered rays, by a factor of 5.1 was achieved. With the implementation of FM-SS, deposited dose was reduced by 27% in the studied breast.

CONCLUSIONS

The disclosed implementation of FM-SS, within a cone-beam breast CT system, results in reduction of scatter-components in acquired projections, reduction of dose deposit to the breast, and relaxation of requirements for the detector's dynamic range. Controlling or correcting for patient motion occurring during image acquisition remains an open problem to be solved prior to practical clinical usage of FM-SS cone-beam breast CT.

Flat-panel conebeam CT in the clinic: history and current state

Research into conebeam CT concepts began as soon as the first clinical single-slice CT scanner was conceived. Early implementations of conebeam CT in the 1980s focused on high-contrast applications where concurrent high resolution ( < 200    μ m ), for visualization of small contrast-filled vessels, bones, or teeth, was an imaging requirement that could not be met by the contemporaneous CT scanners. However, the use of nonlinear imagers, e.g., x-ray image intensifiers, limited the clinical utility of the earliest diagnostic conebeam CT systems. The development of consumer-electronics large-area displays provided a technical foundation that was leveraged in the 1990s to first produce large-area digital x-ray detectors for use in radiography and then compact flat panels suitable for high-resolution and high-frame-rate conebeam CT. In this review, we show the concurrent evolution of digital flat panel (DFP) technology and clinical conebeam CT. We give a brief summary of conebeam CT reconstruction, followed by a brief review of the correction approaches for DFP-specific artifacts. The historical development and current status of flat-panel conebeam CT in four clinical areas-breast, fixed C-arm, image-guided radiation therapy, and extremity/head-is presented. Advances in DFP technology over the past two decades have led to improved visualization of high-contrast, high-resolution clinical tasks, and image quality now approaches the soft-tissue contrast resolution that is the standard in clinical CT. Future technical developments in DFPs will enable an even broader range of clinical applications; research in the arena of flat-panel CT shows no signs of slowing down.

Tumor-to-Gland Volume Ratio versus Tumor-to-Breast Ratio as Measured on CBBCT: Possible Predictors of Breast-Conserving Surgery

Background

Breast-conserving surgery plus postoperative radiotherapy is the standard surgical treatment mode for early breast cancer. Currently, there are no clear predictive indicators to determine whether a patient can choose breast-conserving surgery, which mainly depends on the surgeon’s clinical experience and subjective judgment. Cone-beam breast computed tomography (CBBCT) reconstructs the breast 3D image from three mutually perpendicular angles, helping surgeons to locate and accurately measure the volume of the tumor, mammary gland, and breast. We used CBBCT to retrospectively measure the tumor-to-gland volume ratio and tumor-to-breast volume ratio in breast cancer cases. Then, we analyzed the correlation between the surgical methods and ratios in breast cancer patients.

Methods

We collected 100 patients undergoing breast-conserving surgery as the study group, and 100 patients undergoing mastectomy as the control group. All patients chose the surgical approach after comprehensive consideration of examination results and assessment of patient condition. Patients underwent CBBCT examination before surgery. We retrospectively measured the volume of tumor, mammary glands and breast, then calculated tumor-to-gland and tumor-to-breast volume ratios.

Results

Tumor volume and the ratios of the two groups statistically differed (P < 0.001), while the mammary gland and breast volume did not (P > 0.05). The average tumor-to-gland volume ratio was 4.32% in the study group and 10.74% in the control group, and the average tumor-to-breast volume ratio was 0.74% in the study group and 1.36% in the control group. In breast-conserving surgery, the 95% reference range of tumor-to-gland ratio is (0, 12.90%), and the 95% reference range of tumor-to-breast ratio is (0, 2.17%).

Conclusion

The tumor-to-gland volume ratio and tumor-to-breast volume ratio measured using CBBCT are correlated with the choice of surgical methods (breast-conserving surgery or mastectomy) for breast cancer patients. This can be used as possible predictor of breast-conserving surgery to help surgeons.

Radiation dosimetry of a clinical prototype dedicated cone-beam breast CT system with offset detector

PURPOSE

A clinical-prototype, dedicated, cone-beam breast computed tomography (CBBCT) system with offset detector is undergoing clinical evaluation at our institution. This study is to estimate the normalized glandular dose coefficients ( DgN CT ) that provide air kerma-to-mean glandular dose conversion factors using Monte Carlo simulations.

MATERIALS AND METHODS

The clinical prototype CBBCT system uses 49 kV x-ray spectrum with 1.39 mm 1st half-value layer thickness. Monte Carlo simulations (GATE, version 8) were performed with semi-ellipsoidal, homogeneous breasts of various fibroglandular weight fractions ( f g = 0.01 , 0.15 , 0.5 , 1 ) , chest wall diameters ( d = 8 , 10 , 14 , 18 , 20  cm), and chest wall to nipple length ( l = 0.75 d ), aligned with the axis of rotation (AOR) located at 65 cm from the focal spot to determine the DgN CT . Three geometries were considered - 40 × 30 -cm detector with no offset that served as reference and corresponds to a clinical CBBCT system, 30 × 30 -cm detector with 5 cm offset, and a 30 × 30 -cm detector with 10 cm offset.

RESULTS

For 5 cm lateral offset, the DgN CT ranged 0.177 - 0.574  mGy/mGy and reduction in DgN CT with respect to reference geometry was observed only for 18 cm ( 6.4 % ± 0.23 % ) and 20 cm ( 9.6 % ± 0.22 % ) diameter breasts. For the 10 cm lateral offset, the DgN CT ranged 0.221 - 0.581  mGy/mGy and reduction in DgN CT was observed for all breast diameters. The reduction in DgN CT was 1.4 % ± 0.48 % , 7.1 % ± 0.13 % , 17.5 % ± 0.19 % , 25.1 % ± 0.15 % , and 27.7 % ± 0.08 % for 8, 10, 14, 18, and 20 cm diameter breasts, respectively. For a given breast diameter, the reduction in DgN CT with offset-detector geometries was not dependent on f g . Numerical fits of DgN CT d , l , f g were generated for each geometry.

CONCLUSION

The DgN CT and the numerical fit, D g N CT d , l , f g would be of benefit for current CBBCT systems using the reference geometry and for future generations using offset-detector geometry. There exists a potential for radiation dose reduction with offset-detector geometry, provided the same technique factors as the reference geometry are used, and the image quality is clinically acceptable.

Optical conductivity of triple point fermions

As a low-energy effective theory on non-symmorphic lattices, we consider a generic triple point fermion Hamiltonian, which is parameterized by an angular parameterλ. We find strongλdependence in both Drude and interband optical absorption of these systems. The deviation of theT2coefficient of the Drude weight from Dirac/Weyl fermions can be used as a quick way to optically distinguish the triple point degeneracies from the Dirac/Weyl degeneracies. At the particularλ=π/6 point, we find that the 'helicity' reversal optical transition matrix element is identically zero. Nevertheless, deviating from this point, the helicity reversal emerges as an absorption channel.

Reduction of scatter in breast CT yields improved microcalcification visibility

The inadequate visibility of microcalcifications-small calcium deposits that cue radiologists to early stages of cancer-is a major limitation in current designs of dedicated breast computed tomography (bCT). This limitation has previously been attributed to the constituent components, spatial resolution, and utilized dose. Scattered radiation has been considered an occurrence with low-frequency impacts that can be compensated for in post-processing. We hypothesized, however, that the acquisition of scattered radiation has a far more detrimental impact on clinically relevant features than has previously been understood. Critically, acquisition of scatter leads to the reduced visibility of microcalcifications. This hypothesis was investigated and supported via mathematical derivations and simulation studies. We conducted a series of comparative studies in which four bCT systems were simulated under iso-dose and iso-resolution conditions, characterizing the dependencies of microcalcification contrast on accumulated scatter. Included among the simulated systems is a novel bCT design-narrow beam bCT (NB-bCT)-that captures nearly zero scatter. We find that current bCT systems suffer from significant levels of scatter. As validated in theory, depending on the system and size of microcalcifications, between 25% and over 70% of contrast resolution is lost due to scatter. The results in NB-bCT, however, provide evidence that by removing scatter build-up in projections, the contrast of microcalcifications in a bCT image is preserved, regardless of their size or location in the breast.

A residual dense network assisted sparse view reconstruction for breast computed tomography

To develop and investigate a deep learning approach that uses sparse-view acquisition in dedicated breast computed tomography for radiation dose reduction, we propose a framework that combines 3D sparse-view cone-beam acquisition with a multi-slice residual dense network (MS-RDN) reconstruction. Projection datasets (300 views, full-scan) from 34 women were reconstructed using the FDK algorithm and served as reference. Sparse-view (100 views, full-scan) projection data were reconstructed using the FDK algorithm. The proposed MS-RDN uses the sparse-view and reference FDK reconstructions as input and label, respectively. Our MS-RDN evaluated with respect to fully sampled FDK reference yields superior performance, quantitatively and visually, compared to conventional compressed sensing methods and state-of-the-art deep learning based methods. The proposed deep learning driven framework can potentially enable low dose breast CT imaging.

Intelligent system for predicting breast tumors using machine learning

The early hidden characteristics of breast tumors make their features difficult to be effectively identified. In order to improve the detection accuracy of breast tumors, this study combined with computer-aided diagnosis techniques such as machine learning and computer vision and used X-ray analysis to study breast tumor diagnosis techniques. Moreover, this study combines breast tumor diagnostic images to determine various parameters of the image. At the same time, through experimental research and analysis of the region segmentation method and preprocessing method of breast detection images, the best diagnostic images are obtained, and the influence of background and other noise on the image diagnosis results is effectively proposed. In addition, this study proposes a method for detecting the distortion of the mammogram image structure, which accurately detects the structural distortion and reduces the interference of various influencing factors. Finally, this paper designs experiments to study the effects of the diagnostic method of this paper. Through comparative analysis, it can be seen that the results of this study have certain advantages in accuracy and image clarity, and have certain clinical significance, and can provide theoretical reference for subsequent related research.

Sparse-view, short-scan, dedicated cone-beam breast computed tomography: image quality assessment

The purpose of this study is to quantify the impact of sparse-view acquisition in short-scan trajectories, compared to 360-degrees full-scan acquisition, on image quality measures in dedicated cone-beam breast computed tomography (BCT). Projection data from 30 full-scan (360-degrees; 300 views) BCT exams with calcified lesions were selected from an existing clinical research database. Feldkamp-Davis-Kress (FDK) reconstruction of the full-scan data served as the reference. Projection data corresponding to two short-scan trajectories, 204 and 270-degrees, which correspond to the minimum and maximum angular range achievable in a cone-beam BCT system were selected. Projection data were retrospectively sampled to provide 225, 180, and 168 views for 270-degrees short-scan, and 170 views for 204-degrees short-scan. Short-scans with 180 and 168 views in 270-degrees used non-uniform angular sampling. A fast, iterative, total variation-regularized, statistical reconstruction technique (FIRST) was used for short-scan image reconstruction. Image quality was quantified by variance, signal-difference to noise ratio (SDNR) between adipose and fibroglandular tissues, full-width at half-maximum (FWHM) of calcifications in two orthogonal directions, as well as, bias and root-mean-squared-error (RMSE) computed with respect to the reference full-scan FDK reconstruction. The median values of bias (8.6 × 10-4-10.3 × 10-4cm-1) and RMSE (6.8 × 10-6-9.8 × 10-6cm-1) in the short-scan reconstructions, computed with the full-scan FDK as the reference were close to, but not zero (P < 0.0001, one-sample median test). The FWHM of the calcifications in the short-scan reconstructions did not differ significantly from the reference FDK reconstruction (P > 0.118), except along the superior-inferior direction for the short-scan reconstruction with 168 views in 270-degrees (P = 0.046). The variance and SDNR from short-scan reconstructions were significantly improved compared to the full-scan FDK reconstruction (P < 0.0001). This study demonstrates the feasibility of the short-scan, sparse-view, compressed sensing-based iterative reconstruction. This study indicates that shorter scan times and reduced radiation dose without sacrificing image quality are potentially feasible.

Cone-beam breast computed tomography using ultra-fast image reconstruction with constrained, total-variation minimization for suppression of artifacts

Compressed sensing based iterative reconstruction algorithms for computed tomography such as adaptive steepest descent-projection on convex sets (ASD-POCS) are attractive due to their applicability in incomplete datasets such as sparse-view data and can reduce radiation dose to the patients while preserving image quality. Although IR algorithms reduce image noise compared to analytical Feldkamp-Davis-Kress (FDK) algorithm, they may generate artifacts, particularly along the periphery of the object. One popular solution is to use finer image-grid followed by down-sampling. This approach is computationally intensive but may be compensated by reducing the field of view. Our proposed solution is to replace the algebraic reconstruction technique within the original ASD-POCS by ordered subsets-simultaneous algebraic reconstruction technique (OS-SART) and with initialization using FDK image. We refer to this method as Fast, Iterative, TV-Regularized, Statistical reconstruction Technique (FIRST). In this study, we investigate FIRST for cone-beam dedicated breast CT with large image matrix. The signal-difference to noise ratio (SDNR), the difference of the mean value and the variance of adipose and fibroglandular tissues for both FDK and FIRST reconstructions were determined. With FDK serving as the reference, the root-mean-square error (RMSE), bias, and the full-width at half-maximum (FWHM) of microcalcifications in two orthogonal directions were also computed. Our results suggest that FIRST is competitive to the finer image-grid method with shorter reconstruction time. Images reconstructed using the FIRST do not exhibit artifacts and outperformed FDK in terms of image noise. This suggests the potential of this approach for radiation dose reduction in cone-beam breast CT.

Dedicated cone-beam breast CT using laterally-shifted detector geometry: Quantitative analysis of feasibility for clinical translation

BACKGROUND

High-resolution, low-noise detectors with minimal dead-space at chest-wall could improve posterior coverage and microcalcification visibility in the dedicated cone-beam breast CT (CBBCT). However, the smaller field-of-view necessitates laterally-shifted detector geometry to enable optimizing the air-gap for x-ray scatter rejection.

OBJECTIVE

To evaluate laterally-shifted detector geometry for CBBCT with clinical projection datasets that provide for anatomical structures and lesions.

METHODS

CBBCT projection datasets (n = 17 breasts) acquired with a 40×30 cm detector (1024×768-pixels, 0.388-mm pixels) were truncated along the fan-angle to emulate 20.3×30 cm, 22.2×30 cm and 24.1×30 cm detector formats and correspond to 20, 120, 220 pixels overlap in conjugate views, respectively. Feldkamp-Davis-Kress (FDK) algorithm with 3 different weighting schemes were used for reconstruction. Visual analysis for artifacts and quantitative analysis of root-mean-squared-error (RMSE), absolute difference between truncated and 40×30 cm reconstructions (Diff), and its power spectrum (PSDiff) were performed.

RESULTS

Artifacts were observed for 20.3×30 cm, but not for other formats. The 24.1×30 cm provided the best quantitative results with RMSE and Diff (both in units of μ, cm-1) of 4.39×10-3±1.98×10-3 and 4.95×10-4±1.34×10-4, respectively. The PSDiff (>0.3 cycles/mm) was in the order of 10-14μ2mm3 and was spatial-frequency independent.

CONCLUSIONS

Laterally-shifted detector CBBCT with at least 220 pixels overlap in conjugate views (24.1×30 cm detector format) provides quantitatively accurate and artifact-free image reconstruction.

Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography

PURPOSE

The incorporation of cone-beam computed tomography (CBCT) has allowed for enhanced image-guided radiation therapy. While CBCT allows for daily 3D imaging, images suffer from severe artifacts, limiting the clinical potential of CBCT. In this work, a deep learning-based method for generating high quality corrected CBCT (CCBCT) images is proposed.

METHODS

The proposed method integrates a residual block concept into a cycle-consistent adversarial network (cycle-GAN) framework, called res-cycle GAN, to learn a mapping between CBCT images and paired planning CT images. Compared with a GAN, a cycle-GAN includes an inverse transformation from CBCT to CT images, which constrains the model by forcing calculation of both a CCBCT and a synthetic CBCT. A fully convolution neural network with residual blocks is used in the generator to enable end-to-end CBCT-to-CT transformations. The proposed algorithm was evaluated using 24 sets of patient data in the brain and 20 sets of patient data in the pelvis. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC) indices, and spatial non-uniformity (SNU) were used to quantify the correction accuracy of the proposed algorithm. The proposed method is compared to both a conventional scatter correction and another machine learning-based CBCT correction method.

RESULTS

Overall, the MAE, PSNR, NCC, and SNU were 13.0 HU, 37.5 dB, 0.99, and 0.05 in the brain, 16.1 HU, 30.7 dB, 0.98, and 0.09 in the pelvis for the proposed method, improvements of 45%, 16%, 1%, and 93% in the brain, and 71%, 38%, 2%, and 65% in the pelvis, over the CBCT image. The proposed method showed superior image quality as compared to the scatter correction method, reducing noise and artifact severity. The proposed method produced images with less noise and artifacts than the comparison machine learning-based method.

CONCLUSIONS

The authors have developed a novel deep learning-based method to generate high-quality corrected CBCT images. The proposed method increases onboard CBCT image quality, making it comparable to that of the planning CT. With further evaluation and clinical implementation, this method could lead to quantitative adaptive radiation therapy.

Shading correction for volumetric CT using deep convolutional neural network and adaptive filter

BACKGROUND

Shading artifact may lead to CT number inaccuracy, image contrast loss and spatial non-uniformity (SNU), which is considered as one of the fundamental limitations for volumetric CT (VCT) application. To correct the shading artifact, a novel approach is proposed using deep learning and an adaptive filter (AF).

METHODS

Firstly, we apply the deep convolutional neural network (DCNN) to train a human tissue segmentation model. The trained model is implemented to segment the tissue. According to the general knowledge that CT number of the same human tissue is approximately the same, a template image without shading artifact can be generated using segmentation and then each tissue is filled with the corresponding CT number of a specific tissue. By subtracting the template image from the uncorrected image, the residual image with image detail and shading artifact are generated. The shading artifact is mainly low-frequency signals while the image details are mainly high-frequency signals. Therefore, we proposed an adaptive filter to separate the shading artifact and image details accurately. Finally, the estimated shading artifacts are deleted from the raw image to generate the corrected image.

RESULTS

On the Catphan©504 study, the error of CT number in the corrected image's region of interest (ROI) is reduced from 109 to 11 HU, and the image contrast is increased by a factor of 1.46 on average. On the patient pelvis study, the error of CT number in selected ROI is reduced from 198 to 10 HU. The SNU calculated from the ROIs decreases from 24% to 9% after correction.

CONCLUSIONS

The proposed shading correction method using DCNN and AF may find a useful application in future clinical practice.

Shading artifact correction in breast CT using an interleaved deep learning segmentation and maximum-likelihood polynomial fitting approach

PURPOSE

The purpose of this work was twofold: (a) To provide a robust and accurate method for image segmentation of dedicated breast CT (bCT) volume data sets, and (b) to improve Hounsfield unit (HU) accuracy in bCT by means of a postprocessing method that uses the segmented images to correct for the low-frequency shading artifacts in reconstructed images.

METHODS

A sequential and iterative application of image segmentation and low-order polynomial fitting to bCT volume data sets was used in the interleaved correction (IC) method. Image segmentation was performed through a deep convolutional neural network (CNN) with a modified U-Net architecture. A total of 45 621 coronal bCT images from 111 patient volume data sets were segmented (using a previously published segmentation algorithm) and used for neural network training, validation, and testing. All patient data sets were selected from scans performed on four different prototype breast CT systems. The adipose voxels for each patient volume data set, segmented using the proposed CNN, were then fit to a three-dimensional low-order polynomial. The polynomial fit was subsequently used to correct for the shading artifacts introduced by scatter and beam hardening in a method termed "flat fielding." An interleaved utilization of image segmentation and flat fielding was repeated until a convergence criterion was satisfied. Mathematical and physical phantom studies were conducted to evaluate the dependence of the proposed algorithm on breast size and the distribution of fibroglandular tissue. In addition, a subset of patient scans (not used in the CNN training, testing or validation) were used to investigate the accuracy of the IC method across different scanner designs and beam qualities.

RESULTS

The IC method resulted in an accurate classification of different tissue types with an average Dice similarity coefficient > 95%, precision > 97%, recall > 95%, and F1-score > 96% across all tissue types. The flat fielding correction of bCT images resulted in a significant reduction in either cupping or capping artifacts in both mathematical and physical phantom studies as measured by the integral nonuniformity metric with an average reduction of 71% for cupping and 30% for capping across different phantom sizes, and the Uniformity Index with an average reduction of 53% for cupping and 34% for capping.

CONCLUSION

The validation studies demonstrated that the IC method improves Hounsfield Units (HU) accuracy and effectively corrects for shading artifacts caused by scatter contamination and beam hardening. The postprocessing approach described herein is relevant to the broad scope of bCT devices and does not require any modification in hardware or existing scan protocols. The trained CNN parameters and network architecture are available for interested users.

Fast shading correction for cone-beam CT via partitioned tissue classification

The quantitative use of cone beam computed tomography (CBCT) in radiation therapy is limited by severe shading artifacts, even with system embedded correction. We recently proposed effective shading correction methods, using planning CT (pCT) as prior information to estimate low-frequency errors in either the projection domain or image domain. In this work, we further improve the clinical practicality of our previous methods by removing the requirement of prior pCT images. Clinical CBCT images are typically composed of a limited number of tissues. By utilizing the low frequency characteristic of shading distribution, we first generate a 'shading-free' template image by enforcing uniformity on CBCT voxels of the same tissue type via a technique named partitioned tissue classification. Only a small subset of voxels in the template image are used in the correction process to generate sparse samples of shading artifacts. Local filtration, a Fourier transform based algorithm, is employed to efficiently process the sparse errors to compute a full-field distribution of shading artifacts for CBCT correction. We evaluate the method's performance using an anthropomorphic pelvis phantom and 6 pelvis patients. The proposed method improves the image quality of CBCT for both phantom and patients to a level matching that of pCT. On the pelvis phantom, the signal non-uniformity (SNU) is reduced from 12.11% to 3.11% and 8.40% to 2.21% on fat and muscle, respectively. The maximum CT number error is reduced from 70 to 10 HU and 73 to 11 HU on fat and muscle, respectively. On patients, the average SNU is reduced from 9.22% to 1.06% and 11.41% to 1.67% on fat and muscle, respectively. The maximum CT number error is reduced from 95 to 9 HU and 88 to 8 HU on fat and muscle, respectively. The typical processing time for one CBCT dataset is about 45 s on a standard PC.

Emerging Breast Imaging Technologies on the Horizon

Early detection of breast cancers by mammography in conjunction with adjuvant therapy has contributed to reduction in breast cancer mortality. Mammography remains the "gold-standard" for breast cancer screening but is limited by tissue superposition. Digital breast tomosynthesis and more recently, dedicated breast computed tomography have been developed to alleviate the tissue superposition problem. However, all of these modalities rely upon x-ray attenuation contrast to provide anatomical images, and there are ongoing efforts to develop and clinically translate alternative modalities. These emerging modalities could provide for new contrast mechanisms and may potentially improve lesion detection and diagnosis. In this article, several of these emerging modalities are discussed with a focus on technologies that have advanced to the stage of in vivo clinical evaluation.

The role of off-focus radiation in scatter correction for dedicated cone beam breast CT

PURPOSE

Dedicated cone beam breast CT (CBBCT) suffers from x-ray scatter contamination. We aim to identify the source of the significant difference between the scatter distributions estimated by two recent methods proposed by our group and to investigate its effect on CBBCT image quality.

METHOD

We recently proposed two novel methods of scatter correction for CBBCT, using a library based (LB) technique and a forward projection (FP) model. Despite similar enhancement on CBBCT image qualities, these two methods obtain very different scatter distributions. We hypothesize that the off-focus radiation (OFR) is the contributor and results in nontrivial signals in x-ray projections, which is ignored in the scatter estimation via the LB method. Experiments using a thin wire test tool are designed to study the effect of OFR on CBBCT spatial resolution by measuring the point spread function (PSF) and the modulation transfer function (MTF). A narrow collimator setting is used to suppress the OFR-induced signals. In addition, "PSFs" and "MTFs" are measured on clinical CBBCT images obtained by the LB and FP methods using small calcifications as point sources. The improvement of spatial resolution achieved by suppressing OFR in the wire experiment as well as in the clinical study is quantified by the improvement ratios of PSFs and spatial frequencies at different MTF values. Our hypothesis that OFR causes the imaging difference between the FP and LB methods is verified if these ratios obtained from experimental and clinical data are consistent.

RESULTS

In the wire experiment, the results show that suppression of OFR increases the maximum signal of the PSF by about 14% and reduces the full-width-at-half-maximum (FWHM) by about 12.0%. Similar improvement on spatial resolution is achieved by the FP method compared with the LB method in the patient study. The improvement ratios of spatial frequencies at different MTF values without OFR match very well in both studies at a level of around 16%, with an average root-mean-square difference of 0.47%.

CONCLUSION

The results of the wire experiment and the clinical study indicate that the main difference between the LB and FP methods is whether the OFR-induced signals are included after scatter correction. Our study further shows that OFR significantly affects the image spatial resolution of CBBCT, indicating that the visualization of micro-calcifications is susceptible to OFR contamination. Our finding is therefore important in further improvement of diagnostic performance of CBBCT.

X-ray scatter correction for dedicated cone beam breast CT using a forward-projection model

PURPOSE

The quality of dedicated cone-beam breast CT (CBBCT) imaging is fundamentally limited by x-ray scatter contamination due to the large irradiation volume. In this paper, we propose a scatter correction method for CBBCT using a novel forward-projection model with high correction efficacy and reliability.

METHOD

We first coarsely segment the uncorrected, first-pass, reconstructed CBBCT images into binary-object maps and assign the segmented fibroglandular and adipose tissue with the correct attenuation coefficients based on the mean x-ray energy. The modified CBBCT are treated as the prior images toward scatter correction. Primary signals are first estimated via forward projection on the modified CBBCT. To avoid errors caused by inaccurate segmentation, only sparse samples of estimated primary are selected for scatter estimation. A Fourier-Transform based algorithm, herein referred to as local filtration hereafter, is developed to efficiently estimate the global scatter distribution on the detector. The scatter-corrected images are obtained by removing the estimated scatter distribution from measured projection data.

RESULTS

We evaluate the method performance on six patients with different breast sizes and shapes representing the general population. The results show that the proposed method effectively reduces the image spatial non-uniformity from 8.27 to 1.91% for coronal views and from 6.50 to 3.00% for sagittal views. The contrast-to-deviation ratio is improved by an average factor of 1.41. Comparisons on the image details reveal that the proposed scatter correction successfully preserves fine structures of fibroglandular tissues that are lost in the segmentation process.

CONCLUSION

We propose a highly practical and efficient scatter correction algorithm for CBBCT via a forward-projection model. The method is attractive in clinical CBBCT imaging as it is readily implementable on a clinical system without modifications in current imaging protocols or system hardware.

Local filtration based scatter correction for cone-beam CT using primary modulation

PURPOSE

Excessive scatter contamination fundamentally limits the image quality of cone-beam CT (CBCT), hindering its quantitative use in clinical applications. The author has previously proposed an effective scatter correction method for CBCT using primary modulation. A Fourier transform-based algorithm (FTPM) was implemented to estimate scatter from modulated projections, with a few limitations including the assumption of uniform modulation frequency and magnitude that becomes less accurate in the presence of beam-hardening and other nonideal effects. This paper aims to overcome the above drawbacks by developing a new algorithm for the primary modulation method with improved accuracy and reliability.

METHODS

Incident x-ray intensities for each detector pixel with and without the interception of the modulator blocker are estimated from a modulated flat-field image. A new signal relationship is then developed to obtain a first scatter estimate from a modulated projection using a spatially varying modulation distribution. The method empirically adjusts the effective modulation magnitude for each projection ray to account for the beam-hardening effects. Estimated scatter signals with high expected errors are discarded in the generation of the final scatter distribution. The author proposes a technique of local filtration to accelerate major portions of the signal processing, and the new algorithm is referred to as local filtration based primary modulation (LFPM).

RESULTS

The study on the Catphan® 600 phantom shows that LFPM effectively removes scatter-induced cupping artifacts on CBCT images and reduces the CT image error from 222 to 15 HU. In addition, the image contrast on eight contrast rods of the phantom is enhanced by a factor of 2 on average. On an anthropomorphic head phantom, LFPM reduces the CT image error from 153 to 18 HU and eliminates the streak artifacts observed on the result of FTPM with substantially improved image uniformity. On the Rando® phantom, LFPM reduces the CT image error from 278 to 4 HU around the object center.

CONCLUSIONS

As compared with the previously developed FTPM algorithm, LFPM enhances the imaging performance by using a more flexible data processing framework that does not require projection data downsampling or uniform modulation frequency and magnitude. It also becomes possible to discard suspicious scatter estimate values prior to the generation of a final scatter distribution and to model the beam-hardening effects on modulation for improved scatter estimation accuracy. The presented research further exploits the potential of the primary modulation method on scatter correction and facilitates its clinical adoption in CBCT imaging.