Image quality improvement in bowtie-filter-equipped cone-beam CT using a dual-domain neural network.

BACKGROUND: The bowtie-filter in cone-beam CT (CBCT) causes spatially nonuniform x-ray beam often leading to eclipse artifacts in the reconstructed image. The artifacts are further confounded by the patient scatter, which is therefore patient-dependent as well as system-specific. PURPOSE: In this study, we propose a dual-domain network for reducing the bowtie-filter-induced artifacts in CBCT images. METHODS: In the projection domain, the network compensates for the filter-induced beam-hardening that are highly related to the eclipse artifacts. The output of the projection-domain network was used for image reconstruction and the reconstructed images were fed into the image-domain network. In the image domain, the network further reduces the remaining cupping artifacts that are associated with the scatter. A single image-domain-only network was also implemented for comparison. RESULTS: The proposed approach successfully enhanced soft-tissue contrast with much-reduced image artifacts. In the numerical study, the proposed method decreased perceptual loss and root-mean-square-error (RMSE) of the images by 84.5% and 84.9%, respectively, and increased the structure similarity index measure (SSIM) by 0.26 compared to the original input images on average. In the experimental study, the proposed method decreased perceptual loss and RMSE of the images by 87.2% and 92.1%, respectively, and increased SSIM by 0.58 compared to the original input images on average. CONCLUSIONS: We have proposed a deep-learning-based dual-domain framework to reduce the bowtie-filter artifacts and to increase the soft-tissue contrast in CBCT images. The performance of the proposed method has been successfully demonstrated in both numerical and experimental studies.

A novel analysis of the formation and resorption changes in dental hard tissue using longitudinal in vivo micro computed tomography.

This study was to investigate the new analysis manner of dental hard tissue change using in vivo micro-computed tomography (CT) in rat. Scanning, registration, analyzing, and presenting method to track longitudinal in vivo micro-CT data on dental hard tissues were validated in murine models: formative, dentin thickness after direct pulp capping with mineral trioxide aggregate; resorptive, development of apical bone rarefaction in apical periodontitis model. Serial in vivo micro-CT scans were analyzed through rigid-registration, active-contouring, deformable-registration, and motion vector-based quantitative analyses. The rate and direction of hard tissue formation after direct pulp capping was datafied by tracing coordinate shift of fiducial points on pulp chamber outline in formative model. The development of apical periodontitis could be monitored with voxel counts, and quantitatively analyzed in terms of lesion size, bone loss, and mineral density in resorptive model. This study supports the application of longitudinal in vivo micro-CT for resorptive- and formative-phase specific monitoring of dental hard tissues.

Panoramic dental tomosynthesis imaging by use of CBCT projection data.

Dental CBCT and panoramic images are important imaging modalities used in dental diagnosis and treatment planning. In order to acquire a panoramic image without an additional panoramic scan, in this study, we proposed a method of reconstructing a panoramic image by extracting panoramic projection data from dental CBCT projection data. After specifying the patient's dental arch from the patient's CBCT image, panoramic projection data are extracted from the CBCT projection data along the appropriate panoramic scan trajectory that fits the dental arch. A total of 40 clinical human datasets and one head phantom dataset were used to test the proposed method. The clinical human dataset used in this study includes cases in which it is difficult to reconstruct panoramic images from CBCT images, such as data with severe metal artifacts or data without teeth. As a result of applying the panoramic image reconstruction method proposed in this study, we were able to successfully acquire panoramic images from the CBCT projection data of various patients. The proposed method acquires a universally applicable panoramic image that is less affected by CBCT image quality and metal artifacts by extracting panoramic projection data from dental CBCT data and reconstructing a panoramic image.

Homogenization of multi-institutional chest x-ray images in various data transformation schemes.

Purpose: Although there are several options for improving the generalizability of learned models, a data instance-based approach is desirable when stable data acquisition conditions cannot be guaranteed. Despite the wide use of data transformation methods to reduce data discrepancies between different data domains, detailed analysis for explaining the performance of data transformation methods is lacking. Approach: This study compares several data transformation methods in the tuberculosis detection task with multi-institutional chest x-ray (CXR) data. Five different data transformations, including normalization, standardization with and without lung masking, and multi-frequency-based (MFB) standardization with and without lung masking were implemented. A tuberculosis detection network was trained using a reference dataset, and the data from six other sites were used for the network performance comparison. To analyze data harmonization performance, we extracted radiomic features and calculated the Mahalanobis distance. We visualized the features with a dimensionality reduction technique. Through similar methods, deep features of the trained networks were also analyzed to examine the models' responses to the data from various sites. Results: From various numerical assessments, the MFB standardization with lung masking provided the highest network performance for the non-reference datasets. From the radiomic and deep feature analyses, the features of the multi-site CXRs after MFB with lung masking were found to be well homogenized to the reference data, whereas the others showed limited performance. Conclusions: Conventional normalization and standardization showed suboptimal performance in minimizing feature differences among various sites. Our study emphasizes the strengths of MFB standardization with lung masking in terms of network performance and feature homogenization.

Neural network based ensemble model to predict radiation induced lymphopenia after concurrent chemo-radiotherapy for non-small cell lung cancer from two institutions.

The use of adjuvant Immune Checkpoint Inhibitors (ICI) after concurrent chemo-radiation therapy (CCRT) has become the standard of care for locally advanced non-small cell lung cancer (LA-NSCLC). However, prolonged radiotherapy regimens are known to cause radiation-induced lymphopenia (RIL), a long-neglected toxicity that has been shown to correlate with response to ICIs and survival of patients treated with adjuvant ICI after CCRT. In this study, we aim to develop a novel neural network (NN) approach that integrates patient characteristics, treatment related variables, and differential dose volume histograms (dDVH) of lung and heart to predict the incidence of RIL at the end of treatment. Multi-institutional data of 139 LA-NSCLC patients from two hospitals were collected for training and validation of our suggested model. Ensemble learning was combined with a bootstrap strategy to stabilize the model, which was evaluated internally using repeated cross validation. The performance of our proposed model was compared to conventional models using the same input features, such as Logistic Regression (LR) and Random Forests (RF), using the Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) curves. Our suggested model (AUC=0.77) outperformed the comparison models (AUC=0.72, 0.74) in terms of absolute performance, indicating that the convolutional structure of the network successfully abstracts additional information from the differential DVHs, which we studied using Gradient-weighted Class Activation Map. This study shows that clinical factors combined with dDVHs can be used to predict the risk of RIL for an individual patient and shows a path toward preventing lymphopenia using patient-specific modifications of the radiotherapy plan.

A feasibility study on deep-neural-network-based dose-neutral dual-energy digital breast tomosynthesis.

BACKGROUND: Diagnostic performance based on x-ray breast imaging is subject to breast density. Although digital breast tomosynthesis (DBT) is reported to outperform conventional mammography in denser breasts, mass detection and malignancy characterization are often considered challenging yet. PURPOSE: As an improved diagnostic solution to the dense breast cases, we propose a dual-energy DBT imaging technique that enables breast compositional imaging at comparable scanning time and patient dose compared to the conventional single-energy DBT. METHODS: The proposed dual-energy DBT acquires projection data by alternating two different energy spectra. Then, we synthesize unmeasured projection data using a deep neural network that exploits the measured projection data and adjacent projection data obtained under the other x-ray energy spectrum. For material decomposition, we estimate partial path lengths of an x-ray through water, lipid, and protein from the measured and the synthesized projection data with the object thickness information. After material decomposition in the projection domain, we reconstruct material-selective DBT images. The deep neural network is trained with the numerical breast phantoms. A pork meat phantom is scanned with a prototype dual-energy DBT system to demonstrate the feasibility of the proposed imaging method. RESULTS: The developed deep neural network successfully synthesized missing projections. Material-selective images reconstructed from the synthesized data present comparable compositional contrast of the cancerous masses compared with those from the fully measured data. CONCLUSIONS: The proposed dual-energy DBT scheme is expected to substantially contribute to enhancing mass malignancy detection accuracy particularly in dense breasts.

A generalized simultaneous algebraic reconstruction technique (GSART) for dual-energy X-ray computed tomography.

BACKGROUND: Dual-energy computed tomography (DECT) is a widely used and actively researched imaging modality that can estimate the physical properties of an object more accurately than single-energy CT (SECT). Recently, iterative reconstruction methods called one-step methods have received attention among various approaches since they can resolve the intermingled limitations of the conventional methods. However, the one-step methods typically have expensive computational costs, and their material decomposition performance is largely affected by the accuracy in the spectral coefficients estimation. OBJECTIVE: In this study, we aim to develop an efficient one-step algorithm that can effectively decompose into the basis material maps and is less sensitive to the accuracy of the spectral coefficients. METHODS: By use of a new loss function that employs the non-linear forward model and the weighted squared errors, we propose a one-step reconstruction algorithm named generalized simultaneous algebraic reconstruction technique (GSART). The proposed algorithm was compared with the image-domain material decomposition and other existing one-step reconstruction algorithm. RESULTS: In both simulation and experimental studies, we demonstrated that the proposed algorithm effectively reduced the beam-hardening artifacts thereby increasing the accuracy in the material decomposition. CONCLUSIONS: The proposed one-step reconstruction for material decomposition in dual-energy CT outperformed the image-domain approach and the existing one-step algorithm. We believe that the proposed method is a practically very useful addition to the material-selective image reconstruction field.

Deep-learning-based projection-domain breast thickness estimation for shape-prior iterative image reconstruction in digital breast tomosynthesis.

BACKGROUND: Digital breast tomosynthesis (DBT) is a technique that can overcome the shortcomings of conventional X-ray mammography and can be effective for the early screening of breast cancer. The compression of the breast is essential during the DBT imaging. However, since the periphery of the breast cannot be compressed to a constant value, nonuniformity of thickness and in-plane shape variation happen. These cause inconvenience in diagnosis, scatter correction, and breast density estimation. PURPOSE: In this study, we propose a deep-learning-based methodology for projection-domain breast thickness estimation and demonstrate a shape-prior iterative DBT image reconstruction. METHODS: We prepared the Euclidean distance map, the thickness map, and the thickness corrected image of the simulated breast projections for thickness and shape estimation. Each pixel of the Euclidean distance map denotes a distance to the closest skin-line. The thickness map is defined as a conceptual projection of ideal breast support that differentiates the inner and outer regions of the breast phantom. The thickness projection map thus represents the X-ray path lengths of a homogeneous breast phantom. We generated the thickness corrected image by dividing the projection image by the thickness map in a pixel-wise manner. We developed a convolutional neural network for thickness estimation and correction. The network utilizes a projection image and a Euclidean distance image together as a dual input. An estimated breast thickness map is then used for constructing the breast shape mask by use of the discrete algebraic reconstruction technique. RESULTS: The proposed network effectively corrected the breast thickness in various simulation situations. Low normalized root-mean-squared error (1.976%) and high structural similarity (99.997%) indicated a good agreement between the network-generated thickness corrected image and the ground truth image. Compared to the existing methods and simple single-input network, the proposed method showed outperformance in breast thickness estimation and accordingly in breast shape recovery for various numerical phantoms without provoking any significant artifact. We have demonstrated that the uniformity of voxel value has improved by the inclusion of a shape prior for the iterative DBT reconstruction. CONCLUSIONS: We presented a novel deep-learning-based breast thickness correction and a shape reconstruction method. This approach to estimating the true thickness map and the shape of the breast undergoing compression can benefit various fields such as improvement of diagnostic breast images, scatter correction, material decomposition, and breast density estimation.

Lymphocyte dynamics during and after chemo-radiation correlate to dose and outcome in stage III NSCLC patients undergoing maintenance immunotherapy.

PURPOSE: We investigated the dynamics of lymphocyte depletion and recovery during and after definitive concurrent chemoradiotherapy (CCRT), dose to which structures is correlated to them, and how they affect the prognosis of stage III non-small cell lung cancer (NSCLC) patients undergoing maintenance immunotherapy. METHODS AND MATERIALS: In this retrospective study, absolute lymphocyte counts (ALC) of 66 patients were obtained before, during, and after CCRT. Persistent lymphopenia was defined as ALC < 500/µL at 3 months after CCRT. The impact of regional dose on lymphocyte depletion and recovery was investigated using voxel-based analysis (VBA). RESULTS: Most patients (n = 65) experienced lymphopenia during CCRT: 39 patients (59.0%) had grade (G) 3+ lymphopenia. Fifty-nine patients (89.3%) recovered from treatment-related lymphopenia at 3 months after CCRT, whereas 7 (10.6%) showed persistent lymphopenia. Patient characteristics associated with persistent lymphopenia were older age and ALC before and during treatment. In multivariable Cox regression analysis, recovery from lymphopenia was identified as a significant prognostic factor for Progression Free Survival (HR 0.35, 95% CI 0.13-0.93, p = 0.034) and Overall Survival (HR 0.24, 95% CI 0.08-0.68, p = 0.007). Voxel-based analysis showed strong correlation of dose to the upper mediastinum with lymphopenia at the end of CCRT, but not at 3 months after CCRT. CONCLUSION: Recovery from lymphopenia is strongly correlated to improved survival of patients undergoing CCRT and adjuvant immunotherapy, and is correlated to lymphocyte counts pre- and post-CCRT. VBA reveals high correlation of dose to large vessels to lymphopenia at the end of CCRT. Therefore, efforts should be made not only for preventing lymphocyte depletion during CCRT but also for helping lymphocyte recovery after CCRT.

Three-compartment-breast (3CB) prior-guided diffuse optical tomography based on dual-energy digital breast tomosynthesis (DBT).

Diffuse optical tomography (DOT) is a non-invasive functional imaging modality that uses near-infrared (NIR) light to measure the oxygenation state and the concentration of hemoglobin. By complementarily using DOT with other anatomical imaging modalities, physicians can diagnose more accurately through additional functional image information. In breast imaging, diagnosis of dense breasts is often challenging because the bulky fibrous tissues may hinder the correct tumor characterization. In this work, we proposed a three-compartment-breast (3CB) decomposition-based prior-guided optical tomography for enhancing DOT image quality. We conjectured that the 3CB prior would lead to improvement of the spatial resolution and also of the contrast of the reconstructed tumor image, particularly for the dense breasts. We conducted a Monte-Carlo simulation to acquire dual-energy X-ray projections of a realistic 3D numerical breast phantom and performed digital breast tomosynthesis (DBT) for setting up a 3CB model. The 3CB prior was then used as a structural guide in DOT image reconstruction. The proposed method resulted in the higher spatial resolution of the recovered tumor even when the tumor is surrounded by the fibroglandular tissues compared with the typical two-composition-prior method or the standard Tikhonov regularization method.

A Novel Low-Dose Dual-Energy Imaging Method for a Fast-Rotating Gantry-Type CT Scanner.

CT scan by use of a beam-filter placed between the x-ray source and the patient allows a single-scan low-dose dual-energy imaging with a minimal hardware modification to the existing CT systems. We have earlier demonstrated the feasibility of such imaging method with a multi-slit beam-filter reciprocating along the direction perpendicular to the CT rotation axis in a cone-beam CT system. However, such method would face mechanical challenges when the beam-filter is supposed to cooperate with a fast-rotating gantry in a diagnostic CT system. In this work, we propose a new scanning method and associated image reconstruction algorithm that can overcome these challenges. We propose to slide a beam-filter that has multi-slit structure with its slits being at a slanted angle with the CT gantry rotation axis during a scan. A streaky pattern would show up in the sinogram domain as a result. Using a notch filter in the Fourier domain of the sinogram, we removed the streaks and reconstructed an image by use of the filtered-backprojection algorithm. The remaining image artifacts were suppressed by applying l0 norm based smoothing. Using this image as a prior, we have reconstructed low- and high-energy CT images in the iterative reconstruction framework. An image-based material decomposition then followed. We conducted a simulation study to test its feasibility using the XCAT phantom and also an experimental study using the Catphan phantom, a head phantom, an iodine-solution phantom, and a monkey in anesthesia, and showed its successful performance in image reconstruction and in material decomposition.

A synthesizing method for signal-enhanced and artifact-reduced mammogram from digital breast tomosynthesis.

In this paper, we propose a method for compositing a synthetic mammogram (SM) from digital breast tomosynthesis (DBT) slice images. The method consists of four parts. The first part is image reconstruction of DBT from the acquired projection data by use of backprojection-filtration (BPF) algorithm with a low-frequency boosting scheme and a high-density object reduction technique embedded. Also, a few expectation-maximization (EM) iterations have been additively implemented on top of the BPF algorithm to prepare a separate volume image. The second is generating three kinds of intermediate SMs. A forward projection image and a linear structure weighted forward projection image were computed. A maximum intensity projection of the BPF reconstructed volume image was also generated. The third part is integrating three intermediate SMs. The last is the post-processing of the SM. We scanned two physical phantoms in a prototype DBT scanner, and we have evaluated the performance of the proposed method. We also performed a clinical data study by use of 30 patient data who went through both DBT and digital mammography (DM) scans. Three experienced radiologists have read the SMs generated by several component techniques and also read the DM of each patient, and evaluated the generated SMs. The experimental phantom study and the clinical reader study consistently demonstrated the usefulness of the proposed method.

Data-specific mask-guided image reconstruction for diffuse optical tomography.

Conventional approaches in diffuse optical tomography (DOT) image reconstruction often address the ill-posed inverse problem via regularization with a constant penalty parameter, which uniformly smooths out the solution. In this study, we present a data-specific mask-guided scheme that incorporates a prior mask constraint into the image reconstruction framework. The prior mask was created from the DOT data itself by exploiting the multi-measurement vector formulation. We accordingly propose two methods to integrate the prior mask into the reconstruction process. First, as a soft prior by exploiting a spatially varying regularization. Second, as a hard prior by imposing a region-of-interest-limited reconstruction. Furthermore, the latter method iterates between discrete and continuous steps to update the mask and optical parameters, respectively. The proposed methods showed enhanced optical contrast accuracy, improved spatial resolution, and reduced noise level in DOT reconstructed images compared with the conventional approaches such as the modified Levenberg-Marquardt approach and the l1-regularization based sparse recovery approach.

Development of digital breast tomosynthesis and diffuse optical tomography fusion imaging for breast cancer detection.

Diffuse optical tomography (DOT) non-invasively measures the functional characteristics of breast lesions using near infrared light to probe tissue optical properties. This study aimed to evaluate a new digital breast tomosynthesis (DBT)/DOT fusion imaging technique and obtain preliminary data for breast cancer detection. Twenty-eight women were prospectively enrolled and underwent both DBT and DOT examinations. DBT/DOT fusion imaging was created after acquisition of both examinations. Two breast radiologists analyzed DBT and DOT images independently, and then finally evaluated the fusion images. The diagnostic performance of each reading session was compared and interobserver agreement was assessed. The technical success rate was 96.4%, with one failure due to an error during DOT data storage. Among the 27 women finally included in the analysis, 13 had breast cancer. The areas under the receiver operating characteristic curve (AUCs) for DBT were 0.783 and 0.854 for readers 1 and 2, respectively. DOT showed comparable diagnostic performance to DBT for both readers. The AUCs were significantly improved (P = 0.004) when the DBT/DOT fusion images were used. Interobserver agreements were highest for the DBT/DOT fusion images. In conclusion, this study suggests that DBT/DOT fusion imaging technique appears to be a promising tool for breast cancer diagnosis.

A Pilot Study of Chronological Microbiota Changes in a Rat Apical Periodontitis Model.

Apical periodontitis caused by microbial infection in the dental pulp is characterized by inflammation, destruction of the pulpal and periradicular tissues, and alveolar bone resorption. We analyzed the chronological changes in microbiota using a pyrosequencing-based approach combined with radiologic and histopathologic changes in a rat apical periodontitis model. During the three-week observation, the pulp and periapical area showed a typical progress of apical periodontitis. A total of 27 phyla, 645 genera, and 1276 species were identified. The root apex had a lower bacterial species diversity than the pulp chamber. Proteobacteria, Firmicutes, Bacteroidetes, and Actinobacteria were dominant phyla in both the pulp chamber and root apex. Remarkably, bacterial communities showed a tendency to change in the root apex based on the disease progression. At the genus level, Escherichia, Streptococcus, Lactobacillus, Rodentibacter, and Bacteroidetes were dominant genera in the pulp chamber. The most abundant genera in the root apex were Bradyrhizobium, Halomonas, and Escherichia. The species Azospirillum oryzae increased in the pulp chamber, whereas the species Bradyrhizobium japonicum and Halomonas stevensii were highly observed in the root apex as the disease progressed. The experimental rat model of apical periodontitis demonstrated a relationship between the microbiota and the apical periodontitis progression.

Clinical implementation of a wide-field electron arc technique with a scatterer for widespread Kaposi's sarcoma in the distal extremities.

A novel wide-field electron arc technique with a scatterer is implemented for widespread Kaposi's sarcoma (KS) in the distal extremities. Monte Carlo beam modeling for electron arc beams was established to achieve <2% deviation from the measurements, and used for dose calculation. MC-based electron arc plan was performed using CT images of a foot and leg mimicking phantom and compared with in-vivo measurement data. We enrolled one patient with recurrent KS on the lower extremities who had been treated with photon radiation therapy. The 4- and 6-MeV electron arc plans were created, and then compared to two photon plans: two opposite photon beam and volumetric modulated arc with bolus. Compared to the two photon techniques, the electron arc plans resulted in superior dose saving to normal organs beneath the skin region, although it shows inferior coverage and homogeneity for PTV. The electron arc treatment technique with scatterer was successfully implemented for the treatment of widespread KS in the distal extremities with lower radiation exposure to the normal organs beyond the skin lesions, which could be a treatment option for recurrent skin cancer in the extremities.

Convolutional neural network-based approach to estimate bulk optical properties in diffuse optical tomography.

Deep learning has been actively investigated for various applications such as image classification, computer vision, and regression tasks, and it has shown state-of-the-art performance. In diffuse optical tomography (DOT), the accurate estimation of the bulk optical properties of a medium is paramount because it directly affects the overall image quality. In this work, we exploit deep learning to propose a novel, to the best of our knowledge, convolutional neural network (CNN)-based approach to estimate the bulk optical properties of a highly scattering medium such as biological tissue in DOT. We validated the proposed method by using experimental, as well as, simulated data. For performance assessment, we compared the results of the proposed method with those of existing approaches. The results demonstrate that the proposed CNN-based approach for bulk optical property estimation outperforms existing methods in terms of estimation accuracy, with lower computation time.

On-beam computed tomography reconstruction for radiotherapy verification from projection image differences caused by motion during treatment.

The purpose of this study is to propose a reconstruction method of a target and its neighborhood, representative of the moment of radiotherapy delivery, based on differences in its transit images between the time of planning computed tomography (pCT) and the time of treatment beam delivery. To validate the method, a lung phantom with a target object was constructed, and CT-scanned before and after making a shift of the target. The latter scan was intended to simulate a potential organ movement at the time of treatment, and to serve as ground-truth images. Treatment planning using arc-beam delivery was done on the first pCT images. The planned beams were irradiated to the phantom after the shift, while cine transit images were acquired. Cine transit images were also calculated through the pCT images before the shift. From the ratio of the measured and calculated transit images, the amount of image changes due to the organ movement between the time of pCT and that of treatment was three-dimensionally reconstructed. By adding the reconstructed images to the pCT images before the shift, the CT images of the phantom at the time of the beam delivery were generated and compared with the ground truth images. The phantom after the shift was also scanned by on-board cone-beam computer tomography (CBCT) and reconstructed from the measured transit images (MVCT) for comparison. The proposed method reconstructed images that are very close to the ground-truth images in the volume and HU values of the target and the dose-volume coverage of the target and lung. Similar agreement was not found in the CBCT and MVCT images. The method may be used for 4D target image reconstruction, and, combined with the reconstructed image of un-irradiated areas, may offer clinically useful images of the entire region of interest.

Enhancement of soft-tissue contrast in cone-beam CT using an anti-scatter grid with a sparse sampling approach.

PURPOSE: Anti-scatter grids suppress the scatter substantially thus improving image contrast in radiography. However, its active use in cone-beam CT for the purpose of improving contrast-to-noise ratio (CNR) has not been successful mainly due to the increased noise related to Poisson statistics of photons. This paper proposes a sparse-view scanning approach to address the above issue. METHOD: Compared to the conventional cone-beam CT imaging framework, the proposed method reduces the number of projections and increases exposure in each projection to enhance image quality without an additional cost of radiation dose to patients. For image reconstruction from sparse-view data, an adaptive-steepest-descent projection-onto-convex-sets (ASD POCS) algorithm regularized by total-variation (TV) minimization was adopted. Contrast and CNR with various scattering conditions were evaluated in projection domain by a simulation study using GATE. Then we evaluated contrast, resolution, and image uniformity in CT image domain with Catphan phantom. A head phantom with soft-tissue structures was also employed for demonstrating a realistic application. A virtual grid-based estimation and reduction of scatter has also been implemented for comparison with the real anti-scatter grid. RESULTS: In the projection domain evaluation, contrast and CNR enhancement was observed when using an anti-scatter grid compared to the virtual grid. In the CT image domain, the proposed method produced substantially higher contrast and CNR of the low-contrast structures with much improved image uniformity. CONCLUSION: We have shown that the proposed method can provide high-quality CBCT images particularly with an increased contrast of soft-tissue at a neutral dose for image-guidance.

Deep Learning Diffuse Optical Tomography.

Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level. However, due to the complicated non-linear photon scattering physics and ill-posedness, the conventional reconstruction algorithms are sensitive to imaging parameters such as boundary conditions. To address this, here we propose a novel deep learning approach that learns non-linear photon scattering physics and obtains an accurate three dimensional (3D) distribution of optical anomalies. In contrast to the traditional black-box deep learning approaches, our deep network is designed to invert the Lippman-Schwinger integral equation using the recent mathematical theory of deep convolutional framelets. As an example of clinical relevance, we applied the method to our prototype DOT system. We show that our deep neural network, trained with only simulation data, can accurately recover the location of anomalies within biomimetic phantoms and live animals without the use of an exogenous contrast agent.