In a standard computed tomography (CT) image, pixels having the same Hounsfield Units (HU) can correspond to different materials and it is therefore challenging to differentiate and quantify materials. Dual-energy CT (DECT) is desirable to differentiate multiple materials, but DECT scanners are not widely available as singleenergy CT (SECT) scanners. Here we develop a deep learning approach to perform DECT imaging by using standard SECT data. The end point of the deep learning approach is a model capable of providing the high-energy CT image for a given input low-energy CT image. We retrospectively studied 22 patients who received contrast-enhanced abdomen DECT scan. The difference between the predicted and original high-energy CT images are 3.47 HU, 2.95 HU, 2.38 HU, and 2.40 HU for spine, aorta, liver and stomach, respectively. The difference between virtual non-contrast (VNC) images obtained from original DECT and deep learning DECT are 4.10 HU, 3.75 HU, 2.33 HU and 2.92 HU for spine, aorta, liver and stomach, respectively. The aorta iodine quantification difference between iodine maps obtained from original DECT and deep learning DECT images is 0.9%. This study demonstrates that highly accurate DECT imaging with single low-energy data is achievable by using a deep learning approach. The proposed method can significantly simplify the DECT system design, reducing the scanning dose and imaging cost.
Current image-guided prostate radiotherapy often relies on the use of implanted fiducial markers (FMs) or transducers for target localization. Fiducial or transducer insertion requires an invasive procedure that adds cost and risks for bleeding, infection and discomfort to some patients. We are developing a novel markerless prostate localization strategy using a pre-trained deep learning model to interpret routine projection kV X-ray images without the need for daily cone-beam computed tomography (CBCT). A deep learning model was first trained by using several thousand annotated projection X-ray images. The trained model is capable of identifying the location of the prostate target for a given input X-ray projection image. To assess the accuracy of the approach, three patients with prostate cancer received volumetric modulated arc therapy (VMAT) were retrospectively studied. The results obtained by using the deep learning model and the actual position of the prostate were compared quantitatively. The deviations between the target positions obtained by the deep learning model and the corresponding annotations ranged from 1.66 mm to 2.77 mm for anterior-posterior (AP) direction, and from 1.15 mm to 2.88 mm for lateral direction. Target position provided by deep learning model for the kV images acquired using OBI is found to be consistent that derived from the implanted FMs. This study demonstrates, for the first time, that highly accurate markerless prostate localization based on deep learning is achievable. The strategy provides a clinically valuable solution to daily patient positioning and real-time target tracking for image-guided radiotherapy (IGRT) and interventions.
Tomographic imaging using a penetrating wave, such as X-ray, light and microwave, is a fundamental approach to generate cross-sectional views of internal anatomy in a living subject or interrogate material composition of an object and plays an important role in modern science. To obtain an image free of aliasing artifacts, a sufficiently dense angular sampling that satisfies the Shannon-Nyquist criterion is required. In the past two decades, image reconstruction strategy with sparse sampling has been investigated extensively using approaches such as compressed-sensing. This type of approach is, however, ad hoc in nature as it encourages certain form of images. Recent advancement in deep learning provides an enabling tool to transform the way that an image is constructed. Along this line, Zhu et al1 presented a data-driven supervised learning framework to relate the sensor and image domain data and applied the method to magnetic resonance imaging (MRI). Here we investigate a deep learning strategy of tomographic X-ray imaging in the limit of a single-view projection data input. For the first time, we introduce the concept of dimension transformation in image feature domain to facilitate volumetric imaging by using a single or multiple 2D projections. The mechanism here is fundamentally different from the traditional approaches in that the image formation is driven by prior knowledge casted in the deep learning model. This work pushes the boundary of tomographic imaging to the single-view limit and opens new opportunities for numerous practical applications, such as image guided interventions and security inspections. It may also revolutionize the hardware design of future tomographic imaging systems
X-ray energy spectrum plays an essential role in imaging and related tasks. Due to the high photon flux
of clinical CT scanners, most of the spectrum estimation methods are indirect and are usually suffered from
various limitations. The recently proposed indirect transmission measurement-based method requires at least
the segmentation of one material, which is insufficient for CT images of highly noisy and with artifacts. To
combat for the bottleneck of spectrum estimation using segmented CT images, in this study, we develop a
segmentation-free indirect transmission measurement based energy spectrum estimation method using dual-energy
material decomposition. The general principle of the method is to compare polychromatic forward
projection with raw projection to calibrate a set of unknown weights which are used to express the unknown
spectrum together with a set of model spectra. After applying dual-energy material decomposition using high-and
low-energy raw projection data, polychromatic forward projection is conducted on material-specific images.
The unknown weights are then iteratively updated to minimize the difference between the raw projection and
estimated projection. Both numerical simulations and experimental head phantom are used to evaluate the
proposed method. The results indicate that the method provides accurate estimate of the spectrum and it may
be attractive for dose calculations, artifacts correction and other clinical applications.
A grating-based x-ray multi-contrast imaging system integrates a source grating G0, a diffraction grating G1, and an analyzer grating G2 into a conventional x-ray imaging system to generate images with three contrast mechanisms: absorption contrast, differential phase contrast, and dark field contrast. To facilitate the potential translation of this multi-contrast imaging system into a clinical setting, our group has developed several single-shot data acquisition methods to eliminate the necessity of the time-consuming phase stepping procedure. These methods have enabled us to acquire multi-contrast images with the same data acquisition time currently used for absorption imaging. One of the proposed methods is the use a staggered G2 grating. In this work, we propose to incorporate this staggered G2 grating into a state-of-the-art breast tomosynthesis imaging system to generate tomosynthesis images with three contrast mechanisms. The introduction of this staggered G2 grating will reject scatter and thus improve image contrast at the detector plane, but it will also absorb some x-ray photons reaching detector, thus increasing noise and reducing the contrast to noise ratio (CNR). Therefore, a key technical question is whether the CNR and dose efficiency can be maintained for absorption imaging after the introduction of this staggered G2 grating. In this paper, both the CNR and scatter-to-primary ratio (SPR) of absorption imaging were investigated with Monte Carlo simulations for a variety of staggered G2 grating designs.
This paper provides a fast and patient-specific scatter artifact correction method for cone-beam computed tomography (CBCT) used in image-guided interventional procedures. Due to increased irradiated volume of interest in CBCT imaging, scatter radiation has increased dramatically compared to 2D imaging, leading to a degradation of image quality. In this study, we propose a scatter artifact correction strategy using an analytical convolution-based model whose free parameters are estimated using a rough estimation of scatter profiles from the acquired cone-beam projections. It was evaluated using Monte Carlo simulations with both monochromatic and polychromatic X-ray sources. The results demonstrated that the proposed method significantly reduced the scatter-induced shading artifacts and recovered CT numbers.