Dual-energy computed tomography (DECT) is of great significance for clinical practice due to its huge potential to provide material-specific information. However, DECT scanners are usually more expensive than standard singleenergy CT (SECT) scanners and thus are less accessible to undeveloped regions. In this paper, we show that the energy-domain correlation and anatomical consistency between standard DECT images can be harnessed by a deep learning model to provide high-performance DECT imaging from fully-sampled low-energy data together with singleview high-energy data. We demonstrate the feasibility of the approach with two independent cohorts (the first cohort including contrast-enhanced DECT scans of 5,753 image slices from 22 patients and the second cohort including spectral CT scans without contrast injection of 2463 image slices from other 22 patients) and show its superior performance on DECT applications. The deep-learning-based approach could be useful to further significantly reduce the radiation dose of current premium DECT scanners and has the potential to simplify the hardware of DECT imaging systems and to enable DECT imaging using standard SECT scanners.

No abstract

No abstract

Dual-energy computed tomography (DECT) is of great significance for clinical practice due to its huge potential to provide material-specific information. However, DECT scanners are usually more expensive than standard single-energy CT (SECT) scanners and thus are less accessible to undeveloped regions. In this paper, we show that the energy-domain correlation and anatomical consistency between standard DECT images can be harnessed by a deep learning model to provide high-performance DECT imaging from fully-sampled low-energy data together with single-view high-energy data, which can be obtained by using a scout-view high-energy image. We demonstrate the feasibility of the approach with contrast-enhanced DECT scans from 5,753 slices of images of twenty-two patients and show its superior performance on DECT applications. The deep learning-based approach could be useful to further significantly reduce the radiation dose of current premium DECT scanners and has the potential to simplify the hardware of DECT imaging systems and to enable DECT imaging using standard SECT scanners.

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 purpose a deep learning approach to perform DECT imaging by using standard SECT data. Methods: We designed a predenoising and difference learning mechanism to generate DECT images from SECT data. The method encompasses two parts: the first is image denoising using a fully convolutional network (FCN). The FCN is trained on the AAPM Low-Dose CT Grand Challenge dataset and applied to a set of contrastenhanced routine DECT data to reduce image noise. The second is dual-energy difference learning using a U-Net type network. In this part, the denoised low-energy CT images together with the difference image between the low-energy image and its corresponding high-energy counterpart image, are used as the network input and output, respectively. Finally, the predicted difference image is added to the input low-energy image to generate noise correlated high-energy image. The performance of the deep learning-based DECT approach was studied using images from patients who received contrast-enhanced abdomen DECT scan with a popular DE application: virtual noncontrast (VNC) imaging and contrast quantification. Clinically relevant metrics were used for quantitative assessment. Results: The absolute HU difference between the predicted and original high-energy CT images are 1.3 HU, 1.6 HU, 1.8 HU and 1.3 HU (corresponding maximum absolute HU differences are 3.0 HU, 2.9 HU, 3.1 HU, and 3.0 HU)for the ROIs on aorta, liver, spine and stomach, respectively. The aorta iodine quantification difference between iodine maps obtained from the original and deep learning DECT images is smaller than 1.0%, and the noise levels in the material images have been reduced by more than 7-folds for the latter. Conclusions: This study demonstrates that highly accurate DECT imaging with single low-energy data is achievable by using a deep learning approach. The proposed method allows us to obtain high-quality DECT images without paying the overhead i