Deep learning-based virtual noncontrast CT for volumetric modulated arc therapy planning: Comparison with a dual-energy CT-based approach

Abstract

Purpose: The aim of this study was to develop a deep learning (DL) method for generating virtual noncontrast (VNC) computed tomography (CT) images from contrast-enhanced (CE) CT images (VNC_DL ) and to evaluate its performance in dose calculations for head and neck radiotherapy in comparison with VNC images derived from a dual-energy CT (DECT) scanner (VNC_DECT ).

Methods: This retrospective study included data for 61 patients who underwent head and neck radiotherapy. All planning CT images were obtained with a single-source DECT scanner (80 and 140 kVp) with rapid kVp switching. The DL-based method used a pair of virtual monochromatic images (VMIs) at 70 keV with and without contrast materials. VMIs without contrast materials were used as reference true noncontrast (TNC) images. Deformable image registration was used between the TNC and CE images. We used the data of 45 patients, chosen randomly, for training (7922 paired images), and data from the other 16 patients as test data. We generated the VNC_DL images with a densely connected convolutional network. As the VNC_DECT images, we used VMIs with the iodine signal suppressed, reconstructed from the CE images of the 16 test patients. The CT numbers of the tumor, common carotid artery, internal jugular vein, muscle, fat, bone marrow, cortical bone, and mandible of each VNC image were compared with those of the TNC image. The dose of the reference TNC plan was recalculated using the CE, VNC_DL , and VNC_DECT images. Difference maps of the dose distributions and dose-volume histograms were evaluated.

Results: The mean prediction time for the VNC_DL images was 3.4 s per patient, and the mean number of slices was 204. The absolute differences in CT numbers of the VNC_DL images were significantly smaller than those of the VNC_DECT images for the bone marrow (8.0 ± 6.5 vs 175.1 ± 40.9 HU; P < 0.001) and mandible (20.3 ± 19.3 vs 106.2 ± 80.5 HU; P = 0.002). The DL-based model provided the dose distribution most similar to that of the TNC plan. With the VNC_DECT plans, dose errors >1.0% were observed in bone regions. The dose-volume histogram analysis showed that the VNC_DL plans yielded the smallest errors for the primary target, although dose differences were <1.0% for all the approaches. For the maximum dose to the mandible, the mean ± SD errors for the CE, VNC_DL , and VNC_DECT plans were -0.13% ± 0.23% (range: -0.46% to 0.31%; P = 0.037), -0.01% ± 0.22% (range: -0.40% to 0.36%; P = 1.0), and 0.53% ± 0.47% (range: -0.21% to 1.41%; P < 0.001), respectively.

Conclusions: In this study, we developed a method based on DL that can rapidly generate VNC images from CE images without a DECT scanner. Compared with the DECT approach, the DL-based method improved the prediction accuracy of CT numbers in bone regions. Consequently, there was greater agreement between the VNC_DL and TNC plan dose distributions than with the CE and VNC_DECT plans, achieved by suppressing the contrast material signals while retaining the CT numbers of bone structures.

Keywords: deep learning; dose calculation; dual-energy CT; treatment planning; virtual noncontrast CT.