Premium
Deep learning‐based virtual noncontrast CT for volumetric modulated arc therapy planning: Comparison with a dual‐energy CT‐based approach
Author(s) -
Koike Yuhei,
Ohira Shingo,
Akino Yuichi,
Sagawa Tomohiro,
Yagi Masashi,
Ueda Yoshihiro,
Miyazaki Masayoshi,
Sumida Iori,
Teshima Teruki,
Ogawa Kazuhiko
Publication year - 2020
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.13925
Subject(s) - nuclear medicine , medicine , scanner , image registration , head and neck , computer science , artificial intelligence , image (mathematics) , surgery
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.