{"title":"Pseudo dual-energy CT-derived iodine mapping using single-energy CT data based on a convolution neural network.","authors":"Yuki Yuasa, Takehiro Shiinoki, Koya Fujimoto, Hidekazu Tanaka","doi":"10.1259/bjro.20220059","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The objectives of this study are: (1) to develop a convolutional neural network model that yields pseudo high-energy CT (CT<sub>pseudo_high</sub>) from simple image processed low-energy CT (CT<sub>low</sub>) images, and (2) to create a pseudo iodine map (IM<sub>pseudo</sub>) and pseudo virtual non-contrast (VNC<sub>pseudo</sub>) images for thoracic and abdominal regions.</p><p><strong>Methods: </strong>Eighty patients who underwent dual-energy CT (DECT) examinations were enrolled. The data obtained from 55, 5, and 20 patients were used for training, validation, and testing, respectively. The ResUnet model was used for image generation model and was trained using CT<sub>low</sub> and high-energy CT (CT<sub>high</sub>) images. The proposed model performance was evaluated by calculating the CT values, image noise, mean absolute errors (MAEs), and histogram intersections (HIs).</p><p><strong>Results: </strong>The mean difference in the CT values between CT<sub>pseudo_high</sub> and CT<sub>high</sub> images were less than 6 Hounsfield unit (HU) for all evaluating patients. The image noise of CT<sub>pseudo_high</sub> was significantly lower than that of CT<sub>high</sub>. The mean MAEs was less than 15 HU, and HIs were almost 1.000 for all the patients. The evaluation metrics of IM and VNC exhibited the same tendency as that of the comparison between CT<sub>pseudo_high</sub> and CT<sub>high</sub> images.</p><p><strong>Conclusions: </strong>Our results indicated that the proposed model enables to obtain the DECT images and material-specific images from only single-energy CT images.</p><p><strong>Advances in knowledges: </strong>We constructed the CNN-based model which can generate pseudo DECT image and DECT-derived material-specific image using only simple image-processed CT<sub>low</sub> images for the thoracic and abdominal regions.</p>","PeriodicalId":72419,"journal":{"name":"BJR open","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10630979/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BJR open","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1259/bjro.20220059","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: The objectives of this study are: (1) to develop a convolutional neural network model that yields pseudo high-energy CT (CTpseudo_high) from simple image processed low-energy CT (CTlow) images, and (2) to create a pseudo iodine map (IMpseudo) and pseudo virtual non-contrast (VNCpseudo) images for thoracic and abdominal regions.
Methods: Eighty patients who underwent dual-energy CT (DECT) examinations were enrolled. The data obtained from 55, 5, and 20 patients were used for training, validation, and testing, respectively. The ResUnet model was used for image generation model and was trained using CTlow and high-energy CT (CThigh) images. The proposed model performance was evaluated by calculating the CT values, image noise, mean absolute errors (MAEs), and histogram intersections (HIs).
Results: The mean difference in the CT values between CTpseudo_high and CThigh images were less than 6 Hounsfield unit (HU) for all evaluating patients. The image noise of CTpseudo_high was significantly lower than that of CThigh. The mean MAEs was less than 15 HU, and HIs were almost 1.000 for all the patients. The evaluation metrics of IM and VNC exhibited the same tendency as that of the comparison between CTpseudo_high and CThigh images.
Conclusions: Our results indicated that the proposed model enables to obtain the DECT images and material-specific images from only single-energy CT images.
Advances in knowledges: We constructed the CNN-based model which can generate pseudo DECT image and DECT-derived material-specific image using only simple image-processed CTlow images for the thoracic and abdominal regions.