Your browser doesn't support javascript.
loading
Deep neural network-based synthetic image digital fluoroscopy using digitally reconstructed tomography.
Mori, Shinichiro; Hirai, Ryusuke; Sakata, Yukinobu; Tachibana, Yasuhiko; Koto, Masashi; Ishikawa, Hitoshi.
Afiliação
  • Mori S; National Institutes for Quantum Science and Technology, Quantum Life and Medical Science Directorate, Institute for Quantum Medical Science, Inage-ku, Chiba, 263-8555, Japan. mori.shinichiro@qst.go.jp.
  • Hirai R; Corporate Research and Development Center, Toshiba Corporation, Kanagawa, 212-8582, Japan.
  • Sakata Y; Corporate Research and Development Center, Toshiba Corporation, Kanagawa, 212-8582, Japan.
  • Tachibana Y; National Institutes for Quantum Science and Technology, Quantum Life and Medical Science Directorate, Institute for Quantum Medical Science, Inage-ku, Chiba, 263-8555, Japan.
  • Koto M; QST hospital, National Institutes for Quantum Science and Technology, Inage-ku, Chiba, 263-8555, Japan.
  • Ishikawa H; QST hospital, National Institutes for Quantum Science and Technology, Inage-ku, Chiba, 263-8555, Japan.
Phys Eng Sci Med ; 46(3): 1227-1237, 2023 Sep.
Article em En | MEDLINE | ID: mdl-37349631
We developed a deep neural network (DNN) to generate X-ray flat panel detector (FPD) images from digitally reconstructed radiographic (DRR) images. FPD and treatment planning CT images were acquired from patients with prostate and head and neck (H&N) malignancies. The DNN parameters were optimized for FPD image synthesis. The synthetic FPD images' features were evaluated to compare to the corresponding ground-truth FPD images using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). The image quality of the synthetic FPD image was also compared with that of the DRR image to understand the performance of our DNN. For the prostate cases, the MAE of the synthetic FPD image was improved (= 0.12 ± 0.02) from that of the input DRR image (= 0.35 ± 0.08). The synthetic FPD image showed higher PSNRs (= 16.81 ± 1.54 dB) than those of the DRR image (= 8.74 ± 1.56 dB), while SSIMs for both images (= 0.69) were almost the same. All metrics for the synthetic FPD images of the H&N cases were improved (MAE 0.08 ± 0.03, PSNR 19.40 ± 2.83 dB, and SSIM 0.80 ± 0.04) compared to those for the DRR image (MAE 0.48 ± 0.11, PSNR 5.74 ± 1.63 dB, and SSIM 0.52 ± 0.09). Our DNN successfully generated FPD images from DRR images. This technique would be useful to increase throughput when images from two different modalities are compared by visual inspection.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Tomografia Computadorizada por Raios X / Neoplasias de Cabeça e Pescoço Limite: Humans / Male Idioma: En Ano de publicação: 2023 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Tomografia Computadorizada por Raios X / Neoplasias de Cabeça e Pescoço Limite: Humans / Male Idioma: En Ano de publicação: 2023 Tipo de documento: Article