Two-view topogram-based anatomy-guided CT reconstruction for prospective risk minimization

• Verfasst von: Liu, Chang [VerfasserIn]
• Verfasst von: Klein, Laura [VerfasserIn]
• Verfasst von: Huang, Yixing [VerfasserIn]
• Verfasst von: Baader, Edith [VerfasserIn]
• Verfasst von: Lell, Michael [VerfasserIn]
• Verfasst von: Kachelrieß, Marc [VerfasserIn]
• Verfasst von: Maier, Andreas [VerfasserIn]
• Titel: Two-view topogram-based anatomy-guided CT reconstruction for prospective risk minimization
• Verf.angabe: Chang Liu, Laura Klein, Yixing Huang, Edith Baader, Michael Lell, Marc Kachelrieß & Andreas Maier
• E-Jahr: 2024
• Jahr: 23 April 2024
• Umfang: 11 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 05.02.2025
• Titel Quelle: Enthalten in: Scientific reports
• Ort Quelle: [London] : Springer Nature, 2011
• Jahr Quelle: 2024
• Band/Heft Quelle: 14(2024), Artikel-ID 9373, Seite 1-11
• ISSN Quelle: 2045-2322
• DOI: doi:10.1038/s41598-024-59731-y
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Humans
• Sach-SW: Prospective Studies
• Sach-SW: Phantoms, Imaging
• Sach-SW: Radiation Dosage
• Sach-SW: Imaging, Three-Dimensional
• Sach-SW: Algorithms
• Sach-SW: Tomography, X-Ray Computed
• Sach-SW: Image Processing, Computer-Assisted
• Sach-SW: CT
• Sach-SW: Two-view reconstruction
• K10plus-PPN: 1916432174

Abstract

To facilitate a prospective estimation of the effective dose of an CT scan prior to the actual scanning in order to use sophisticated patient risk minimizing methods, a prospective spatial dose estimation and the known anatomical structures are required. To this end, a CT reconstruction method is required to reconstruct CT volumes from as few projections as possible, i.e. by using the topograms, with anatomical structures as correct as possible. In this work, an optimized CT reconstruction model based on a generative adversarial network (GAN) is proposed. The GAN is trained to reconstruct 3D volumes from an anterior-posterior and a lateral CT projection. To enhance anatomical structures, a pre-trained organ segmentation network and the 3D perceptual loss are applied during the training phase, so that the model can then generate both organ-enhanced CT volume and organ segmentation masks. The proposed method can reconstruct CT volumes with PSNR of 26.49, RMSE of 196.17, and SSIM of 0.64, compared to 26.21, 201.55 and 0.63 using the baseline method. In terms of the anatomical structure, the proposed method effectively enhances the organ shapes and boundaries and allows for a straight-forward identification of the relevant anatomical structures. We note that conventional reconstruction metrics fail to indicate the enhancement of anatomical structures. In addition to such metrics, the evaluation is expanded with assessing the organ segmentation performance. The average organ dice of the proposed method is 0.71 compared with 0.63 for the baseline model, indicating the enhancement of anatomical structures.