Purpose: To assess the feasibility of deep learning-based high resolution synthetic CT generation from MRIscans of the lower arm for orthopedic applications.Methods: A conditional Generative Adversarial Network was trained to synthesize CT images from multi-echoMR images. A training set of MRI and CT scans of 9 ex vivo lower arms was acquired and the CT images wereregistered to the MRI images. Three-fold cross-validation was applied to generate independent results for theentire dataset. The synthetic CT images were quantitatively evaluated with the mean absolute error metric, andDice similarity and surface to surface distance on cortical bone segmentations.Results: The mean absolute error was 63.5 HU on the overall tissue volume and 144.2 HU on the cortical bone.The mean Dice similarity of the cortical bone segmentations was 0.86. The average surface to surface distancebetween bone on real and synthetic CT was 0.48 mm. Qualitatively, the synthetic CT images corresponded wellwith the real CT scans and partially maintained high resolution structures in the trabecular bone. The bonesegmentations on synthetic CT images showed some false positives on tendons, but the general shape of the bonewas accurately reconstructed.Conclusions: This study demonstrates that high quality synthetic CT can be generated from MRI scans ofthe lower arm. The good correspondence of the bone segmentations demonstrates that synthetic CT could becompetitive with real CT in applications that depend on such segmentations, such as planning of orthopedicsurgery and 3D printing.
展开▼
