Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging
Medical Physics2019Vol. 46(9), pp. 3788–3798
Citations Over TimeTop 10% of 2019 papers
Abstract
The 2D and 3D CNNs generated accurate pelvic sCTs for the 20 patients using T1-weighted MR images. Statistical tests indicated that the proposed 3D model was able to generate sCTs with smaller MAE and higher bone region precision compared to 2D models. Results of patient alignment tests suggested that sCTs generated by the proposed CNNs can provide accurate patient positioning. The accuracy of the dose calculation using generated sCTs will be tested and compared for the proposed models in the future.
Related Papers
- → CT Hounsfield Numbers of Soft Tissues on Unenhanced Abdominal CT Scans: Variability Between Two Different Manufacturers’ MDCT Scanners(2014)148 cited
- → Commissioning of a relative stopping power to Hounsfield unit calibration curve for a Mevion proton radiation treatment unit(2016)4 cited
- 악골 병소의 켬퓨터 촬영상에서 Hounsfield Unit에 관한 연구(2006)
- → On the prediction of X-ray dose deviations and the influence of CT scan protocols(2017)
- → Predicting the Hounsfield Unit (HU) of Aluminum Alloy AA2011 From the Weight Fractions of its Alloying Elements: An X-Ray Computed Tomography Study(2022)