3DCT Reconstruction from a Single X-Ray Projection Using Convolutional Neural Network

• Main Authors: Loyen, Estelle, Dasnoy-Sumell, Damien, Macq, Benoit
• Format: Conference Proceeding
• Language: English
• Subjects: 3DCT reconstruction; convolutional neural network; Convolutional neural networks; fluoroscopy; markerless tumor tracking; Neural networks; Real-time systems; Root mean square; Safety; Three-dimensional displays; Training
• ISSN: 2381-8549
• DOI: 10.1109/ICIP46576.2022.9897902

The treatment of mobile tumors remains complex in radiotherapy due to breathing-related organ movements. A solution to ensure target coverage during the process is to plan the treatment taking into account safety margins. One way to significantly reduce these safety margins would be to adapt the treatment in real time using image-guided radiation therapy. The acquisition of x-ray projections during treatment is commonly used to localise the tumor in 2D but doesn't provide 3D information. Hence, the aim of this work is to reconstruct a high resolution 3D image based on a single radiograph in order to know the 3D position of the tumor and the organs. This is done using a convolutional neural network. The results show that the proposed method is able to reconstruct a 3DCT based on a 2D projection x-ray only. The normalized root mean square error is computed between the ground truth 3DCT and the predicted 3DCT, and the mean of this metric is between 0.02713 and 0.02776 depending on the patient.