Three‐dimensional image volumes from two‐dimensional digitally reconstructed radiographs: A deep learning approach in lower limb CT scans

Abstract

Purpose: Three-dimensional (3D) reconstructions of the human anatomy have been available for surgery planning or diagnostic purposes for a few years now. The different image modalities usually rely on several consecutive two-dimensional (2D) acquisitions in order to reconstruct the 3D volume. Hence, such acquisitions are expensive, time-demanding and often expose the patient to an undesirable amount of radiation. For such reasons, along the most recent years, several studies have been proposed that extrapolate 3D anatomical features from merely 2D exams such as x rays for implant templating in total knee or hip arthroplasties. Method: The presented study shows an adaptation of a deep learning-based convolutional neural network to reconstruct 3D volumes from a mere 2D digitally reconstructed radiograph from one of the most extensive lower limb computed tomography datasets available. This novel approach is based on an encoder-decoder architecture with skip connections and a multidimensional Gaussian filter as data augmentation technique. Results: The results achieved promising values when compared against the ground truth volumes, quantitatively yielding an average of 0.77 AE 0.05 structured similarity index. Conclusions: A novel deep learning-based approach to reconstruct 3D medical image volumes from a single x-ray image was shown in the present study. The network architecture was validated against the original scans presenting SSIM values of 0.77 AE 0.05 and 0.78 AE 0.06, respectively for the knee and the hip crop.

Increase in tibial internal rotation due to weight-bearing is a key feature to diagnose early-stage knee osteoarthritis: a study with upright computed tomography

“…As anterior-posterior radiograph is still the gold standard to diagnose knee OA, there is a need to develop method to evaluate tibial internal/external rotation on radiographs. In the future, computer-aided method with deep learning algorithm has a potential to evaluate the tibial rotation and to diagnose early-stage knee OA on 2D radiograph [ 29 ]. Third, K-L grading was done on supine non-weight-bearing radiographs.…”

Increase in Tibial Internal Rotation Due to Weight-bearing is a Key Feature to Diagnose Early-stage Knee Osteoarthritis: A Study with Upright Computed Tomography

“…As anterior-posterior radiograph is still the gold standard to diagnose knee OA, there is a need to develop method to evaluate tibial internal/external rotation on radiographs. In the future, computer-aided method with deep learning algorithm has a potential to evaluate the tibial rotation and to diagnose early-stage knee OA on 2D radiograph [27]. Third, we evaluated knee kinematics under weight-bearing conditions while the subjects stood on both legs.…”

Patient‐specific radiation risk‐based tube current modulation for diagnostic CT

“…This could be achieved by using a deep learning-based reconstruction that utilizes the information from the available topogram(s) and a potential 3D camera image 15 of the patient surface.Such reconstructions based on one or two projections are described in the literature. [16][17][18][19][20] Since the focus of this study is to show the effective dose reduction potential of a riskminimizing TCM, CT reconstructions from a full scan are used instead.…”