This study aims at assessing approaches for generating high-resolution magnetic resonance imaging- (MRI-) based synthetic computed tomography (sCT) images suitable for orthopedic care using a deep learning model trained on low-resolution computed tomography (CT) data. To that end, paired MRI and CT data of three anatomical regions were used: high-resolution knee and ankle data, and low-resolution hip data. Four experiments were conducted to investigate the impact of low-resolution training CT data on sCT generation and to find ways to train models on low-resolution data while providing high-resolution sCT images. Experiments included resampling of the training data or augmentation of the low-resolution data with high-resolution data. Training sCT generation models using low-resolution CT data resulted in blurry sCT images. By resampling the MRI/CT pairs before the training, models generated sharper images, presumably through an increase in the MRI/CT mutual information. Alternatively, augmenting the low-resolution with high-resolution data improved sCT in terms of mean absolute error proportionally to the amount of high-resolution data. Overall, the morphological accuracy was satisfactory as assessed by an average intermodal distance between joint centers ranging from 0.7 to 1.2 mm and by an average intermodal root-mean-squared distances between bone surfaces under 0.7 mm. Average dice scores ranged from 79.8% to 87.3% for bony structures. To conclude, this paper proposed approaches to generate high-resolution sCT suitable for orthopedic care using low-resolution data. This can generalize the use of sCT for imaging the musculoskeletal system, paving the way for an MR-only imaging with simplified logistics and no ionizing radiation.

Download full-text PDF

Source
http://dx.doi.org/10.1002/jor.25707DOI Listing

Publication Analysis

Top Keywords

low-resolution data
16
data
13
sct images
12
high-resolution data
12
magnetic resonance
8
high-resolution
8
generating high-resolution
8
synthetic computed
8
computed tomography
8
sct
8

Similar Publications

Single-molecule localization microscopy (SMLM) can decipher fine details that are otherwise impossible using diffraction-limited microscopy. Often, the reconstructed super-resolved images suffer from noise, strong background and are prone to false detections that may impact quantitative imaging. To overcome these limitations, we propose a technique (corrSMLM) that recognizes and detects fortunate molecules (molecules with long blinking cycles) from the recorded data.

View Article and Find Full Text PDF

High-throughput DNA transformation techniques are invaluable when generating high-diversity mutant libraries, a cornerstone of successful protein engineering. However, transformation efficiencies have a direct correlation with the probability of introducing multiple DNA molecules into each cell, although reliable library screenings require cells that contain a single unique genotype. Thus, transformation methods that yield a high multiplicity of transformations are unsuitable for high-diversity library screenings.

View Article and Find Full Text PDF

Quantification of cyanobacterial CO fixation rates is vital to determining their potential as industrial strains in a circular bioeconomy. Currently, however, CO fixation rates are most often determined through indirect and/or low-resolution methods, resulting in an incomplete picture of both dynamic behaviors and total carbon fixation potential. To address this, we developed the "Automated Carbon and CO Experimental Sampling System" (ACCESS); a low-cost system for in situ off-gas analysis that supports the automated acquisition of high-resolution volumetric CO uptake rates from multiple cyanobacterial cultures in parallel.

View Article and Find Full Text PDF

The recent surge in artificial intelligence (AI) advancements has been driven by the availability of open datasets for model development and evaluation. However, in the field of earth sciences, particularly in digital rock physics applications, open data remains scarce. To bridge this gap, we introduce a dataset comprising 16 rock samples from the Brazilian pre-salt region, available in both low resolution (48 μm - 64 μm) and high resolution (6 μm - 8 μm).

View Article and Find Full Text PDF

The increasing demand for high spatial resolution in remote sensing has underscored the need for super-resolution (SR) algorithms that can upscale low-resolution (LR) images to high-resolution (HR) ones. To address this, we present SEN2NAIP, a novel and extensive dataset explicitly developed to support SR model training. SEN2NAIP comprises two main components.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!