Dataset Information

Super-resolution Reconstruction MRI Application in Fetal Neck Masses and Congenital High Airway Obstruction Syndrome

ABSTRACT:

Objective

Reliable airway patency diagnosis in fetal tracheolaryngeal obstruction is crucial to select and plan ex utero intrapartum treatment (EXIT) surgery. We compared the clinical utility of magnetic resonance imaging (MRI) super-resolution reconstruction (SRR) of the trachea, which can mitigate unpredictable fetal motion effects, with standard 2-dimensional (2D) MRI for airway patency diagnosis and assessment of fetal neck mass anatomy.

Study Design

A single-center case series of 7 consecutive singleton pregnancies with complex upper airway obstruction (2013-2019).

Setting

A tertiary fetal medicine unit performing EXIT surgery.

Methods

MRI SRR of the trachea was performed involving rigid motion correction of acquired 2D MRI slices combined with robust outlier detection to reconstruct an isotropic high-resolution volume. SRR, 2D MRI, and paired data were blindly assessed by 3 radiologists in 3 experimental rounds.

Results

Airway patency was correctly diagnosed in 4 of 7 cases (57%) with 2D MRI as compared with 2 of 7 cases (29%) with SRR alone or paired 2D MRI and SRR. Radiologists were more confident (P = .026) in airway patency diagnosis when using 2D MRI than SRR. Anatomic clarity was higher with SRR (P = .027) or paired data (P = .041) in comparison with 2D MRI alone. Radiologists detected further anatomic details by using paired images versus 2D MRI alone (P < .001). Cognitive load, as assessed by the NASA Task Load Index, was increased with paired or SRR data in comparison with 2D MRI.

Conclusion

The addition of SRR to 2D MRI does not increase fetal airway patency diagnostic accuracy but does provide improved anatomic information, which may benefit surgical planning of EXIT procedures.

SUBMITTER: Mufti N

PROVIDER: S-EPMC8549475 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PURPOSE:To develop a super-resolution technique using convolutional neural networks for generating thin-slice knee MR images from thicker input slices, and compare this method with alternative through-plane interpolation methods. METHODS:We implemented a 3D convolutional neural network entitled DeepResolve to learn residual-based transformations between high-resolution thin-slice images and lower-resolution thick-slice images at the same center locations. DeepResolve was trained using 124 double echo in steady-state (DESS) data sets with 0.7-mm slice thickness and tested on 17 patients. Ground-truth images were compared with DeepResolve, clinically used tricubic interpolation, and Fourier interpolation methods, along with state-of-the-art single-image sparse-coding super-resolution. Comparisons were performed using structural similarity, peak SNR, and RMS error image quality metrics for a multitude of thin-slice downsampling factors. Two musculoskeletal radiologists ranked the 3 data sets and reviewed the diagnostic quality of the DeepResolve, tricubic interpolation, and ground-truth images for sharpness, contrast, artifacts, SNR, and overall diagnostic quality. Mann-Whitney U tests evaluated differences among the quantitative image metrics, reader scores, and rankings. Cohen's Kappa (?) evaluated interreader reliability. RESULTS:DeepResolve had significantly better structural similarity, peak SNR, and RMS error than tricubic interpolation, Fourier interpolation, and sparse-coding super-resolution for all downsampling factors (p?<?.05, except 4?×?and 8?×?sparse-coding super-resolution downsampling factors). In the reader study, DeepResolve significantly outperformed (p?<?.01) tricubic interpolation in all image quality categories and overall image ranking. Both readers had substantial scoring agreement (??=?0.73). CONCLUSION:DeepResolve was capable of resolving high-resolution thin-slice knee MRI from lower-resolution thicker slices, achieving superior quantitative and qualitative diagnostic performance to both conventionally used and state-of-the-art methods.

Project description:Spatial resolution plays a critically important role in MRI for the precise delineation of the imaged tissues. Unfortunately, acquisitions with high spatial resolution require increased imaging time, which increases the potential of subject motion, and suffers from reduced signal-to-noise ratio (SNR). Super-resolution reconstruction (SRR) has recently emerged as a technique that allows for a trade-off between high spatial resolution, high SNR, and short scan duration. Deconvolution-based SRR has recently received significant interest due to the convenience of using the image space. The most critical factor to succeed in deconvolution is the accuracy of the estimated blur kernels that characterize how the image was degraded in the acquisition process. Current methods use handcrafted filters, such as Gaussian filters, to approximate the blur kernels, and have achieved promising SRR results. As the image degradation is complex and varies with different sequences and scanners, handcrafted filters, unfortunately, do not necessarily ensure the success of the deconvolution. We sought to develop a technique that enables accurately estimating blur kernels from the image data itself. We designed a deep architecture that utilizes an adversarial scheme with a generative neural network against its degradation counterparts. This design allows for the SRR tailored to an individual subject, as the training requires the scan-specific data only, i.e., it does not require auxiliary datasets of high-quality images, which are practically challenging to obtain. With this technique, we achieved high-quality brain MRI at an isotropic resolution of 0.125 cubic mm with six minutes of imaging time. Extensive experiments on both simulated low-resolution data and clinical data acquired from ten pediatric patients demonstrated that our approach achieved superior SRR results as compared to state-of-the-art deconvolution-based methods, while in parallel, at substantially reduced imaging time in comparison to direct high-resolution acquisitions.