Dataset Information

Super-resolution head and neck MRA using deep machine learning.

ABSTRACT:

Purpose

To probe the feasibility of deep learning-based super-resolution (SR) reconstruction applied to nonenhanced MR angiography (MRA) of the head and neck.

Methods

High-resolution 3D thin-slab stack-of-stars quiescent interval slice-selective (QISS) MRA of the head and neck was obtained in eight subjects (seven healthy volunteers, one patient) at 3T. The spatial resolution of high-resolution ground-truth MRA data in the slice-encoding direction was reduced by factors of 2 to 6. Four deep neural network (DNN) SR reconstructions were applied, with two based on U-Net architectures (2D and 3D) and two (2D and 3D) consisting of serial convolutions with a residual connection. SR images were compared to ground-truth high-resolution data using Dice similarity coefficient (DSC), structural similarity index measure (SSIM), arterial diameter, and arterial sharpness measurements. Image review of the optimal DNN SR reconstruction was done by two experienced neuroradiologists.

Results

DNN SR of up to twofold and fourfold lower-resolution (LR) input volumes provided images that resembled those of the original high-resolution ground-truth volumes for intracranial and extracranial arterial segments, and improved DSC, SSIM, arterial diameters, and arterial sharpness relative to LR volumes (P < .001). The 3D DNN SR outperformed 2D DNN SR reconstruction. According to two neuroradiologists, 3D DNN SR reconstruction consistently improved image quality with respect to LR input volumes (P < .001).

Conclusion

DNN-based SR reconstruction of 3D head and neck QISS MRA offers the potential for up to fourfold reduction in acquisition time for neck vessels without the need to commensurately sacrifice spatial resolution.

SUBMITTER: Koktzoglou I

PROVIDER: S-EPMC8034362 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Super-resolution head and neck MRA using deep machine learning.

Koktzoglou Ioannis I Huang Rong R Ankenbrandt William J WJ Walker Matthew T MT Edelman Robert R RR

Magnetic resonance in medicine 20210222 1

<h4>Purpose</h4>To probe the feasibility of deep learning-based super-resolution (SR) reconstruction applied to nonenhanced MR angiography (MRA) of the head and neck.<h4>Methods</h4>High-resolution 3D thin-slab stack-of-stars quiescent interval slice-selective (QISS) MRA of the head and neck was obtained in eight subjects (seven healthy volunteers, one patient) at 3T. The spatial resolution of high-resolution ground-truth MRA data in the slice-encoding direction was reduced by factors of 2 to 6. ...[more]

PMID: 33619802

Similar Datasets

Project description:PurposeTo 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.MethodsWe 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 (κ) evaluated interreader reliability.ResultsDeepResolve 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 (κ = 0.73).ConclusionDeepResolve 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:Digital phantoms are important tools for optimization and evaluation of x-ray imaging systems, and should ideally reflect the 3D structure of human anatomy and its potential variability. In addition, they need to include a good level of detail at a high enough spatial resolution to accurately model the continuous nature of the human anatomy. A pipeline to increase the spatial resolution of patient-based digital breast phantoms that can be used for computer simulations of breast imaging is proposed. Given a tomographic breast image of finite resolution, the proposed methods can generate a phantom and increase its resolution at will, not only simply through super-sampling, but also by generating additional random glandular details to account for glandular edges and strands to compensate for those that may have not been detected in the original image due to the limited spatial resolution of the imaging system used. The proposed algorithms use supervised learning to predict the loss in glandularity due to limited resolution, and then to realistically recover this loss by learning the mapping between low and high resolution images. They were trained on high-resolution synchrotron images (detector pixel size 60 ?m) reconstructed at seven voxel dimensions (60 ?m-480 ?m), and applied to patient images acquired with a clinical breast CT system (detector pixel size 194 ?m) to generate super-resolution phantoms (voxel sizes 68 ?m). Several evaluations were made to assess the appropriateness of the developed methods, both with the synchrotron (relative prediction error 0.010??±??0.004, recovering accuracy 0.95??±??0.04), and with the clinical images (average glandularity error at 194 ?m: 0.15%??±??0.12%). Finally, a breast radiologist assessed the realism of the developed phantoms by blindly comparing original and phantom images, resulting in not being able to distinguish the real from the phantom images. In conclusion, the proposed method can generate super-resolution phantoms from tomographic breast patient images that can be used for future computer simulations for optimization of new breast imaging technologies.

Project description:PurposeThis study proposes a cascaded network model for generating high-resolution doses (i.e., a 1 mm grid) from low-resolution doses (i.e., ≥3 mm grids) with reduced computation time.MethodsUsing the anisotropic analytical algorithm with three grid sizes (1, 3, and 5 mm) and the Acuros XB algorithm with two grid sizes (1 and 3 mm), dose distributions were calculated for volumetric modulated arc therapy plans for 73 prostate cancer patients. Our cascaded network model consisted of a hierarchically densely connected U-net (HD U-net) and a residual dense network (RDN), which were trained separately following a two-dimensional slice-by-slice procedure. The first network (HD U-net) predicted the downsampled high-resolution dose (generated through bicubic downsampling of the baseline high-resolution dose) using the low-resolution dose; subsequently, the second network (RDN) predicted the high-resolution dose from the output of the first network. Further, the predicted high-resolution dose was converted to its absolute value. We quantified the network performance using the spatial/dosimetric parameters (dice similarity coefficient, mean dose, maximum dose, minimum dose, homogeneity index, conformity index, and V95%, V70%, V50%, and V30%) for the low-resolution and predicted high-resolution doses relative to the baseline high-resolution dose. Gamma analysis (between the baseline dose and the low-resolution dose/predicted high-resolution dose) was performed with a 2%/2 mm criterion and 10% threshold.ResultsThe average computation time to predict a high-resolution axial dose plane was <0.02 s. The dice similarity coefficient values for the predicted doses were closer to 1 when compared to those for the low-resolution doses. Most of the dosimetric parameters for the predicted doses agreed more closely with those for the baseline than for the low-resolution doses. In most of the parameters, no significant differences (p-value of >0.05) between the baseline and predicted doses were observed. The gamma passing rates for the predicted high-resolution does were higher than those for the low-resolution doses.ConclusionThe proposed model accurately predicted high-resolution doses for the same dose calculation algorithm. Our model uses only dose data as the input without additional data, which provides advantages of convenience to user over other dose super-resolution methods.

Project description:ObjectiveTo assess the accuracy of deep learning reconstruction (DLR) technique on synthetic MRI (SyMRI) including T2 measurements and diagnostic performance of DLR synthetic MRI (SyMRIDL) in patients with knee osteoarthritis (KOA) using conventional MRI as standard reference.Materials and methodsThis prospective study recruited 36 volunteers and 70 patients with suspected KOA from May to October 2023. DLR and non-DLR synthetic T2 measurements (T2-SyMRIDL, T2-SyMRI) for phantom and in vivo knee cartilage were compared with multi-echo fast-spin-echo (MESE) sequence acquired standard T2 values (T2MESE). The inter-reader agreement on qualitative evaluation of SyMRIDL and the positive percent agreement (PPA) and negative percentage agreement (NPA) were analyzed using routine images as standard diagnosis.ResultsDLR significantly narrowed the quantitative differences between T2-SyMRIDL and T2MESE for 0.8 ms with 95% LOA [-5.5, 7.1]. The subjective assessment between DLR synthetic MR images and conventional MRI was comparable (all p > 0.05); Inter-reader agreement for SyMRIDL and conventional MRI was substantial to almost perfect with values between 0.62 and 0.88. SyMRIDL MOAKS had substantial inter-reader agreement and high PPA/NPA values (95%/99%) using conventional MRI as standard reference. Moreover, T2-SyMRIDL measurements instead of non-DLR ones significantly differentiated normal-appearing from injury-visible cartilages.ConclusionDLR synthetic knee MRI provided both weighted images for clinical diagnosis and accurate T2 measurements for more confidently identifying early cartilage degeneration from normal-appearing cartilages.Critical relevance statementOne-acquisition synthetic MRI based on deep learning reconstruction provided an accurate quantitative T2 map and morphologic images in relatively short scan time for more confidently identifying early cartilage degeneration from normal-appearing cartilages compared to the conventional morphologic knee sequences.Key pointsDeep learning reconstruction (DLR) synthetic knee cartilage T2 values showed no difference from conventional ones. DLR synthetic T1-, proton density-, STIR-weighted images had high positive percent agreement and negative percentage agreement using MRI OA Knee Score features. DLR synthetic T2 measurements could identify early cartilage degeneration from normal-appearing ones.

Dataset Information

Super-resolution head and neck MRA using deep machine learning.

Purpose

Methods

Results

Conclusion

Publications

Super-resolution head and neck MRA using deep machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets