Unsupervised learning of a deep neural network for metal artifact correction using dual‐polarity readout gradients

GAN-based metal artifacts region inpainting in brain MRI imaging with reflective registration

BACKGROUND AND OBJECTIVE

Metallic magnetic resonance imaging (MRI) implants can introduce magnetic field distortions, resulting in image distortion, such as bulk shifts and signal-loss artifacts. Metal Artifacts Region Inpainting Network (MARINet), using the symmetry of brain MRI images, has been developed to generate normal MRI images in the image domain and improve image quality.

METHODS

T1-weighted MRI images containing or located near the teeth of 100 patients were collected. A total of 9000 slices were obtained after data augmentation. Then, MARINet based on U-Net with a dual-path encoder was employed to inpaint the artifacts in MRI images. The input of MARINet contains the original image and the flipped registered image, with partial convolution used concurrently. Subsequently, we compared PConv with partial convolution, and GConv with gated convolution, SDEdit using a diffusion model for inpainting the artifact region of MRI images. The mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) for the mask were used to compare the results of these methods. In addition, the artifact masks of clinical MRI images were inpainted by physicians.

RESULTS

MARINet could directly and effectively inpaint the incomplete MRI images generated by masks in the image domain. For the test results of PConv, GConv, SDEdit, and MARINet, the masked MAEs were 0.1938, 0.1904, 0.1876, and 0.1834, respectively, and the masked PSNRs were 17.39, 17.40, 17.49, and 17.60 dB, respectively. The visualization results also suggest that the network can recover the tissue texture, alveolar shape, and tooth contour. Additionally, for clinical artifact MRI images, MARINet completed the artifact region inpainting task more effectively when compared with other models.

CONCLUSIONS

By leveraging the quasi-symmetry of brain MRI images, MARINet can directly and effectively inpaint the metal artifacts in MRI images in the image domain, restoring the tooth contour and detail, thereby enhancing the image quality.

A dual-stage partially interpretable neural network for joint suppression of bSSFP banding and flow artifacts in non-phase-cycled cine imaging

PURPOSE

To develop a partially interpretable neural network for joint suppression of banding and flow artifacts in non-phase-cycled bSSFP cine imaging.

METHODS

A dual-stage neural network consisting of a voxel-identification (VI) sub-network and artifact-suppression (AS) sub-network is proposed. The VI sub-network provides identification of artifacts, which guides artifact suppression and improves interpretability. The AS sub-network reduces banding and flow artifacts. Short-axis cine images of 12 frequency offsets from 28 healthy subjects were used to train and test the dual-stage network. An additional 77 patients were retrospectively enrolled to evaluate its clinical generalizability. For healthy subjects, artifact suppression performance was analyzed by comparison with traditional phase cycling. The partial interpretability provided by the VI sub-network was analyzed via correlation analysis. Generalizability was evaluated for cine obtained with different sequence parameters and scanners. For patients, artifact suppression performance and partial interpretability of the network were qualitatively evaluated by 3 clinicians. Cardiac function before and after artifact suppression was assessed via left ventricular ejection fraction (LVEF).

RESULTS

For the healthy subjects, visual inspection and quantitative analysis found a considerable reduction of banding and flow artifacts by the proposed network. Compared with traditional phase cycling, the proposed network improved flow artifact scores (4.57 ± 0.23 vs 3.40 ± 0.38, P = 0.002) and overall image quality (4.33 ± 0.22 vs 3.60 ± 0.38, P = 0.002). The VI sub-network well identified the location of banding and flow artifacts in the original movie and significantly correlated with the change of signal intensities in these regions. Changes of imaging parameters or the scanner did not cause a significant change of overall image quality relative to the baseline dataset, suggesting a good generalizability. For the patients, qualitative analysis showed a significant improvement of banding artifacts (4.01 ± 0.50 vs 2.77 ± 0.40, P < 0.001), flow artifacts (4.22 ± 0.38 vs 2.97 ± 0.57, P < 0.001), and image quality (3.91 ± 0.45 vs 2.60 ± 0.43, P < 0.001) relative to the original cine. The artifact suppression slightly reduced the LVEF (mean bias = -1.25%, P = 0.01).

CONCLUSIONS

The dual-stage network simultaneously reduces banding and flow artifacts in bSSFP cine imaging with a partial interpretability, sparing the need for sequence modification. The method can be easily deployed in a clinical setting to identify artifacts and improve cine image quality.

The role of AI in prostate MRI quality and interpretation: Opportunities and challenges

Prostate MRI plays an important role in imaging the prostate gland and surrounding tissues, particularly in the diagnosis and management of prostate cancer. With the widespread adoption of multiparametric magnetic resonance imaging in recent years, the concerns surrounding the variability of imaging quality have garnered increased attention. Several factors contribute to the inconsistency of image quality, such as acquisition parameters, scanner differences and interobserver variabilities. While efforts have been made to standardize image acquisition and interpretation via the development of systems, such as PI-RADS and PI-QUAL, the scoring systems still depend on the subjective experience and acumen of humans. Artificial intelligence (AI) has been increasingly used in many applications, including medical imaging, due to its ability to automate tasks and lower human error rates. These advantages have the potential to standardize the tasks of image interpretation and quality control of prostate MRI. Despite its potential, thorough validation is required before the implementation of AI in clinical practice. In this article, we explore the opportunities and challenges of AI, with a focus on the interpretation and quality of prostate MRI.

Superconducting magnet designs and MRI accessibility: A review

Presently, magnetic resonance imaging (MRI) magnets must deliver excellent magnetic field (B₀ ) uniformity to achieve optimum image quality. Long magnets can satisfy the homogeneity requirements but require considerable superconducting material. These designs result in large, heavy, and costly systems that aggravate as field strength increases. Furthermore, the tight temperature tolerance of niobium titanium magnets adds instability to the system and requires operation at liquid helium temperature. These issues are crucial factors in the disparity of MR density and field strength use across the globe. Low-income settings show reduced access to MRI, especially to high field strengths. This article summarizes the proposed modifications to MRI superconducting magnet design and their impact on accessibility, including compact, reduced liquid helium, and specialty systems. Reducing the amount of superconductor inevitably entails shrinking the magnet size, resulting in higher field inhomogeneity. This work also reviews the state-of-the-art imaging and reconstruction methods to overcome this issue. Finally, we summarize the current and future challenges and opportunities in the design of accessible MRI.

Deep learning based unpaired image-to-image translation applications for medical physics: a systematic review

Purpose. There is a growing number of publications on the application of unpaired image-to-image (I2I) translation in medical imaging. However, a systematic review covering the current state of this topic for medical physicists is lacking. The aim of this article is to provide a comprehensive review of current challenges and opportunities for medical physicists and engineers to apply I2I translation in practice.Methods and materials. The PubMed electronic database was searched using terms referring to unpaired (unsupervised), I2I translation, and medical imaging. This review has been reported in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. From each full-text article, we extracted information extracted regarding technical and clinical applications of methods, Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) study type, performance of algorithm and accessibility of source code and pre-trained models.Results. Among 461 unique records, 55 full-text articles were included in the review. The major technical applications described in the selected literature are segmentation (26 studies), unpaired domain adaptation (18 studies), and denoising (8 studies). In terms of clinical applications, unpaired I2I translation has been used for automatic contouring of regions of interest in MRI, CT, x-ray and ultrasound images, fast MRI or low dose CT imaging, CT or MRI only based radiotherapy planning, etc Only 5 studies validated their models using an independent test set and none were externally validated by independent researchers. Finally, 12 articles published their source code and only one study published their pre-trained models.Conclusion. I2I translation of medical images offers a range of valuable applications for medical physicists. However, the scarcity of external validation studies of I2I models and the shortage of publicly available pre-trained models limits the immediate applicability of the proposed methods in practice.

Performance of PROPELLER FSE T2WI in reducing metal artifacts of material porcelain fused to metal crown: a clinical preliminary study

This study aimed to compare MRI quality between conventional fast spin echo T₂ weighted imaging (FSE T₂WI) with periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) FSE T₂WI for patients with various porcelain fused to metal (PFM) crown and analyze the value of PROPELLER technique in reducing metal artifacts. Conventional FSE T₂WI and PROPELLER FSE T₂WI sequences for axial imaging of head were applied in participants with different PFM crowns: cobalt-chromium (Co–Cr) alloy, pure titanium (Ti), gold–palladium (Au–Pd) alloy. Two radiologists evaluated overall image quality of section in PFM using a 5-point scale qualitatively and measured the maximum artifact area and artifact signal-to-noise ratio (SNR) quantitatively. Fifty-nine participants were evaluated. The metal crown with the least artifacts and the optimum image quality shown in conventional FSE T₂WI and PROPELLER FSE T₂WI were in Au–Pd alloy, Ti, and Co–Cr alloy order. PROPELLER FSE T₂WI was superior to conventional FSE T₂WI in improving image quality and reducing artifact area for Co-Cr alloy (17.0 ± 0.2% smaller artifact area, p < 0.001) and Ti (11.6 ± 0.7% smaller artifact area, p = 0.005), but had similar performance compared to FSE T₂WI for Au–Pd alloy. The SNRs of the tongue and masseter muscle were significantly higher on PROPELLER FSE T₂WI compared with conventional FSE T₂WI (tongue: 29.76 ± 8.45 vs. 21.54 ± 9.31, p = 0.007; masseter muscle: 19.11 ± 8.24 vs. 15.26 ± 6.08, p = 0.016). Therefore, the different PFM crown generate varying degrees of metal artifacts in MRI, and the PROPELLER can effectively reduce metal artifacts especially in the PFM crown of Co-Cr alloy.

Suppression of artifact-generating echoes in cine DENSE using deep learning

PURPOSE

To use deep learning for suppression of the artifact-generating T1 -relaxation echo in cine displacement encoding with stimulated echoes (DENSE) for the purpose of reducing the scan time.

METHODS

A U-Net was trained to suppress the artifact-generating T1 -relaxation echo using complementary phase-cycled data as the ground truth. A data-augmentation method was developed that generates synthetic DENSE images with arbitrary displacement-encoding frequencies to suppress the T1 -relaxation echo modulated for a range of frequencies. The resulting U-Net (DAS-Net) was compared with k-space zero-filling as an alternative method. Non-phase-cycled DENSE images acquired in shorter breath-holds were processed by DAS-Net and compared with DENSE images acquired with phase cycling for the quantification of myocardial strain.

RESULTS

The DAS-Net method effectively suppressed the T1 -relaxation echo and its artifacts, and achieved root Mean Square(RMS) error = 5.5 ± 0.8 and structural similarity index = 0.85 ± 0.02 for DENSE images acquired with a displacement encoding frequency of 0.10 cycles/mm. The DAS-Net method outperformed zero-filling (root Mean Square error = 5.8 ± 1.5 vs 13.5 ± 1.5, DAS-Net vs zero-filling, P < .01; and structural similarity index = 0.83 ± 0.04 vs 0.66 ± 0.03, DAS-Net vs zero-filling, P < .01). Strain data for non-phase-cycled DENSE images with DAS-Net showed close agreement with strain from phase-cycled DENSE.

CONCLUSION

The DAS-Net method provides an effective alternative approach for suppression of the artifact-generating T1 -relaxation echo in DENSE MRI, enabling a 42% reduction in scan time compared to DENSE with phase-cycling.

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

This article presents an overview of deep learning (DL) and its applications to function approximation for MR in medicine. The aim of this article is to help readers develop various applications of DL. DL has made a large impact on the literature of many medical sciences, including MR. However, its technical details are not easily understandable for non-experts of machine learning (ML).The first part of this article presents an overview of DL and its related technologies, such as artificial intelligence (AI) and ML. AI is explained as a function that can receive many inputs and produce many outputs. ML is a process of fitting the function to training data. DL is a kind of ML, which uses a composite of many functions to approximate the function of interest. This composite function is called a deep neural network (DNN), and the functions composited into a DNN are called layers. This first part also covers the underlying technologies required for DL, such as loss functions, optimization, initialization, linear layers, non-linearities, normalization, recurrent neural networks, regularization, data augmentation, residual connections, autoencoders, generative adversarial networks, model and data sizes, and complex-valued neural networks.The second part of this article presents an overview of the applications of DL in MR and explains how functions represented as DNNs are applied to various applications, such as RF pulse, pulse sequence, reconstruction, motion correction, spectroscopy, parameter mapping, image synthesis, and segmentation.

Metallic Implants in MRI - Hazards and Imaging Artifacts

BACKGROUND

 Magnetic resonance imaging (MRI) is an examination method for noninvasive soft tissue imaging without the use of ionizing radiation. Metallic implants, however, may pose a risk for the patient and often result in imaging artifacts. Due to the increasing number of implants, reducing these artifacts has become an important goal. In this review, we describe the risks associated with implants and provide the background on how metal-induced artifacts are formed. We review the literature on methods on how to reduce artifacts and summarize our findings.

METHOD

 The literature was searched using PubMed and the keywords "MRI metal artifact reduction", "metallic implants" and "MRI artefacts/artifacts".

RESULTS AND CONCLUSION

 The MRI compatibility of implants has to be evaluated individually. To reduce artifacts, two general approaches were found: a) parameter optimization in standard sequences (echo time, slice thickness, bandwidth) and b) specialized sequences, such as VAT, OMAR, WARP, SEMAC and MAVRIC. These methods reduced artifacts and improved image quality, albeit at the cost of a (sometimes significantly) prolonged scan time. New developments in accelerated imaging will likely shorten the scan time of these methods significantly, such that routine use may become feasible.

KEY POINTS

  · Metallic implants may pose a risk for patients and often cause artifacts.. · Imaging artifacts can be reduced by parameter optimization or special sequences.. · Metal artifacts are reduced with a lower TE, smaller voxel size, larger matrix, and higher bandwidth.. · SPI, STIR, VAT, SEMAC, MAVRIC, and MAVRIC-SL are specialized MR sequences that can reduce artifacts further..

CITATION FORMAT

· Peschke E, Ulloa P, Jansen O et al. Metallic Implants in MRI - Hazards and Imaging Artifacts. Fortschr Röntgenstr 2021; 193: 1285 - 1293.

Dual polarity encoded MRI using high bandwidth radiofrequency pulses for robust imaging with large field inhomogeneity

PURPOSE

The ability to use dual polarity encoded MRI with the missing pulse steady-state free precession (MP-SSFP) sequence is demonstrated to perform robust MRI with low radiofrequency (RF) amplitude, where the field is distorted by embedding metallic screws in an agar phantom. Image-based estimation of the 3D ΔB₀ map and image distortion correction is shown to require ~1 minute to perform.

THEORY AND METHODS

Dual polarity encoded MP-SSFP was implemented at 1.5T and used to image agar phantoms with one stainless steel and one titanium screw embedded inside. A multispectral fast spin-echo acquisition was performed for comparison. Self-consistent ΔB₀ estimation is performed iteratively using a 3D B-spline basis, which is compared to the ΔB₀ estimate generated by the multispectral sequence.

RESULTS

Dual polarity encoded MP-SSFP yields image quality similar to the multispectral sequence used with substantially less imaging time, provided the MP-SSFP experimental parameters are chosen well. The multispectral sequence appears to visualize modestly closer in proximity to the metallic screws used, despite the spectral bins covering the same bandwidth as the pulses used in MP-SSFP. However, MP-SSFP avoids ripple artifacts characteristic of the multispectral sequence. The ΔB₀ estimate generated by MP-SSFP is qualitatively similar to that generated by the multispectral sequence but larger in magnitude.

CONCLUSION

Despite longer processing time compared to multispectral imaging, MP-SSFP yields similar image quality with significantly lower acquisition times in the absence of parallel imaging. The work herein demonstrates the ability to perform 3D ΔB₀ estimation and image correction within a reasonable amount of time, ~1 minute.

Contemporary approaches to high-field magnetic resonance imaging with large field inhomogeneity

Despite its importance as a clinical imaging modality, magnetic resonance imaging remains inaccessible to most of the world's population due to its high cost and infrastructure requirements. Substantial effort is underway to develop portable, low-cost systems able to address MRI access inequality and to enable new uses of MRI such as bedside imaging. A key barrier to development of portable MRI systems is increased magnetic field inhomogeneity when using small polarizing magnets, which degrades image quality through distortions and signal dropout. Many approaches address field inhomogeneity by using a low polarizing field, approximately ten to hundreds of milli-Tesla. At low-field, even a large relative field inhomogeneity of several thousand parts-per-million (ppm) results in resonance frequency dispersion of only 1-2 kHz. Under these conditions, with necessarily wide pulse bandwidths, fast spin-echo sequences may be used at low field with negligible subject heating, and a broad range of other available imaging sequences can be implemented. However, high-field MRI, 1.5 T or greater, can provide substantially improved signal-to-noise ratio and image contrast, so that higher spatial resolution, clinical quality images may be acquired in significantly less time than is necessary at low-field. The challenge posed by small, high-field systems is that the relative field inhomogeneity, still thousands of ppm, becomes tens of kilohertz over the imaging volume. This article describes the physical consequences of field inhomogeneity on established gradient- and spin-echo MRI sequences, and suggests ways to reduce signal dropout and image distortion from field inhomogeneity. Finally, the practicality of currently available image contrasts is reviewed when imaging with a high magnetic field with large inhomogeneity.