Lesion-conditioning of synthetic MRI-derived subtraction-MIPs of the breast using a latent diffusion model.

The purpose of this feasibility study is to investigate if latent diffusion models (LDMs) are capable to generate contrast enhanced (CE) MRI-derived subtraction maximum intensity projections (MIPs) of the breast, which are conditioned by lesions. We trained an LDM with n = 2832 CE-MIPs of breast MRI examinations of n = 1966 patients (median age: 50 years) acquired between the years 2015 and 2020. The LDM was subsequently conditioned with n = 756 segmented lesions from n = 407 examinations, indicating their location and BI-RADS scores. By applying the LDM, synthetic images were generated from the segmentations of an independent validation dataset. Lesions, anatomical correctness, and realistic impression of synthetic and real MIP images were further assessed in a multi-rater study with five independent raters, each evaluating n = 204 MIPs (50% real/50% synthetic images). The detection of synthetic MIPs by the raters was akin to random guessing with an AUC of 0.58. Interrater reliability of the lesion assessment was high both for real (Kendall's W = 0.77) and synthetic images (W = 0.85). A higher AUC was observed for the detection of suspicious lesions (BI-RADS ≥ 4) in synthetic MIPs (0.88 vs. 0.77; p = 0.051). Our results show that LDMs can generate lesion-conditioned MRI-derived CE subtraction MIPs of the breast, however, they also indicate that the LDM tended to generate rather typical or 'textbook representations' of lesions.

Smart forecasting of artifacts in contrast-enhanced breast MRI before contrast agent administration.

OBJECTIVES: To evaluate whether artifacts on contrast-enhanced (CE) breast MRI maximum intensity projections (MIPs) might already be forecast before gadolinium-based contrast agent (GBCA) administration during an ongoing examination by analyzing the unenhanced T1-weighted images acquired before the GBCA injection. MATERIALS AND METHODS: This IRB-approved retrospective analysis consisted of n = 2884 breast CE MRI examinations after intravenous administration of GBCA, acquired with n = 4 different MRI devices at different field strengths (1.5 T/3 T) during clinical routine. CE-derived subtraction MIPs were used to conduct a multi-class multi-reader evaluation of the presence and severity of artifacts with three independent readers. An ensemble classifier (EC) of five DenseNet models was used to predict artifacts for the post-contrast subtraction MIPs, giving as the input source only the pre-contrast T1-weighted sequence. Thus, the acquisition directly preceded the GBCA injection. The area under ROC (AuROC) and diagnostics accuracy scores were used to assess the performance of the neural network in an independent holdout test set (n = 285). RESULTS: After majority voting, potentially significant artifacts were detected in 53.6% (n = 1521) of all breast MRI examinations (age 49.6 ± 12.6 years). In the holdout test set (mean age 49.7 ± 11.8 years), at a specificity level of 89%, the EC could forecast around one-third of artifacts (sensitivity 31%) before GBCA administration, with an AuROC = 0.66. CONCLUSION: This study demonstrates the capability of a neural network to forecast the occurrence of artifacts on CE subtraction data before the GBCA administration. If confirmed in larger studies, this might enable a workflow-blended approach to prevent breast MRI artifacts by implementing in-scan personalized predictive algorithms. CLINICAL RELEVANCE STATEMENT: Some artifacts in contrast-enhanced breast MRI maximum intensity projections might be predictable before gadolinium-based contrast agent injection using a neural network. KEY POINTS: • Potentially significant artifacts can be observed in a relevant proportion of breast MRI subtraction sequences after gadolinium-based contrast agent administration (GBCA). • Forecasting the occurrence of such artifacts in subtraction maximum intensity projections before GBCA administration for individual patients was feasible at 89% specificity, which allowed correctly predicting one in three future artifacts. • Further research is necessary to investigate the clinical value of such smart personalized imaging approaches.

Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI.

The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/mm2 was acquired. From these, 2D MIP images were computed and the left and right breast were cropped out as regions of interest (ROI). The presence of MRI image artifacts on the ROIs was rated by three independent observers. Artifact prevalence in the dataset was 37% (961 out of 2618 images). A DenseNet was trained with a fivefold cross-validation to identify artifacts on these images. In an independent holdout test dataset (n = 350 images) artifacts were detected by the neural network with an area under the precision-recall curve of 0.921 and a positive predictive value of 0.981. Our results show that a deep learning algorithm is capable to identify MRI artifacts in breast DWI-derived MIPs, which could help to improve quality assurance approaches for DWI sequences of breast examinations in the future.

Clinically compatible subject-specific dynamic parallel transmit pulse design for homogeneous fat saturation and water-excitation at 7T: Proof-of-concept for CEST MRI of the brain.

PURPOSE: To evaluate the benefits and challenges of dynamic parallel transmit (pTx) pulses for fat saturation (FS) and water-excitation (WE), in the context of CEST MRI. METHODS: "Universal" kT -points (for FS) and spiral non-selective (for WE) trajectories were optimized offline for flip angle (FA) homogeneity. Routines to optimize the pulse shape online, based on the subject's fields maps, were implemented (target FA of 110°/0° for FS, 0°/5° for WE at fat/water frequencies). The pulses were inserted in a CEST sequence with a pTx readout. The different fat suppression schemes and their effects on CEST contrasts were compared in 12 volunteers at 7T. RESULTS: With a 25%-shorter pulse duration, pTx FS largely improved the FA homogeneity (root-mean-square-error (RMSE) = 12.3° vs. 53.4° with circularly-polarized mode, at the fat frequency). However, the spectral selectivity was degraded mainly in the cerebellum and close to the sinuses (RMSE = 5.8° vs. 0.2° at the water frequency). Similarly, pTx WE showed a trade-off between FA homogeneity and spectral selectivity compared to pTx non-selective pulses (RMSE = 0.9° and 1.1° at the fat and water frequencies, vs. 4.6° and 0.5°). In the brain, CEST metrics were reduced by up to 31.9% at -3.3 ppm with pTx FS, suggesting a mitigated lipid-induced bias. CONCLUSION: This clinically compatible implementation of dynamic pTx pulses improved the fat suppression homogeneity at 7T taking into account the subject-specific B0 heterogeneities online. This study highlights the lipid-induced biases on the CEST z-spectrum. The results are promising for body applications where B0 heterogeneities and fat are more substantial.

7 tricks for 7 T CEST: Improving the reproducibility of multipool evaluation provides insights into the effects of age and the early stages of Parkinson's disease.

The objective of the current study was to optimize the postprocessing pipeline of 7 T chemical exchange saturation transfer (CEST) imaging for reproducibility and to prove this optimization for the detection of age differences and differences between patients with Parkinson's disease versus normal subjects. The following 7 T CEST MRI experiments were analyzed: repeated measurements of a healthy subject, subjects of two age cohorts (14 older, seven younger subjects), and measurements of 12 patients with Parkinson's disease. A slab-selective, B 1 + -homogeneous parallel transmit protocol was used. The postprocessing, consisting of motion correction, smoothing, B 0 -correction, normalization, denoising, B 1 + -correction and Lorentzian fitting, was optimized regarding the intrasubject and intersubject coefficient of variation (CoV) of the amplitudes of the amide pool and the aliphatic relayed nuclear Overhauser effect (rNOE) pool within the brain. Seven "tricks" for postprocessing accomplished an improvement of the mean voxel CoV of the amide pool and the aliphatic rNOE pool amplitudes of less than 5% and 3%, respectively. These postprocessing steps are: motion correction with interpolation of the motion of low-signal offsets (1) using the amide pool frequency offset image as reference (2), normalization of the Z-spectrum using the outermost saturated measurements (3), B 0 correction of the Z-spectrum with moderate spline smoothing (4), denoising using principal component analysis preserving the 11 highest intensity components (5), B 1 + correction using a linear fit (6) and Lorentzian fitting using the five-pool fit model (7). With the optimized postprocessing pipeline, a significant age effect in the amide pool can be detected. Additionally, for the first time, an aliphatic rNOE contrast between subjects with Parkinson's disease and age-matched healthy controls in the substantia nigra is detected. We propose an optimized postprocessing pipeline for CEST multipool evaluation. It is shown that by the use of these seven "tricks", the reproducibility and, thus, the statistical power of a CEST measurement, can be greatly improved and subtle changes can be detected.

Linear projection-based chemical exchange saturation transfer parameter estimation.

Isolated evaluation of multiparametric in vivo chemical exchange saturation transfer (CEST) MRI often requires complex computational processing for both correction of B0 and B1 inhomogeneity and contrast generation. For that, sufficiently densely sampled Z-spectra need to be acquired. The list of acquired frequency offsets largely determines the total CEST acquisition time, while potentially representing redundant information. In this work, a linear projection-based multiparametric CEST evaluation method is introduced that offers fast B0 and B1 inhomogeneity correction, contrast generation and feature selection for CEST data, enabling reduction of the overall measurement time. To that end, CEST data acquired at 7 T in six healthy subjects and in one brain tumor patient were conventionally evaluated by interpolation-based inhomogeneity correction and Lorentzian curve fitting. Linear regression was used to obtain coefficient vectors that directly map uncorrected data to corrected Lorentzian target parameters. L1-regularization was applied to find subsets of the originally acquired CEST measurements that still allow for such a linear projection mapping. The linear projection method allows fast and interpretable mapping from acquired raw data to contrast parameters of interest, generalizing from healthy subject training data to unseen healthy test data and to the tumor patient dataset. The L1-regularization method shows that a fraction of the acquired CEST measurements is sufficient to preserve tissue contrasts, offering up to a 2.8-fold reduction of scan time. Similar observations as for the 7-T data can be made for data from a clinical 3-T scanner. Being a fast and interpretable computation step, the proposed method is complementary to neural networks that have recently been employed for similar purposes. The scan time acceleration offered by the L1-regularization ("CEST-LASSO") constitutes a step towards better applicability of multiparametric CEST protocols in a clinical context.

Automated artifact detection in abbreviated dynamic contrast-enhanced (DCE) MRI-derived maximum intensity projections (MIPs) of the breast.

OBJECTIVES: To automatically detect MRI artifacts on dynamic contrast-enhanced (DCE) maximum intensity projections (MIPs) of the breast using deep learning. METHODS: Women who underwent clinically indicated breast MRI between October 2015 and December 2019 were included in this IRB-approved retrospective study. We employed two convolutional neural network architectures (ResNet and DenseNet) to detect the presence of artifacts on DCE MIPs of the left and right breasts. Networks were trained on images acquired up to and including the year 2018 using a 5-fold cross-validation (CV). Ensemble classifiers were built with the resulting CV models and applied to an independent holdout test dataset, which was formed by images acquired in 2019. RESULTS: Our study sample contained 2265 examinations from 1794 patients (median age at first acquisition: 50 years [IQR: 17 years]), corresponding to 1827 examinations of 1378 individuals in the training dataset and 438 examinations of 416 individuals in the holdout test dataset with a prevalence of image-level artifacts of 53% (1951/3654 images) and 43% (381/876 images), respectively. On the holdout test dataset, the ResNet and DenseNet ensembles demonstrated an area under the ROC curve of 0.92 and 0.94, respectively. CONCLUSION: Neural networks are able to reliably detect artifacts that may impede the diagnostic assessment of MIPs derived from DCE subtraction series in breast MRI. Future studies need to further explore the potential of such neural networks to complement quality assurance and improve the application of DCE MIPs in a clinical setting, such as abbreviated protocols. KEY POINTS: • Deep learning classifiers are able to reliably detect MRI artifacts in dynamic contrast-enhanced protocol-derived maximum intensity projections of the breast. • Automated quality assurance of maximum intensity projections of the breast may be of special relevance for abbreviated breast MRI, e.g., in high-throughput settings, such as cancer screening programs.

Brain tissues have single-voxel signatures in multi-spectral MRI.

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

The traveling heads 2.0: Multicenter reproducibility of quantitative imaging methods at 7 Tesla.

OBJECT: This study evaluates inter-site and intra-site reproducibility at ten different 7 T sites for quantitative brain imaging. MATERIAL AND METHODS: Two subjects - termed the "traveling heads" - were imaged at ten different 7 T sites with a harmonized quantitative brain MR imaging protocol. In conjunction with the system calibration, MP2RAGE, QSM, CEST and multi-parametric mapping/relaxometry were examined. RESULTS: Quantitative measurements with MP2RAGE showed very high reproducibility across sites and subjects, and errors were in concordance with previous results and other field strengths. QSM had high inter-site reproducibility for relevant subcortical volumes. CEST imaging revealed systematic differences between the sites, but reproducibility was comparable to results in the literature. Relaxometry had also very high agreement between sites, but due to the high sensitivity, differences caused by different applications of the B1 calibration of the two RF coil types used were observed. CONCLUSION: Our results show that quantitative brain imaging can be performed with high reproducibility at 7 T and with similar reliability as found at 3 T for multicenter studies of the supratentorial brain.

Whole-brain quantitative CEST MRI at 7T using parallel transmission methods and B1+ correction.

PURPOSE: To enable whole-brain quantitative CEST MRI at ultra-high magnetic field strengths (B0 ≥ 7T) within short acquisition times. METHODS: Multiple interleaved mode saturation (MIMOSA) was combined with fast online-customized (FOCUS) parallel transmission (pTx) excitation pulses and B1+ correction to achieve homogenous whole-brain coverage. Examinations of 13 volunteers were performed on a 7T MRI system with 3 different types of pulse sequences: (1) saturation in circular polarized (CP) mode and CP mode readout, (2) MIMOSA and CP readout, and (3) MIMOSA and FOCUS readout. For comparison, the inverse magnetic transfer ratio metric for relayed nuclear Overhauser effect and amide proton transfer were calculated. To investigate the number of required acquisitions for a good B1+ correction, 4 volunteers were measured with 6 different B1 amplitudes. Finally, time point repeatability was investigated for 6 volunteers. RESULTS: MIMOSA FOCUS sequence using B1+ correction, with both single and multiple points, reduced inhomogeneity of the CEST contrasts around the occipital lobe and cerebellum. Results indicate that the most stable inter-subject coefficient of variation was achieved using the MIMOSA FOCUS sequence. Time point repeatability of MIMOSA FOCUS with single-point B1+ correction showed a maximum coefficient of variation below 8% for 3 measurements in a single volunteer. CONCLUSION: A combination of MIMOSA FOCUS with a single-point B1+ correction can be used to achieve quantitative CEST measurements at ultra-high magnetic field strengths. Compared to previous B1+ correction methods, acquisition time can be reduced as additional scans required for B1+ correction can be omitted.

Multiple interleaved mode saturation (MIMOSA) for B1+ inhomogeneity mitigation in chemical exchange saturation transfer.

PURPOSE: To mitigate B1+ inhomogeneity in quantitative CEST MRI at ultra-high magnetic field strengths (B0 ≥ 7 Tesla) using a parallel transmit system. METHODS: Multiple interleaved mode saturation employs interleaving of 2 complementary phase sets during the saturation pulse train. Phase differences of 45° (first mode) and 90° (second mode) between 2 adjacent transmitter coil channels are used. The influence of the new saturation scheme on the CEST contrast was analyzed using Bloch-McConnell simulations. The presented method was verified in phantom and in vivo measurements of the healthy human brain. The relayed nuclear Overhauser effect was evaluated, and the inverse magnetic transfer ratio metric was calculated. Results were compared to a published B1+ correction method. All measurements were conducted on a whole-body 7 Tesla MRI system using an 8 transmitter and 32 receiver channel head coil. RESULTS: Simulations showed that the inverse magnetic transfer ratio metric contrast of relayed nuclear Overhauser effect shows a smaller dependency on the relative amplitudes of the 2 different modes than the contrasts of Cr and amide proton transfer. Measurements of an egg white phantom showed markedly improved homogeneity compared to the uncorrected inverse magnetic transfer ratio metric (relayed nuclear Overhauser effect) images and slightly improved results compared to B1+ corrected images. In vivo multiple interleaved mode saturation images showed similar contrast compared to B1+ corrected images. CONCLUSION: Multiple interleaved mode saturation can be used as a simple method to mitigate B1+ inhomogeneity effects in CEST MRI at ultra-high magnetic field strengths. Compared to previous B1+ correction methods, acquisition time can be reduced because an additional scan, usually required for B1+ correction, can be omitted.