MR Fingerprinting for Contrast Agent-free and Quantitative Characterization of Focal Liver Lesions

Purpose To evaluate the feasibility of liver MR fingerprinting (MRF) for quantitative characterization and diagnosis of focal liver lesions. Materials and Methods This single-site, prospective study included 89 participants (mean age, 62 years ± 15 [SD]; 45 women, 44 men) with various focal liver lesions who underwent MRI between October 2021 and August 2022. The participants underwent routine clinical MRI, non-contrast-enhanced liver MRF, and reference quantitative MRI with a 1.5-T MRI scanner. The bias and repeatability of the MRF measurements were assessed using linear regression, Bland-Altman plots, and coefficients of variation. The diagnostic capability of MRF-derived T1, T2, T2*, proton density fat fraction (PDFF), and a combination of these metrics to distinguish benign from malignant lesions was analyzed according to the area under the receiver operating characteristic curve (AUC). Results Liver MRF measurements showed moderate to high agreement with reference measurements (intraclass correlation = 0.94, 0.77, 0.45, and 0.61 for T1, T2, T2*, and PDFF, respectively), with underestimation of T2 values (mean bias in lesion = -0.5%, -29%, 5.8%, and -8.2% for T1, T2, T2*, and PDFF, respectively). The median coefficients of variation for repeatability of T1, T2, and T2* values were 2.5% (IQR, 3.6%), 3.1% (IQR, 5.6%), and 6.6% (IQR, 13.9%), respectively. After considering multicollinearity, a combination of MRF measurements showed a high diagnostic performance in differentiating benign from malignant lesions (AUC = 0.92 [95% CI: 0.86, 0.98]). Conclusion Liver MRF enabled the quantitative characterization of various focal liver lesions in a single breath-hold acquisition. Keywords: MR Imaging, Abdomen/GI, Liver, Imaging Sequences, Technical Aspects, Tissue Characterization, Technology Assessment, Diagnosis, Liver Lesions, MR Fingerprinting, Quantitative Characterization Supplemental material is available for this article. © RSNA, 2023.

Myocardial Fibrosis in Congenital Heart Disease and the Role of MRI

Progress in the field of congenital heart surgery over the last century can only be described as revolutionary. Recent improvements in patient outcomes have been achieved through refinements in perioperative care. In the current and future eras, the preservation and restoration of myocardial health, beginning with the monitoring of tissue remodeling, will be central to improving cardiac outcomes. Visualization and quantification of fibrotic myocardial remodeling is one of the greatest assets that cardiac MRI brings to the field of cardiology, and its clinical use within the field of congenital heart disease (CHD) has been an area of particular interest in the last few decades. This review summarizes the physical underpinnings of myocardial tissue characterization in CHD, with an emphasis on T1 parametric mapping and late gadolinium enhancement. It describes methods and suggestions for obtaining images, extracting quantitative and qualitative data, and interpreting the results for children and adults with CHD. The tissue characterization observed in different lesions is used to examine the causes and pathomechanisms of fibrotic remodeling in this population. Similarly, the clinical consequences of elevated imaging biomarkers of fibrosis on patient health and outcomes are explored. Keywords: Pediatrics, MR Imaging, Cardiac, Heart, Congenital, Tissue Characterization, Congenital Heart Disease, Cardiac MRI, Parametric Mapping, Fibrosis, Late Gadolinium Enhancement © RSNA, 2023.

A Deep Learning Segmentation Pipeline for Cardiac T1 Mapping Using MRI Relaxation-based Synthetic Contrast Augmentation

PURPOSE

To design and evaluate an automated deep learning method for segmentation and analysis of cardiac MRI T1 maps with use of synthetic T1-weighted images for MRI relaxation-based contrast augmentation.

MATERIALS AND METHODS

This retrospective study included MRI scans acquired between 2016 and 2019 from 100 patients (mean age ± SD, 55 years ± 13; 72 men) across various clinical abnormalities with use of a modified Look-Locker inversion recovery, or MOLLI, sequence to quantify native T1 (T1_native), postcontrast T1 (T1_post), and extracellular volume (ECV). Data were divided into training (n = 60) and internal (n = 40) test subsets. "Synthetic" T1-weighted images were generated from the T1 exponential inversion-recovery signal model at a range of optimal inversion times, yielding high blood-myocardium contrast, and were used for contrast-based image augmentation during training and testing of a convolutional neural network for myocardial segmentation. Automated segmentation, T1, and ECV were compared with experts with use of Dice similarity coefficients (DSCs), correlation coefficients, and Bland-Altman analysis. An external test dataset (n = 147) was used to assess model generalization.

RESULTS

Internal testing showed high myocardial DSC relative to experts (0.81 ± 0.08), which was similar to interobserver DSC (0.81 ± 0.08). Automated segmental measurements strongly correlated with experts (T1_native, R = 0.87; T1_post, R = 0.91; ECV, R = 0.92), which were similar to interobserver correlation (T1_native, R = 0.86; T1_post, R = 0.94; ECV, R = 0.95). External testing showed strong DSC (0.80 ± 0.09) and T1_native correlation (R = 0.88) between automatic and expert analysis.

CONCLUSION

This deep learning method leveraging synthetic contrast augmentation may provide accurate automated T1 and ECV analysis for cardiac MRI data acquired across different abnormalities, centers, scanners, and T1 sequences.Keywords: MRI, Cardiac, Tissue Characterization, Segmentation, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms, Supervised Learning Supplemental material is available for this article. © RSNA, 2022.

Layer-specific Strain Analysis with Cardiac MRI Feature Tracking in Acute Myocarditis

PURPOSE

To evaluate the diagnostic performance of layer-specific cardiac MRI feature-tracking (FT) strain analysis in patients with acute myocarditis.

MATERIALS AND METHODS

Seventy patients (mean age, 43 years ± 19 [SD]; 46 men) with clinically defined acute myocarditis and 42 healthy controls who underwent cardiac MRI from March 2014 to November 2018 were retrospectively analyzed. FT-based left ventricular peak systolic global longitudinal strain (GLS) and global circumferential strain (GCS) were assessed at subendocardial, midmyocardial, and subepicardial layers. The 2018 Lake Louise criteria (LLC) were assessed. Patients with myocarditis were dichotomized into two groups: those with preserved and those with reduced ejection fraction. For statistical analysis, unpaired t test, one-way analysis of variance, Pearson correlation, and receiver operating characteristic analysis were used.

RESULTS

GLS and GCS values of all layers (eg, midmyocardial GCS: -21.3% ± 5.5 vs -28.0% ± 4.3; P < .001) were impaired in patients with myocarditis compared with controls. Only subepicardial GLS (-20.0% ± 3.3 vs -17.5% ± 3.3; P < .001) and midmyocardial GCS values (-28.0% ± 4.3 vs -23.1% ± 4.3; P < .001) could differentiate between controls and patients with preserved ejection fraction. Midmyocardial GCS correlated with inflammatory myocardial parameters (eg, late gadolinium enhancement percentage, r = 0.48, P < .001). Midmyocardial GCS (area under the receiver operating characteristic curve [AUC], 0.82) and subepicardial GLS (AUC, 0.77) had the highest diagnostic performance for acute myocarditis diagnosis (P < .05 against all other strain parameters). The diagnostic performance of the 2018 LLC was significantly improved by inclusion of these two strain parameters (AUC, 0.92 vs 0.97; P = .04).

CONCLUSION

Diagnostic performance of cardiac MRI FT strain was different between myocardial layers in acute myocarditis, with midmyocardial GCS and subepicardial GLS providing the highest diagnostic performance.Keywords: MRI, Cardiac, Heart, Left Ventricle, Inflammation, Tissue Characterization, MR-Functional Imaging, Feature-Tracking Strain, Acute Myocarditis Supplemental material is available for this article. © RSNA, 2022.

Deep Learning for the Detection, Localization, and Characterization of Focal Liver Lesions on Abdominal US Images

Purpose

To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images.

Materials and Methods

In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters.

Results

DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks.

Conclusion

DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article.  RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN).

Accelerated in Vivo Cardiac Diffusion-Tensor MRI Using Residual Deep Learning-based Denoising in Participants with Obesity

Purpose

To develop and assess a residual deep learning algorithm to accelerate in vivo cardiac diffusion-tensor MRI (DT-MRI) by reducing the number of averages while preserving image quality and DT-MRI parameters.

Materials and Methods

In this prospective study, a denoising convolutional neural network (DnCNN) for DT-MRI was developed; a total of 26 participants, including 20 without obesity (body mass index [BMI] < 30 kg/m²; mean age, 28 years ± 3 [standard deviation]; 11 women) and six with obesity (BMI ≥ 30 kg/m²; mean age, 48 years ± 11; five women), were recruited from June 19, 2019, to July 29, 2020. DT-MRI data were constructed at four averages (4Av), two averages (2Av), and one average (1Av) without and with the application of the DnCNN (4Av_DnCNN, 2Av_DnCNN, 1Av_DnCNN). All data were compared against the reference DT-MRI data constructed at eight averages (8Av). Image quality, characterized by using the signal-to-noise ratio (SNR) and structural similarity index (SSIM), and the DT-MRI parameters of mean diffusivity (MD), fractional anisotropy (FA), and helix angle transmurality (HAT) were quantified.

Results

No differences were found in image quality or DT-MRI parameters between the accelerated 4Av_DnCNN DT-MRI and the reference 8Av DT-MRI data for the SNR (29.1 ± 2.7 vs 30.5 ± 2.9), SSIM (0.97 ± 0.01), MD (1.3 µm²/msec ± 0.1 vs 1.31 µm²/msec ± 0.11), FA (0.32 ± 0.05 vs 0.30 ± 0.04), or HAT (1.10°/% ± 0.13 vs 1.11°/% ± 0.09). The relationship of a higher MD and lower FA and HAT in individuals with obesity compared with individuals without obesity in reference 8Av DT-MRI measurements was retained in 4Av_DnCNN and 2Av_DnCNN DT-MRI measurements but was not retained in 4Av or 2Av DT-MRI measurements.

Conclusion

Cardiac DT-MRI can be performed at an at least twofold-accelerated rate by using DnCNN to preserve image quality and DT-MRI parameter quantification.Keywords: Adults, Cardiac, Obesity, Technology Assessment, MR-Diffusion Tensor Imaging, Heart, Tissue CharacterizationSupplemental material is available for this article.© RSNA, 2021.

Ex Vivo MR Histology and Cytometric Feature Mapping Connect Three-dimensional in Vivo MR Images to Two-dimensional Histopathologic Images of Murine Sarcomas

Purpose To establish a platform for quantitative tissue-based interpretation of cytoarchitecture features from tumor MRI measurements. Materials and Methods In a pilot preclinical study, multicontrast in vivo MRI of murine soft-tissue sarcomas in 10 mice, followed by ex vivo MRI of fixed tissues (termed MR histology), was performed. Paraffin-embedded limb cross-sections were stained with hematoxylin-eosin, digitized, and registered with MRI. Registration was assessed by using binarized tumor maps and Dice similarity coefficients (DSCs). Quantitative cytometric feature maps from histologic slides were derived by using nuclear segmentation and compared with registered MRI, including apparent diffusion coefficients and transverse relaxation times as affected by magnetic field heterogeneity (T2* maps). Cytometric features were compared with each MR image individually by using simple linear regression analysis to identify the features of interest, and the goodness of fit was assessed on the basis of R² values. Results Registration of MR images to histopathologic slide images resulted in mean DSCs of 0.912 for ex vivo MR histology and 0.881 for in vivo MRI. Triplicate repeats showed high registration repeatability (mean DSC, >0.9). Whole-slide nuclear segmentations were automated to detect nuclei on histopathologic slides (DSC = 0.8), and feature maps were generated for correlative analysis with MR images. Notable trends were observed between cell density and in vivo apparent diffusion coefficients (best line fit: R² = 0.96, P < .001). Multiple cytoarchitectural features exhibited linear relationships with in vivo T2* maps, including nuclear circularity (best line fit: R² = 0.99, P < .001) and variance in nuclear circularity (best line fit: R² = 0.98, P < .001). Conclusion An infrastructure for registering and quantitatively comparing in vivo tumor MRI with traditional histologic analysis was successfully implemented in a preclinical pilot study of soft-tissue sarcomas. Keywords: MRI, Pathology, Animal Studies, Tissue Characterization Supplemental material is available for this article. © RSNA, 2021.

Conceptual Approach of Diffusion- and Perfusion-Weighted Magnetic Resonance Imaging in Chest Diseases

The present manuscript discusses the development of a quantitative, and ultimately a visual approach as well, for detecting, diagnosing, staging, and following-up chest diseases. At the moment, computer tomography (CT) and positron emission tomography (PET) are the modalities of choice, and despite repeated attempts to integrate magnetic resonance imaging (MRI) in thoracic imaging diagnosis protocols, the classic sequences have - outside radiation reduction - usually no additional benefit in diagnosis. During this thesis, the attempt was made to show that by means of functional imaging sequences a better characterization of pleural, mediastinal and lung lesions was feasible. We even evaluated early treatment response by using diffusion-weighted imaging (DWI) as biomarker. Where possible, the correlation was made between radiological and histopathological images.