Automated, calibration-free quantification of cortical bone porosity and geometry in postmenopausal osteoporosis from ultrashort echo time MRI and deep learning.

BACKGROUND: Assessment of cortical bone porosity and geometry by imaging in vivo can provide useful information about bone quality that is independent of bone mineral density (BMD). Ultrashort echo time (UTE) MRI techniques of measuring cortical bone porosity and geometry have been extensively validated in preclinical studies and have recently been shown to detect impaired bone quality in vivo in patients with osteoporosis. However, these techniques rely on laborious image segmentation, which is clinically impractical. Additionally, UTE MRI porosity techniques typically require long scan times or external calibration samples and elaborate physics processing, which limit their translatability. To this end, the UTE MRI-derived Suppression Ratio has been proposed as a simple-to-calculate, reference-free biomarker of porosity which can be acquired in clinically feasible acquisition times. PURPOSE: To explore whether a deep learning method can automate cortical bone segmentation and the corresponding analysis of cortical bone imaging biomarkers, and to investigate the Suppression Ratio as a fast, simple, and reference-free biomarker of cortical bone porosity. METHODS: In this retrospective study, a deep learning 2D U-Net was trained to segment the tibial cortex from 48 individual image sets comprised of 46 slices each, corresponding to 2208 training slices. Network performance was validated through an external test dataset comprised of 28 scans from 3 groups: (1) 10 healthy, young participants, (2) 9 postmenopausal, non-osteoporotic women, and (3) 9 postmenopausal, osteoporotic women. The accuracy of automated porosity and geometry quantifications were assessed with the coefficient of determination and the intraclass correlation coefficient (ICC). Furthermore, automated MRI biomarkers were compared between groups and to dual energy X-ray absorptiometry (DXA)- and peripheral quantitative CT (pQCT)-derived BMD. Additionally, the Suppression Ratio was compared to UTE porosity techniques based on calibration samples. RESULTS: The deep learning model provided accurate labeling (Dice score 0.93, intersection-over-union 0.88) and similar results to manual segmentation in quantifying cortical porosity (R2 ≥ 0.97, ICC ≥ 0.98) and geometry (R2 ≥ 0.82, ICC ≥ 0.75) parameters in vivo. Furthermore, the Suppression Ratio was validated compared to established porosity protocols (R2 ≥ 0.78). Automated parameters detected age- and osteoporosis-related impairments in cortical bone porosity (P ≤ .002) and geometry (P values ranging from <0.001 to 0.08). Finally, automated porosity markers showed strong, inverse Pearson's correlations with BMD measured by pQCT (|R| ≥ 0.88) and DXA (|R| ≥ 0.76) in postmenopausal women, confirming that lower mineral density corresponds to greater porosity. CONCLUSION: This study demonstrated feasibility of a simple, automated, and ionizing-radiation-free protocol for quantifying cortical bone porosity and geometry in vivo from UTE MRI and deep learning.

Quantitative susceptibility mapping using plug-and-play alternating direction method of multipliers.

Quantitative susceptibility mapping employs regularization to reduce artifacts, yet many recent denoisers are unavailable for reconstruction. We developed a plug-and-play approach to QSM reconstruction (PnP QSM) and show its flexibility using several patch-based denoisers. We developed PnP QSM using alternating direction method of multiplier framework and applied collaborative filtering denoisers. We apply the technique to the 2016 QSM Challenge and in 10 glioblastoma multiforme datasets. We compared its performance with four published QSM techniques and a multi-orientation QSM method. We analyzed magnetic susceptibility accuracy using brain region-of-interest measurements, and image quality using global error metrics. Reconstructions on glioblastoma data were analyzed using ranked and semiquantitative image grading by three neuroradiologist observers to assess image quality (IQ) and sharpness (IS). PnP-BM4D QSM showed good correlation (ß = 0.84, R2 = 0.98, p < 0.05) with COSMOS and no significant bias (bias = 0.007 ± 0.012). PnP-BM4D QSM achieved excellent quality when assessed using structural similarity index metric (SSIM = 0.860), high frequency error norm (HFEN = 58.5), cross correlation (CC = 0.804), and mutual information (MI = 0.475) and also maintained good conspicuity of fine features. In glioblastoma datasets, PnP-BM4D QSM showed higher performance (IQGrade = 2.4 ± 0.4, ISGrade = 2.7 ± 0.3, IQRank = 3.7 ± 0.3, ISRank = 3.9 ± 0.3) compared to MEDI (IQGrade = 2.1 ± 0.5, ISGrade = 2.1 ± 0.6, IQRank = 2.4 ± 0.6, ISRank = 2.9 ± 0.2) and FANSI-TGV (IQGrade = 2.2 ± 0.6, ISGrade = 2.1 ± 0.6, IQRank = 2.7 ± 0.3, ISRank = 2.2 ± 0.2). We illustrated the modularity of PnP QSM by interchanging two additional patch-based denoisers. PnP QSM reconstruction was feasible, and its flexibility was shown using several patch-based denoisers. This technique may allow rapid prototyping and validation of new denoisers for QSM reconstruction for an array of useful clinical applications.

Magnetic susceptibility and R2* of myocardial reperfusion injury at 3T and 7T.

PURPOSE: Magnetic susceptibility (Δχ) alterations have shown association with myocardial infarction (MI) iron deposition, yet there remains limited understanding of the relationship between relaxation rates and susceptibility or the effect of magnetic field strength. Hence, Δχ and R2∗ in MI were compared at 3T and 7T. METHODS: Subacute MI was induced by coronary artery ligation in male Yorkshire swine. 3D multiecho gradient echo imaging was performed at 1-week postinfarction at 3T and 7T. Quantitative susceptibility mapping images were reconstructed using a morphology-enabled dipole inversion. R2∗ maps and quantitative susceptibility mapping were generated to assess the relationship between R2∗ , Δχ, and field strength. Infarct histopathology was investigated. RESULTS: Magnetic susceptibility was not significantly different across field strengths (7T: 126.8 ± 41.7 ppb; 3T: 110.2 ± 21.0 ppb, P = NS), unlike R2∗ (7T: 247.0 ± 14.8 Hz; 3T: 106.1 ± 6.5 Hz, P < .001). Additionally, infarct Δχ and R2∗ were significantly higher than remote myocardium. Magnetic susceptibility at 7T versus 3T had a significant association (ß = 1.02, R2 = 0.82, P < .001), as did R2∗ (ß = 2.35, R2 = 0.98, P < .001). Infarct pathophysiology and iron deposition were detected through histology and compared with imaging findings. CONCLUSION: R2∗ showed dependence and Δχ showed independence of field strength. Histology validated the presence of iron and supported imaging findings.

Classification of Myocardial 18F-FDG PET Uptake Patterns Using Deep Learning.

PURPOSE: To perform automated myocardial segmentation and uptake classification from whole-body fluorine 18 fluorodeoxyglucose (FDG) PET. MATERIALS AND METHODS: In this retrospective study, consecutive patients who underwent FDG PET imaging for oncologic indications were included (July-August 2018). The left ventricle (LV) on whole-body FDG PET images was manually segmented and classified as showing no myocardial uptake, diffuse uptake, or partial uptake. A total of 609 patients (mean age, 64 years ± 14 [standard deviation]; 309 women) were included and split between training (60%, 365 patients), validation (20%, 122 patients), and testing (20%, 122 patients) datasets. Two sequential neural networks were developed to automatically segment the LV and classify the myocardial uptake pattern using segmentation and classification training data provided by human experts. Linear regression was performed to correlate findings from human experts and deep learning. Classification performance was evaluated using receiver operating characteristic (ROC) analysis. RESULTS: There was moderate agreement of uptake pattern between experts and deep learning (as a fraction of correctly categorized images) with 78% (36 of 46) for no uptake, 71% (34 of 48) for diffuse uptake, and 71% (20 of 28) for partial uptake. There was no bias in LV volume for partial or diffuse uptake categories (P = .56); however, deep learning underestimated LV volumes in the no uptake category. There was good correlation for LV volume (R 2 = 0.35, b = .71). ROC analysis showed the area under the curve for classifying no uptake and diffuse uptake was high (> 0.90) but lower for partial uptake (0.77). The feasibility of a myocardial uptake index (MUI) for quantifying the degree of myocardial activity patterns was shown, and there was excellent visual agreement between MUI and uptake patterns. CONCLUSION: Deep learning was able to segment and classify myocardial uptake patterns on FDG PET images.Keywords: PET, Heart, Computer Aided Diagnosis, Computer Application-Detection/DiagnosisSupplemental material is available for this article.©RSNA, 2021.

Iron imaging in myocardial infarction reperfusion injury.

Restoration of coronary blood flow after a heart attack can cause reperfusion injury potentially leading to impaired cardiac function, adverse tissue remodeling and heart failure. Iron is an essential biometal that may have a pathologic role in this process. There is a clinical need for a precise noninvasive method to detect iron for risk stratification of patients and therapy evaluation. Here, we report that magnetic susceptibility imaging in a large animal model shows an infarct paramagnetic shift associated with duration of coronary artery occlusion and the presence of iron. Iron validation techniques used include histology, immunohistochemistry, spectrometry and spectroscopy. Further mRNA analysis shows upregulation of ferritin and heme oxygenase. While conventional imaging corroborates the findings of iron deposition, magnetic susceptibility imaging has improved sensitivity to iron and mitigates confounding factors such as edema and fibrosis. Myocardial infarction patients receiving reperfusion therapy show magnetic susceptibility changes associated with hypokinetic myocardial wall motion and microvascular obstruction, demonstrating potential for clinical translation.

Data-Driven Quantitative Susceptibility Mapping Using Loss Adaptive Dipole Inversion (LADI).

BACKGROUND: Quantitative susceptibility mapping (QSM) uses prior information to reconstruct maps, but prior information may not show pathology and introduce inconsistencies with susceptibility maps, degrade image quality and inadvertently smoothing image features. PURPOSE: To develop a local field data-driven QSM reconstruction that does not depend on spatial edge prior information. STUDY TYPE: Retrospective. SUBJECTS, ANIMAL MODELS: A dataset from 2016 ISMRM QSM Challenge, 11 patients with glioblastoma, a patient with microbleeds and porcine heart. SEQUENCE/FIELD STRENGTH: 3D gradient echo sequence on 3T and 7T scanners. ASSESSMENT: Accuracy was compared to Calculation of Susceptibility through Multiple Orientation Sampling (COSMOS), and several published techniques using region of interest (ROI) measurements, root-mean-squared error (RMSE), structural similarity index metric (SSIM), and high-frequency error norm (HFEN). Numerical ranking and semiquantitative image grading was performed by three expert observers to assess overall image quality (IQ) and image sharpness (IS). STATISTICAL TESTS: Bland-Altman, Friedman test, and Conover multiple comparisons. RESULTS: Loss adaptive dipole inversion (LADI) (ß = 0.82, R2 = 0.96), morphology-enabled dipole inversion (MEDI) (ß = 0.91, R2 = 0.97), and fast nonlinear susceptibility inversion (FANSI) (ß = 0.81, R2 = 0.98) had excellent correlation with COSMOS and no bias was detected (bias = 0.006 ± 0.014, P < 0.05). In glioblastoma patients, LADI showed consistently better performance (IQGrade = 2.6 ± 0.4, ISGrade = 2.6 ± 0.3, IQRank = 3.5 ± 0.4, ISRank = 3.9 ± 0.2) compared with MEDI (IQGrade = 2.1 ± 0.3, ISGrade = 2 ± 0.5, IQRank = 2.4 ± 0.5, ISRank = 2.8 ± 0.2) and FANSI (IQGrade = 2.2 ± 0.5, ISGrade = 2 ± 0.4, IQRank = 2.8 ± 0.3, ISRank = 2.1 ± 0.2). Dark artifact visible near the infarcted region in MEDI (InfMEDI = -0.27 ± 0.06 ppm) was better mitigated by FANSI (InfFANSI-TGV = -0.17 ± 0.05 ppm) and LADI (InfLADI = -0.18 ± 0.05 ppm). CONCLUSION: For neuroimaging applications, LADI preserved image sharpness and fine features in glioblastoma and microbleed patients. LADI performed better at mitigating artifacts in cardiac QSM. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY STAGE: 1 J. Magn. Reson. Imaging 2020;52:823-835.