Multicenter, multivendor validation of liver quantitative susceptibility mapping in patients with iron overload at 1.5 T and 3 T.

PURPOSE: To evaluate the repeatability and reproducibility of QSM of the liver via single breath-hold chemical shift-encoded MRI at both 1.5 T and 3 T in a multicenter, multivendor study in subjects with iron overload. METHODS: This prospective study included four academic medical centers with three different MRI vendors at 1.5 T and 3 T. Subjects with known or suspected liver iron overload underwent multi-echo spoiled gradient-recalled-echo scans at each field strength. A subset received repeatability testing at either 1.5 T or 3 T. Susceptibility and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ maps were reconstructed from the multi-echo images and analyzed at a single center. QSM-measured susceptibility was compared with R 2 * $$ {\mathrm{R}}_2^{\ast } $$ and a commercial R2-based liver iron concentration method across centers and field strengths using linear regression and F-tests on the intercept and slope. Field-strength reproducibility and test/retest repeatability were evaluated using Bland-Altman analysis. RESULTS: A total of 155/80 data sets (test/retest) were available at 1.5 T, and 159/70 data sets (test/retest) were available at 3 T. Calibrations across sites were reproducible, with some variability (e.g., susceptibility slope with liver iron concentration ranged from 0.102 to 0.123 g/[mg · $$ \cdotp $$ ppm] across centers at 1.5 T). Field strength reproducibility was good (concordance correlation coefficient = 0.862), and test/retest repeatability was excellent (intraclass correlation coefficient = 0.951). CONCLUSION: QSM as an imaging biomarker of liver iron overload is feasible and repeatable across centers and MR vendors. It may be complementary with R 2 * $$ {\mathrm{R}}_2^{\ast } $$ as they are obtained from the same acquisition. Although good reproducibility was observed, liver QSM may benefit from standardization of acquisition parameters. Overall, QSM is a promising method for liver iron quantification.

Data adaptive regularization with reference tissue constraints for liver quantitative susceptibility mapping.

PURPOSE: To improve repeatability and reproducibility across acquisition parameters and reduce bias in quantitative susceptibility mapping (QSM) of the liver, through development of an optimized regularized reconstruction algorithm for abdominal QSM. METHODS: An optimized approach to estimation of magnetic susceptibility distribution is formulated as a constrained reconstruction problem that incorporates estimates of the input data reliability and anatomical priors available from chemical shift-encoded imaging. The proposed data-adaptive method was evaluated with respect to bias, repeatability, and reproducibility in a patient population with a wide range of liver iron concentration (LIC). The proposed method was compared to the previously proposed and validated approach in liver QSM for two multi-echo spoiled gradient-recalled echo protocols with different acquisition parameters at 3T. Linear regression was used for evaluation of QSM methods against a reference FDA-approved R 2 $$ {R}_2 $$ -based LIC measure and R 2 ∗ $$ {R}_2^{\ast } $$ measurements; repeatability/reproducibility were assessed by Bland-Altman analysis. RESULTS: The data-adaptive method produced susceptibility maps with higher subjective quality due to reduced shading artifacts. For both acquisition protocols, higher linear correlation with both R 2 $$ {R}_2 $$ - and R 2 ∗ $$ {R}_2^{\ast } $$ -based measurements were observed for the data-adaptive method ( r 2 = 0 . 74 / 0 . 69 $$ {r}^2=0.74/0.69 $$ for R 2 $$ {R}_2 $$ , 0 . 97 / 0 . 95 $$ 0.97/0.95 $$ for R 2 ∗ $$ {R}_2^{\ast } $$ ) than the standard method ( r 2 = 0 . 60 / 0 . 66 $$ {r}^2=0.60/0.66 $$ and 0 . 79 / 0 . 88 $$ 0.79/0.88 $$ ). For both protocols, the data-adaptive method enabled better test-retest repeatability (repeatability coefficients 0.19/0.30 ppm for the data-adaptive method, 0.38/0.47 ppm for the standard method) and reproducibility across protocols (reproducibility coefficient 0.28 vs. 0.53ppm) than the standard method. CONCLUSIONS: The proposed data-adaptive QSM algorithm may enable quantification of LIC with improved repeatability/reproducibility across different acquisition parameters as 3T.

Automated MR Image Prescription of the Liver Using Deep Learning: Development, Evaluation, and Prospective Implementation.

BACKGROUND: There is an unmet need for fully automated image prescription of the liver to enable efficient, reproducible MRI. PURPOSE: To develop and evaluate artificial intelligence (AI)-based liver image prescription. STUDY TYPE: Prospective. POPULATION: A total of 570 female/469 male patients (age: 56 ± 17 years) with 72%/8%/20% assigned randomly for training/validation/testing; two female/four male healthy volunteers (age: 31 ± 6 years). FIELD STRENGTH/SEQUENCE: 1.5 T, 3.0 T; spin echo, gradient echo, bSSFP. ASSESSMENT: A total of 1039 three-plane localizer acquisitions (26,929 slices) from consecutive clinical liver MRI examinations were retrieved retrospectively and annotated by six radiologists. The localizer images and manual annotations were used to train an object-detection convolutional neural network (YOLOv3) to detect multiple object classes (liver, torso, and arms) across localizer image orientations and to output corresponding 2D bounding boxes. Whole-liver image prescription in standard orientations was obtained based on these bounding boxes. 2D detection performance was evaluated on test datasets by calculating intersection over union (IoU) between manual and automated labeling. 3D prescription accuracy was calculated by measuring the boundary mismatch in each dimension and percentage of manual volume covered by AI prescription. The automated prescription was implemented on a 3 T MR system and evaluated prospectively on healthy volunteers. STATISTICAL TESTS: Paired t-tests (threshold = 0.05) were conducted to evaluate significance of performance difference between trained networks. RESULTS: In 208 testing datasets, the proposed method with full network had excellent agreement with manual annotations, with median IoU > 0.91 (interquartile range < 0.09) across all seven classes. The automated 3D prescription was accurate, with shifts <2.3 cm in superior/inferior dimension for 3D axial prescription for 99.5% of test datasets, comparable to radiologists' interreader reproducibility. The full network had significantly superior performance than the tiny network for 3D axial prescription in patients. Automated prescription performed well across single-shot fast spin-echo, gradient-echo, and balanced steady-state free-precession sequences in the prospective study. DATA CONCLUSION: AI-based automated liver image prescription demonstrated promising performance across the patients, pathologies, and field strengths studied. EVIDENCE LEVEL: 4. TECHNICAL EFFICACY: Stage 1.