Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical data.

BACKGROUND: For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images. PURPOSE: This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion. MATERIALS AND METHODS: A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them-it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications. RESULTS: A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors. CONCLUSION: This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.

18F-FDG PET/CT Uptake Classification in Lymphoma and Lung Cancer by Using Deep Convolutional Neural Networks.

Background Fluorine 18 (18F)-fluorodeoxyglucose (FDG) PET/CT is a routine tool for staging patients with lymphoma and lung cancer. Purpose To evaluate configurations of deep convolutional neural networks (CNNs) to localize and classify uptake patterns of whole-body 18F-FDG PET/CT images in patients with lung cancer and lymphoma. Materials and Methods This was a retrospective analysis of consecutive patients with lung cancer or lymphoma referred to a single center from August 2011 to August 2013. Two nuclear medicine experts manually delineated foci with increased 18F-FDG uptake, specified the anatomic location, and classified these findings as suspicious for tumor or metastasis or nonsuspicious. By using these expert readings as the reference standard, a CNN was developed to detect foci positive for 18F-FDG uptake, predict the anatomic location, and determine the expert classification. Examinations were divided into independent training (60%), validation (20%), and test (20%) subsets. Results This study included 629 patients (mean age, 52.2 years ± 20.4 [standard deviation]; 394 men). There were 302 patients with lung cancer and 327 patients with lymphoma. For the test set (123 patients; 10 782 foci), the CNN areas under the receiver operating characteristic curve (AUCs) for determining hypermetabolic 18F-FDG PET/CT foci that were suspicious for cancer versus nonsuspicious by using the five input features were as follows: CT alone, 0.78 (95% confidence interval [CI]: 0.72, 0.83); 18F-FDG PET alone, 0.97 (95% CI: 0.97, 0.98); 18F-FDG PET/CT, 0.98 (95% CI: 0.97, 0.99); 18F-FDG PET/CT maximum intensity projection (MIP), 0.98 (95% CI: 0.98, 0.99); and 18F-FDG PET/CT MIP atlas, 0.99 (95% CI: 0.98, 1.00). The combination of 18F-FDG PET and CT information improved overall classification accuracy (AUC, 0.975 vs 0.981, respectively; P < .001). Anatomic localization accuracy of the CNN was 2543 of 2639 (96.4%; 95% CI: 95.5%, 97.1%) for body part, 2292 of 2639 (86.9%; 95% CI: 85.3%, 88.5%) for region (ie, organ), and 2149 of 2639 (81.4%; 95% CI: 79.3%-83.5%) for subregion. Conclusion The fully automated anatomic localization and classification of fluorine 18-fluorodeoxyglucose PET uptake patterns in foci suspicious and nonsuspicious for cancer in patients with lung cancer and lymphoma by using a convolutional neural network is feasible and achieves high diagnostic performance when both CT and PET images are used. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Froelich and Salavati in this issue.

Steady-state first-pass perfusion (SSFPP): a new approach to 3D first-pass myocardial perfusion imaging.

PURPOSE: To describe and characterize a new approach to first-pass myocardial perfusion utilizing balanced steady-state free precession acquisition without the use of saturation recovery or other magnetization preparation. THEORY: The balanced steady-state free precession sequence is inherently sensitive to contrast agent enhancement of the myocardium. This sensitivity can be used to advantage in first-pass myocardial perfusion imaging by eliminating the need for magnetization preparation. METHODS: Bloch equation simulations, phantom experiments, and in vivo 2D imaging studies were run comparing the proposed technique with three other methods: saturation recovery spoiled gradient echo, saturation recovery steady-state free precession, and steady-state spoiled gradient echo without magnetization preparation. Additionally, an acquisition-reconstruction strategy for 3D perfusion imaging is proposed and initial experience with this approach is demonstrated in healthy subjects and one patient. RESULTS: Phantom experiments verified simulation results showing the sensitivity of the balanced steady-state free precession sequence to contrast agent enhancement in solid tissue is similar to that of magnetization-prepared acquisitions. Images acquired in normal volunteers showed the proposed technique provided superior signal and signal-to-noise ratio compared with all other sequences at baseline as well as postcontrast. CONCLUSIONS: A new approach to first-pass myocardial perfusion is presented that obviates the need for magnetization preparation and provides high signal-to-noise ratio.

Phase-sensitive inversion recovery for myocardial T1 mapping with motion correction and parametric fitting.

The assessment of myocardial fibrosis and extracellular volume requires accurate estimation of myocardial T1 s. While image acquisition using the modified Look-Locker inversion recovery technique is clinically feasible for myocardial T1 mapping, respiratory motion can limit its applicability. Moreover, the conventional T1 fitting approach using the magnitude inversion recovery images can lead to less stable T1 estimates and increased computational cost. In this article, we propose a novel T1 mapping scheme that is based on phase-sensitive image reconstruction and the restoration of polarity of the MR signal after inversion. The motion correction is achieved by registering the reconstructed images after background phase removal. The restored signal polarity of the inversion recovery signal helps the T1 fitting resulting in improved quality of the T1 map and reducing the computational cost. Quantitative validation on a data cohort of 45 patients proves the robustness of the proposed method against varying image contrast. Compared to the magnitude T1 fitting, the proposed phase-sensitive method leads to less fluctuation in T1 estimates.

Assessment of left ventricular myocardial scar in coronary artery disease by a three-dimensional MR imaging technique.

PURPOSE: To evaluate the feasibility of free-breathing three-dimensional (3D) phase sensitive inversion recovery (PSIR) Turbo FLASH late gadolinium enhancement (LGE) magnetic resonance images (MRI) on left ventricular scar in patients with coronary artery disease (CAD) compared with clinically established breathhold two-dimensional (2D) PSIR Turbo FLASH images. MATERIALS AND METHODS: In 58 consecutive patients with confirmed CAD, LGE MRI using the two sequences have been acquired. Image quality was graded on a four-point scale according to the image appearance. Qualitative evaluation including the distribution area and the transmural extent of the scar based on the American Heart Association's (AHA's) 17-segment model was performed in both of 2D and 3D images. The scar volumes were compared quantitatively between 2D and 3D images. RESULTS: A total of 51 individuals were used for final statistical analysis. No differences were noted in image quality (P = 0.80), scar distribution area (P = 0.17), and scar transmural extent (P = 0.20) between 3D and 2D images. There was strong correlation in scar volume between the 3D and 2D results (r = 0.940; P < 0.001; Y = 0.298 + 1.251X, R(2) = 0.876). But the scar volume derived from 3D images was significantly larger than that derived from 2D images (2D versus 3D, 20.08 ± 9.41 cm(3) versus 25.41 ± 12.57 cm(3) , t = -7.60; P < 0.001). The trend toward a larger scar volume identified by 3D method was indicated through Bland-Altman analysis. CONCLUSION: Free-breathing 3D PSIR Turbo FLASH imaging is another feasible method to identify left ventricular myocardial scar in patients with CAD and detects more scar volume compared with breathhold 2D PSIR Turbo FLASH imaging.

Ethical Considerations for Artificial Intelligence in Medical Imaging: Deployment and Governance.

The deployment of artificial intelligence (AI) has the potential to make nuclear medicine and medical imaging faster, cheaper, and both more effective and more accessible. This is possible, however, only if clinicians and patients feel that these AI medical devices (AIMDs) are trustworthy. Highlighting the need to ensure health justice by fairly distributing benefits and burdens while respecting individual patients' rights, the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging has identified 4 major ethical risks that arise during the deployment of AIMD: autonomy of patients and clinicians, transparency of clinical performance and limitations, fairness toward marginalized populations, and accountability of physicians and developers. We provide preliminary recommendations for governing these ethical risks to realize the promise of AIMD for patients and populations.

Ethical Considerations for Artificial Intelligence in Medical Imaging: Data Collection, Development, and Evaluation.

The development of artificial intelligence (AI) within nuclear imaging involves several ethically fraught components at different stages of the machine learning pipeline, including during data collection, model training and validation, and clinical use. Drawing on the traditional principles of medical and research ethics, and highlighting the need to ensure health justice, the AI task force of the Society of Nuclear Medicine and Molecular Imaging has identified 4 major ethical risks: privacy of data subjects, data quality and model efficacy, fairness toward marginalized populations, and transparency of clinical performance. We provide preliminary recommendations to developers of AI-driven medical devices for mitigating the impact of these risks on patients and populations.

Artificial Intelligence in Nuclear Medicine: Opportunities, Challenges, and Responsibilities Toward a Trustworthy Ecosystem.

Trustworthiness is a core tenet of medicine. The patient-physician relationship is evolving from a dyad to a broader ecosystem of health care. With the emergence of artificial intelligence (AI) in medicine, the elements of trust must be revisited. We envision a road map for the establishment of trustworthy AI ecosystems in nuclear medicine. In this report, AI is contextualized in the history of technologic revolutions. Opportunities for AI applications in nuclear medicine related to diagnosis, therapy, and workflow efficiency, as well as emerging challenges and critical responsibilities, are discussed. Establishing and maintaining leadership in AI require a concerted effort to promote the rational and safe deployment of this innovative technology by engaging patients, nuclear medicine physicians, scientists, technologists, and referring providers, among other stakeholders, while protecting our patients and society. This strategic plan was prepared by the AI task force of the Society of Nuclear Medicine and Molecular Imaging.

Prospective self-gating for swallowing motion: a feasibility study in carotid artery wall MRI using three-dimensional variable-flip-angle turbo spin-echo.

Three-dimensional black-blood MRI is a promising noninvasive imaging technique for the assessment of atherosclerotic carotid artery disease. However, this technique is inherently susceptible to motion. In particular, swallowing can result in considerable wall motion at the carotid bifurcations, which may induce drastic image degradation or substantial overestimation of wall thickness. Self-gating techniques have previously been shown to be capable of resolving and compensating for cardiac or respiratory motion during MRI. This work presents a self-gating-based prospective motion gating scheme that is combined with a three-dimensional variable-flip-angle turbo spin-echo sequence (SPACE) for detecting swallowing motion. Self-gating signal readouts along the superior-inferior direction during each repetition time period are used to derive the projection profiles of the imaging volume. Based on cross-correlation analysis between the projection profiles and the corresponding reference profiles, swallowing motion can be detected and the motion-contaminated data will subsequently be discarded and reacquired in the next repetition time. The self-gated SPACE sequence was validated on eight healthy volunteers and two patients and, when compared with the conventional SPACE sequence, proved to be more resistant to swallowing motion and significantly improved image quality as well as the sharpness of carotid artery wall boundaries.

Motion correction for myocardial T1 mapping using image registration with synthetic image estimation.

Quantification of myocardial T1 relaxation has potential value in the diagnosis of both ischemic and nonischemic cardiomyopathies. Image acquisition using the modified Look-Locker inversion recovery technique is clinically feasible for T1 mapping. However, respiratory motion limits its applicability and degrades the accuracy of T1 estimation. The robust registration of acquired inversion recovery images is particularly challenging due to the large changes in image contrast, especially for those images acquired near the signal null point of the inversion recovery and other inversion times for which there is little tissue contrast. In this article, we propose a novel motion correction algorithm. This approach is based on estimating synthetic images presenting contrast changes similar to the acquired images. The estimation of synthetic images is formulated as a variational energy minimization problem. Validation on a consecutive patient data cohort shows that this strategy can perform robust nonrigid registration to align inversion recovery images experiencing significant motion and lead to suppression of motion induced artifacts in the T1 map.

Myocardial T2 mapping with respiratory navigator and automatic nonrigid motion correction.

Quantitative T2 mapping was recently shown to be superior to T2-weighted imaging in detecting T2 changes across myocardium. Pixel-wise T2 mapping is sensitive to misregistration between the images used to generate the parameter map. In this study, utility of two motion-compensation strategies-(i) navigator gating with prospective slice correction and (ii) nonrigid registration-was investigated for myocardial T2 mapping in short axis and horizontal long axis views. Navigator gating provides respiratory motion compensation, whereas registration corrects for residual cardiac and respiratory motion between images; thus, the two strategies provided complementary functions. When these were combined, respiratory-motion-induced T2 variability, as measured by both standard deviation and interquartile range, was comparable to that in breath-hold T2 maps. In normal subjects, this combined motion-compensation strategy increased the percentage of myocardium with T2 measured to be within normal range from 60.1% to 92.2% in short axis and 62.3% to 92.7% in horizontal long axis. The new motion-compensated T2 mapping technique, which combines navigator gating, prospective slice correction, and nonrigid registration to provide through-plane and in-plane motion correction, enables a method for fully automatic and robust free-breathing T2 mapping.

T2-weighted cardiac MR assessment of the myocardial area-at-risk and salvage area in acute reperfused myocardial infarction: comparison of state-of-the-art dark blood and bright blood T2-weighted sequences.

PURPOSE: To compare different state-of-the-art T2-weighted (T2w) imaging sequences combined with late gadolinium enhancement (LGE) for myocardial salvage area (MSA) assessment by cardiac magnetic resonance (CMR). T2w imaging has been used to assess the myocardial area at risk (AAR) in acute myocardial infarction (AMI) patients, but its clinical application is challenging due to technical and physical limitations. MATERIALS AND METHODS: Thirty patients with reperfused AMI underwent complete CMR imaging 2-5 days after hospital admission. Myocardial AAR and MSA were quantified on four different T2w sequences: (a) free-breathing T2-prepared single-shot balanced steady-state free precession (T2p_ssbSSFP); (b) breathhold T2-weighted acquisition for cardiac unified T2 edema (ACUTE); (c) breathhold T2w dark-blood inversion recovery turbo-spin echo (IR-TSE) (short-term inversion recovery: STIR); and (d) free-breathing high-resolution T2 dark-blood navigated BLADE. The diagnostic performance of each technique was also assessed. RESULTS: Quantitative analysis showed significant differences in myocardial AAR extent as quantified by the four T2w sequences (P < 0.05). There were also significant differences in sensitivity, specificity and overall diagnostic performance. CONCLUSION: Detection and quantification of AAR, and thus of MSA, by T2wCMR in reperfused AMI patients varied significantly between different T2w sequences in the same clinical setting.

Nuclear Medicine and Artificial Intelligence: Best Practices for Evaluation (the RELAINCE Guidelines).

An important need exists for strategies to perform rigorous objective clinical-task-based evaluation of artificial intelligence (AI) algorithms for nuclear medicine. To address this need, we propose a 4-class framework to evaluate AI algorithms for promise, technical task-specific efficacy, clinical decision making, and postdeployment efficacy. We provide best practices to evaluate AI algorithms for each of these classes. Each class of evaluation yields a claim that provides a descriptive performance of the AI algorithm. Key best practices are tabulated as the RELAINCE (Recommendations for EvaLuation of AI for NuClear medicinE) guidelines. The report was prepared by the Society of Nuclear Medicine and Molecular Imaging AI Task Force Evaluation team, which consisted of nuclear-medicine physicians, physicists, computational imaging scientists, and representatives from industry and regulatory agencies.

Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development.

The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.

Contrast-enhanced whole-heart coronary magnetic resonance angiography at 3 T with radial EPI.

Whole-heart coronary magnetic resonance angiography is a promising method for detecting coronary artery disease. However, the imaging time is relatively long (typically 10-15 min). The goal of this study was to implement a radial echo planar imaging sequence for contrast-enhanced whole-heart coronary magnetic resonance angiography, with the aim of combining the scan efficiency of echo planar imaging with the motion insensitivity of radial k-space sampling. A self-calibrating phase correction technique was used to correct for off-resonance effects, trajectory measurement was used to correct for k-space trajectory errors, and variable density sampling was used in the partition direction to reduce streaking artifacts. Seven healthy volunteers and two patients were scanned with the proposed radial echo planar imaging sequence, and the images were compared with a traditional gradient echo and X-ray angiography techniques, respectively. Whole-heart images with the radial EPI technique were acquired with a resolution of 1.0 × 1.0 × 2.0 mm(3) in a scan time of 5 min. In healthy volunteers, the average image quality scores and visualized vessel lengths of the RCA and LAD were similar for the radial EPI and gradient echo techniques (P value > 0.05 for all). Anecdotal patient studies showed excellent agreement of the radial EPI technique with X-ray angiography.

3D radial sampling and 3D affine transform-based respiratory motion correction technique for free-breathing whole-heart coronary MRA with 100% imaging efficiency.

The navigator gating and slice tracking approach currently used for respiratory motion compensation during free-breathing coronary magnetic resonance angiography (MRA) has low imaging efficiency (typically 30-50%), resulting in long imaging times. In this work, a novel respiratory motion correction technique with 100% scan efficiency was developed for free-breathing whole-heart coronary MRA. The navigator signal was used as a reference respiratory signal to segment the data into six bins. 3D projection reconstruction k-space sampling was used for data acquisition and enabled reconstruction of low resolution images within each respiratory bin. The motion between bins was estimated by image registration with a 3D affine transform. The data from the different respiratory bins was retrospectively combined after motion correction to produce the final image. The proposed method was compared with a traditional navigator gating approach in nine healthy subjects. The proposed technique acquired whole-heart coronary MRA with 1.0 mm(3) isotropic spatial resolution in a scan time of 6.8 ± 0.9 min, compared with 16.2 ± 2.8 min for the navigator gating approach. The image quality scores, and length, diameter and sharpness of the right coronary artery (RCA), left anterior descending coronary artery (LAD), and left circumflex coronary artery (LCX) were similar for both approaches (P > 0.05 for all), but the proposed technique reduced scan time by a factor of 2.5.

On the mechanisms enabling myocardial edema contrast in bSSFP-based imaging approaches.

The biophysical mechanisms influencing balanced steady-state free precession (bSSFP) based edema imaging in the setting of acute myocardial infarction are not well understood. To assess the various mechanisms that enable the detection of myocardial edema on bSSFP-based imaging approaches (cine bSSFP and T(2)-prepared bSSFP), experiments were conducted in canine models subjected to ischemia-reperfusion injury. Results showed that in addition to relaxation effects, the alteration in thermal equilibrium (M(0)) (including magnetization transfer) has a significant contribution to the image contrast between edematous and healthy myocardium. The relative signal-intensity ratios between edematous and healthy myocardium were: 1.51 ± 0.18 (cine bSSFP) and 1.58 ± 0.20 (T(2)-prepared bSSFP); the theoretically estimated relative relaxation and M(0) effects were: 1.17 ± 0.09 and 1.30 ± 0.19, respectively (cine bSSFP), and 1.49 ± 0.23 and 1.06 ± 0.07, respectively (T(2)-prepared bSSFP). There were no significant difference between cine bSSFP and T(2)-prep bSSFP relative signal-intensity ratios. However, the relative relaxation effect in cine bSSFP was significantly lower than in T(2)-prep bSSFP (P < 0.05), and the M(0) effect in cine bSSFP was significantly higher than in T(2)-prep bSSFP (P < 0.05). Hence the acquisition strategies that wish to maximize myocardial edema contrast in cine bSSFP imaging should take both relaxation and M(0) effects into account.

T(2) -weighted STIR imaging of myocardial edema associated with ischemia-reperfusion injury: the influence of proton density effect on image contrast.

PURPOSE: To investigate the contribution of proton density (PD) in T(2) -STIR based edema imaging in the setting of acute myocardial infarction (AMI). MATERIALS AND METHODS: Canines (n = 5), subjected to full occlusion of the left anterior descending artery for 3 hours, underwent serial magnetic resonance imaging (MRI) studies 2 hours postreperfusion (day 0) and on day 2. During each study, T(1) and T(2) maps, STIR (TE = 7.1 msec and 64 msec) and late gadolinium enhancement (LGE) images were acquired. Using T(1) and T(2) maps, relaxation and PD contributions to myocardial edema contrast (EC) in STIR images at both TEs were calculated. RESULTS: Edematous territories showed significant increase in PD (20.3 ± 14.3%, P < 0.05) relative to healthy territories. The contributions of T(1) changes and T(2) or PD changes toward EC were in opposite directions. One-tailed t-test confirmed that the mean T(2) and PD-based EC at both TEs were greater than zero. EC from STIR images at TE = 7.1 msec was dominated by PD than T(2) effects (94.3 ± 11.3% vs. 17.6 ± 2.5%, P < 0.05), while at TE = 64 msec, T(2) effects were significantly greater than PD effects (90.8 ± 20.3% vs. 12.5 ± 11.9%, P < 0.05). The contribution from PD in standard STIR acquisitions (TE = 64 msec) was significantly higher than 0 (P < 0.05). CONCLUSION: In addition to T(2) -weighting, edema detection in the setting of AMI with T(2) -weighted STIR imaging has a substantial contribution from PD changes, likely stemming from increased free-water content within the affected tissue. This suggests that imaging approaches that take advantage of both PD as well as T(2) effects may provide the optimal sensitivity for detecting myocardial edema.

Assessment of chronic hepatitis and fibrosis: comparison of MR elastography and diffusion-weighted imaging.

OBJECTIVE: The purpose of our study was to compare the utility of MR elastography (MRE) and diffusion-weighted imaging (DWI) in characterizing fibrosis and chronic hepatitis in patients with chronic liver diseases. SUBJECTS AND METHODS: Seventy-six patients with chronic liver disease underwent abdominal MRI, MRE, and DWI. Severities of liver fibrosis and chronic hepatitis were graded by histopathologic analysis according to standard disease-specific classifications. The overall predictive ability of MRE and DWI in assessment of fibrosis was compared by constructing a receiver operating characteristic (ROC) curve and calculating the area under the curve (AUC) on the basis of histopathologic analysis. RESULTS: Using ROC analysis, MRE showed greater capability than DWI in discriminating stage 2 or greater (≥ F2), stage 3 or greater (≥ F3), and cirrhosis (≥ F4), shown as significant differences in AUC (p = 0.003, p = 0.001, and p = 0.001, respectively). Higher sensitivity and specificity were shown by MRE in predicting fibrosis scores ≥ F2 (91% and 97%), scores ≥ F3 (92% and 95%), and scores F4 (95% and 87%) compared with DWI (84% and 82%, 88% and 76%, and 85% and 68%, respectively). Although MRE had higher ability in identification of liver with fibrosis scores ≥ F1 than DWI, a significant difference was not seen (p = 0.398). Stiffness values on MRE increased in relation to increasing severity of fibrosis confirmed by histopathology scores; however, a consistent relationship between apparent diffusion coefficient (ADC) values and stage of fibrosis was not shown. In addition, liver tissue with chronic hepatitis preceding fibrosis may account for mild elevation of liver stiffness. CONCLUSION: MRE had greater predictive ability in distinguishing the stages of liver fibrosis than DWI.