Signal Intensity Trajectories Clustering for Liver Vasculature Segmentation and Labeling (LiVaS) on Contrast-Enhanced MR Images: A Feasibility Pilot Study.

This study aims to develop a semiautomated pipeline and user interface (LiVaS) for rapid segmentation and labeling of MRI liver vasculature and evaluate its time efficiency and accuracy against manual reference standard. Retrospective feasibility pilot study. Liver MR images from different scanners from 36 patients were included, and 4/36 patients were randomly selected for manual segmentation as referenced standard. The liver was segmented in each contrast phase and masks registered to the pre-contrast segmentation. Voxel-wise signal trajectories were clustered using the k-means algorithm. Voxel clusters that best segment the liver vessels were selected and labeled by three independent radiologists and a research scientist using LiVaS. Segmentation times were compared using a paired-sample t-test on log-transformed data. The agreement was analyzed qualitatively and quantitatively using DSC for hepatic and portal vein segmentations. The mean segmentation time among four readers was significantly shorter than manual (3.6 ± 1.4 vs. 70.0 ± 29.2 min; p < 0.001), even when using a higher number of clusters to enhance accuracy. The DSC for portal and hepatic veins reached up to 0.69 and 0.70, respectively. LiVaS segmentations were overall of good quality, with variations in performance related to the presence/severity of liver disease, acquisition timing, and image quality. Our semi-automated pipeline was robust to different MRI vendors in producing segmentation and labeling of liver vasculature in agreement with expert manual annotations, with significantly higher time efficiency. LiVaS could facilitate the creation of large, annotated datasets for training and validation of neural networks for automated MRI liver vascularity segmentation. HIGHLIGHTS: Key Finding: In this pilot feasibility study, our semiautomated pipeline for segmentation of liver vascularity (LiVaS) on MR images produced segmentations with simultaneous labeling of portal and hepatic veins in good agreement with the manual reference standard but at significantly shorter times (mean LiVaS 3.6 ± 1.4 vs. mean manual 70.0 ± 29.2 min; p < 0.001). Importance: LiVaS was robust in producing liver MRI vascular segmentations across images from different scanners in agreement with expert manual annotations, with significant ly higher time efficiency, and therefore potential scalability.

Deep Learning for Inference of Hepatic Proton Density Fat Fraction From T1-Weighted In-Phase and Opposed-Phase MRI: Retrospective Analysis of Population-Based Trial Data.

BACKGROUND. The confounder-corrected chemical shift-encoded MRI (CSE-MRI) sequence used to determine proton density fat fraction (PDFF) for hepatic fat quantification is not widely available. As an alternative, hepatic fat can be assessed by a two-point Dixon method to calculate signal fat fraction (FF) from conventional T1-weighted in- and opposed-phase (IOP) images, although signal FF is prone to biases, leading to inaccurate quantification. OBJECTIVE. The purpose of this study was to compare hepatic fat quantification by use of PDFF inferred from conventional T1-weighted IOP images and deep-learning convolutional neural networks (CNNs) with quantification by use of two-point Dixon signal FF with CSE-MRI PDFF as the reference standard. METHODS. This study entailed retrospective analysis of data from 292 participants (203 women, 89 men; mean age, 53.7 ± 12.0 [SD] years) enrolled at two sites from September 1, 2017, to December 18, 2019, in the Strong Heart Family Study (a prospective population-based study of American Indian communities). Participants underwent liver MRI (site A, 3 T; site B, 1.5 T) including T1-weighted IOP MRI and CSE-MRI (used to reconstruct CSE PDFF and CSE R2* maps). With CSE PDFF as reference, a CNN was trained in a random sample of 218 (75%) participants to infer voxel-by-voxel PDFF maps from T1-weighted IOP images; testing was performed in the other 74 (25%) participants. Parametric values from the entire liver were automatically extracted. Per-participant median CNN-inferred PDFF and median two-point Dixon signal FF were compared with reference median CSE-MRI PDFF by means of linear regression analysis, intraclass correlation coefficient (ICC), and Bland-Altman analysis. The code is publicly available at github.com/kang927/CNN-inference-of-PDFF-from-T1w-IOP-MR. RESULTS. In the 74 test-set participants, reference CSE PDFF ranged from 1% to 32% (mean, 11.3% ± 8.3% [SD]); reference CSE R2* ranged from 31 to 457 seconds-1 (mean, 62.4 ± 67.3 seconds-1 [SD]). Agreement metrics with reference to CSE PDFF for CNN-inferred PDFF were ICC = 0.99, bias = -0.19%, 95% limits of agreement (LoA) = (-2.80%, 2.71%) and for two-point Dixon signal FF were ICC = 0.93, bias = -1.11%, LoA = (-7.54%, 5.33%). CONCLUSION. Agreement with reference CSE PDFF was better for CNN-inferred PDFF from conventional T1-weighted IOP images than for two-point Dixon signal FF. Further investigation is needed in individuals with moderate-to-severe iron overload. CLINICAL IMPACT. Measurement of CNN-inferred PDFF from widely available T1-weighted IOP images may facilitate adoption of hepatic PDFF as a quantitative bio-marker for liver fat assessment, expanding opportunities to screen for hepatic steatosis and nonalcoholic fatty liver disease.

Inter-observer agreement and accuracy of LI-RADS v2018 for differentiating tumor in vein from bland thrombus using gadoxetic acid-enhanced magnetic resonance imaging.

PURPOSE: To assess inter-observer agreement and accuracy of LI-RADS v2018 for differentiating tumor in vein (TIV) from bland thrombus on gadoxetic acid-enhanced magnetic resonance imaging (Gx-MRI). Secondarily, to determine whether a multi-feature model improves accuracy compared to LI-RADS. METHODS: We retrospectively identified consecutive patients at risk for hepatocellular carcinoma with venous occlusion(s) reported on Gx-MRI. Five radiologists independently classified each occlusion as TIV or bland thrombus using the LI-RADS TIV criterion (enhancing soft tissue in vein). They also evaluated imaging features suggestive of TIV or bland thrombus. Intra-class correlation coefficient (ICC) was calculated for individual features. A multi-feature model was developed based on consensus scores of features with > 5% consensus prevalence and > 0.40 ICC. Sensitivity and specificity of the LI-RADS criterion and of the cross-validated multi-feature model were compared. RESULTS: Ninety-eight patients with 103 venous occlusions (58 TIV, 45 bland thrombus) were included. The LI-RADS criterion provided 0.63 ICC and, depending on the reader, 0.62-0.93 sensitivity and 0.87-1.00 specificity. Five other features had > 5% consensus prevalence and > 0.40 ICC, including three LI-RADS suggestive features and two non-LI-RADS features. The optimal multi-feature model incorporated the LI-RADS criterion and one LI-RADS suggestive feature (occluded or obscured vein contiguous with malignant parenchymal mass). After cross-validation, the multi-feature model did not improve sensitivity or specificity compared to the LI-RADS criterion (P = 0.23 and 0.25, respectively). CONCLUSION: Using Gx-MRI, the LI-RADS criterion for TIV provides substantial inter-observer agreement, variable sensitivity, and high specificity for differentiating TIV from bland thrombus. A cross-validated multi-feature model did not improve diagnostic performance.

Comparing Survival Outcomes of Patients With LI-RADS-M Hepatocellular Carcinomas and Intrahepatic Cholangiocarcinomas.

BACKGROUND: There is a sparsity of data evaluating outcomes of patients with Liver Imaging Reporting and Data System (LI-RADS) (LR)-M lesions. PURPOSE: To compare overall survival (OS) and progression free survival (PFS) between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (iCCA) meeting LR-M criteria and to evaluate factors associated with prognosis. STUDY TYPE: Retrospective. SUBJECTS: Patients at risk for HCC with at least one LR-M lesion with histologic diagnosis, from 8 academic centers, yielding 120 patients with 120 LR-M lesions (84 men [mean age 62 years] and 36 women [mean age 66 years]). FIELD STRENGTH/SEQUENCE: A 1.5 and 3.0 T/3D T1 -weighted gradient echo, T2 -weighted fast spin-echo. ASSESSMENT: The imaging categorization of each lesion as LR-M was made clinically by a single radiologist at each site and patient outcome measures were collected. STATISTICAL TESTS: OS, PFS, and potential independent predictors were evaluated by Kaplan-Meier method, log-rank test, and Cox proportional hazard model. A P value of <0.05 was considered significant. RESULTS: A total of 120 patients with 120 LR-M lesions were included; on histology 65 were HCC and 55 were iCCA. There was similar median OS for patients with LR-M HCC compared to patients with iCCA (738 days vs. 769 days, P = 0.576). There were no significant differences between patients with HCC and iCCA in terms of sex (47:18 vs. 37:18, P = 0.549), age (63.0 ± 8.4 vs. 63.4 ± 7.8, P = 0.847), etiology of liver disease (P = 0.202), presence of cirrhosis (100% vs. 100%, P = 1.000), tumor size (4.73 ± 3.28 vs. 4.75 ± 2.58, P = 0.980), method of lesion histologic diagnosis (P = 0.646), and proportion of patients who underwent locoregional therapy (60.0% vs. 38.2%, P = 0.100) or surgery (134.8 ± 165.5 vs. 142.5 ± 205.6, P = 0.913). Using multivariable analysis, nonsurgical compared to surgical management (HR, 4.58), larger tumor size (HR, 1.19), and higher MELD score (HR, 1.12) were independently associated with worse OS. DATA CONCLUSION: There was similar OS in patients with LR-M HCC and LR-M iCCA, suggesting that LR-M imaging features may more closely reflect patient outcomes than histology. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 5.

Liver imaging: it is time to adopt standardized terminology.

Liver imaging plays a vital role in the management of patients at risk for hepatocellular carcinoma (HCC); however, progress in the field is challenged by nonuniform and inconsistent terminology in the published literature. The Steering Committee of the American College of Radiology (ACR)'s Liver Imaging Reporting And Data System (LI-RADS), in conjunction with the LI-RADS Lexicon Writing Group and the LI-RADS International Working Group, present this consensus document to establish a single universal liver imaging lexicon. The lexicon is intended for use in research, education, and clinical care of patients at risk for HCC (i.e., the LI-RADS population) and in the general population (i.e., even when LI-RADS algorithms are not applicable). We anticipate that the universal adoption of this lexicon will provide research, educational, and clinical benefits. KEY POINTS: •To standardize terminology, we encourage authors of research and educational materials on liver imaging to use the standardized LI-RADS Lexicon. •We encourage reviewers to promote the use of the standardized LI-RADS Lexicon for publications on liver imaging. •We encourage radiologists to use the standardized LI-RADS Lexicon for liver imaging in clinical care.

Hepatocellular Carcinoma Staging: Differences Between Radiologic and Pathologic Systems and Relevance to Patient Selection and Outcomes in Liver Transplantation.

Liver transplant is indicated with curative intent for patients with early-stage hepatocellular carcinoma (HCC). The radiologic T category is used to determine candidacy and priority of patients on the waiting list. After transplant, the explant liver pathologic TNM stage is used as a predictor of postoperative outcomes and overall prognosis. Although the comparison of radiologic and pathologic T categories for concordance is often considered to be straightforward, the staging conventions significantly differ. Not accounting for these differences is in part the reason for the high rates of radiologic-pathologic discordance reported in the literature, with inconsistent terminology being an additional source of confusion when evaluating concordance. These factors may affect the understanding of important radiopathologic phenotypes of disease and the adequate investigation of their prognostic capabilities. The aims of this article are to provide an overview of the pathologic and radiologic TNM staging systems for HCC while describing staging procedures, emphasize the differences between these staging systems to highlight the limitations of radiologic-pathologic stage correlation, present a review of the literature on the prognostic value of individual features used for HCC staging; and signal significant aspects of preoperative risk stratification that could be improved to positively impact posttransplant outcomes.

MR Imaging Contrast Agents: Role in Imaging of Chronic Liver Diseases.

Contrast-enhanced MR imaging plays an important role in the evaluation of patients with chronic liver disease, particularly for detection and characterization of liver lesions. The two most commonly used contrast agents for liver MR imaging are extracellular agents (ECAs) and hepatobiliary agents (HBAs). In patients with liver disease, the main advantage of ECA-enhanced MR imaging is its high specificity for the diagnosis of progressed HCCs. Conversely, HBAs have an additional contrast mechanism, which results in high liver-to-lesion contrast and highest sensitivity for lesion detection in the hepatobiliary phase. Emerging data suggest that features depicted on contrast-enhanced MR imaging scans are related to tumor biology and are predictive of patients' prognosis, likely to further expand the role of contrast-enhanced MR imaging in the clinical care of patients with chronic liver disease.

Magnetic Resonance Imaging of Nonhepatocellular Malignancies in Chronic Liver Disease.

Hepatocellular carcinoma (HCC) is the most common liver malignancy associated with chronic liver disease. Nonhepatocellular malignancies may also arise in the setting of chronic liver disease. The imaging diagnosis of non-HCC malignancies may be challenging. Non-HCC malignancies in patients with chronic liver disease most commonly include intrahepatic cholangiocarcinoma and combined hepatocellular-cholangiocarcinoma, and less commonly hepatic lymphomas and metastases. On MR imaging, non-HCC malignancies often demonstrate a targetoid appearance, manifesting as rim arterial phase hyperenhancement, peripheral washout, central delayed enhancement, and peripheral restricted diffusion. When applying the Liver Imaging Reporting and Data System algorithm, observations with targetoid appearance are categorized as LR-M.

Multi-arterial phase MRI depicts inconsistent arterial phase hyperenhancement (APHE) subtypes in liver observations of patients at risk for hepatocellular carcinoma.

OBJECTIVES: According to LI-RADS, a major discriminating feature between hepatocellular carcinoma (HCC) and non-HCC malignancies is the subtype of arterial phase hyperenhancement (APHE). The aim of this study was to investigate whether APHE subtypes are consistent across multi-arterial phase (mHAP) MRI acquisitions while evaluating reader agreement. Secondarily, we investigated factors that may affect reader agreement for APHE subtype. METHODS: In this retrospective study, consecutive patients with liver cirrhosis and focal observations who underwent mHAP were included. Five radiologists reviewed MR images in 2 reading sessions. In reading session 1, individual AP series were reviewed and scored for presence of APHE and subtype. In reading session 2, readers scored observations' major and ancillary features and LI-RADS category in the complete MRI examination. Reader agreement was calculated using Fleiss' kappa for binary outcomes and Kendall's coefficient of concordance for LI-RADS categories. Univariate mixed effects logistic regressions were performed to investigate factors affecting agreement. RESULTS: In total, 61 patients with 77 focal observations were analyzed. Of observations unanimously scored as having APHE, 27.7% showed both rim and nonrim subtypes on mHAP. Inter-reader agreement for APHE subtype ranged from 0.49 (95% CI: 0.33, 0.64) to 0.57 (95% CI: 0.40, 0.74) between reading sessions. Observation size had a trend level effect on rim APHE agreement (p = 0.052). CONCLUSION: Approximately 1/3 of observations demonstrated inconsistent APHE subtype during mHAP acquisition. Small lesions were particularly challenging. Further guidance on APHE subtype classification, especially when applied to mHAP, could be a focus of LI-RADS refinement. KEY POINTS: • In a cohort of patients at risk for HCC, 28% of the observations showed inconsistent arterial phase hyperenhancement (APHE) subtypes (rim and nonrim) on multi-arterial phase imaging according to the majority score of 5 independent readers. • Inconsistent APHE subtypes may challenge reliable imaging diagnosis, i.e., LI-RADS categorization, of focal liver observations in patients at risk for HCC.

CNN color-coded difference maps accurately display longitudinal changes in liver MRI-PDFF.

OBJECTIVES: To assess the feasibility of a CNN-based liver registration algorithm to generate difference maps for visual display of spatiotemporal changes in liver PDFF, without needing manual annotations. METHODS: This retrospective exploratory study included 25 patients with suspected or confirmed NAFLD, who underwent PDFF-MRI at two time points at our institution. PDFF difference maps were generated by applying a CNN-based liver registration algorithm, then subtracting follow-up from baseline PDFF maps. The difference maps were post-processed by smoothing (5 cm2 round kernel) and applying a categorical color scale. Two fellowship-trained abdominal radiologists and one radiology resident independently reviewed difference maps to visually determine segmental PDFF change. Their visual assessment was compared with manual ROI-based measurements of each Couinaud segment and whole liver PDFF using intraclass correlation (ICC) and Bland-Altman analysis. Inter-reader agreement for visual assessment was calculated (ICC). RESULTS: The mean patient age was 49 years (12 males). Baseline and follow-up PDFF ranged from 2.0 to 35.3% and 3.5 to 32.0%, respectively. PDFF changes ranged from - 20.4 to 14.1%. ICCs against the manual reference exceeded 0.95 for each reader, except for segment 2 (2 readers ICC = 0.86-0.91) and segment 4a (reader 3 ICC = 0.94). Bland-Altman limits of agreement were within 5% across all three readers. Inter-reader agreement for visually assessed PDFF change (whole liver and segmental) was excellent (ICCs > 0.96), except for segment 2 (ICC = 0.93). CONCLUSIONS: Visual assessment of liver segmental PDFF changes using a CNN-generated difference map strongly agreed with manual estimates performed by an expert reader and yielded high inter-reader agreement. KEY POINTS: • Visual assessment of longitudinal changes in quantitative liver MRI can be performed using a CNN-generated difference map and yields strong agreement with manual estimates performed by expert readers.

Imaging diagnosis of hepatocellular carcinoma: LI-RADS.

Liver cancer is the third most common cause of cancer related death worldwide, 90% being hepatocellular carcinoma (HCC) and about half of all HCCs estimated to occur in China. Imaging plays a pivotal role in the management of HCC. When stringent criteria are applied to at-risk populations, it enables HCCs to be diagnosed by imaging alone without further need of invasive histology confirmation. To optimize HCC imaging diagnosis and reporting, several systems have been proposed. The Liver Imaging Reporting and Data System (LI-RADS®) is currently the most comprehensive of these systems, providing guidance on all imaging-related aspects of HCC, from technique for acquisition, reporting, assessment of treatment response and management. For diagnosis, LI-RADS uses major and ancillary imaging features to assign hierarchical categories that communicate the relative probability of HCC to focal liver observations detected in patients at risk. Two LI-RADS algorithms yield high specificity and positive predictive value for HCC diagnosis on contrast enhanced ultrasound (CEUS), CT and MRI. The standardized lexicon and interpretation provided by LI-RADS also improve inter-reader agreement for imaging features and lesion categorization. Additionally, a LI-RADS treatment response algorithm (LR-TR) provide imaging criteria for assessment of response to locoregional therapy. LI-RADS is designed for universal adoption and in this review, we highlighted the most relevant aspects of LI-RADS for the diagnosis of HCC in clinical practice and discussed areas where LI-RADS and Asian guidelines are different.

Alternative approach of hepatocellular carcinoma surveillance: abbreviated MRI.

This review focuses on emerging abbreviated magnetic resonance imaging (AMRI) surveillance of patients with chronic liver disease for hepatocellular carcinoma (HCC). This surveillance strategy has been proposed as a high-sensitivity alternative to ultrasound for identification of patients with early-stage HCC, particularly in patients with cirrhosis or obesity, in whom sonographic visualization of small tumors may be compromised. Three general AMRI approaches have been developed and studied in the literature - non-contrast AMRI, dynamic contrast-enhanced AMRI, and hepatobiliary phase contrast-enhanced AMRI - each comprising a small number of selected sequences specifically tailored for HCC detection. The rationale, general technique, advantages and disadvantages, and diagnostic performance of each AMRI approach is explained. Additionally, current gaps in knowledge and future directions are discussed. Based on emerging evidence, we cautiously recommend the use of AMRI for HCC surveillance in situations where ultrasound is compromised.

Imaging Diagnosis of Hepatocellular Carcinoma: The Liver Imaging Reporting and Data System, Why and How?

The Liver Imaging Reporting and Data System (LI-RADS) provides standardized lexicon, technique, interpretation, and reporting of liver imaging in patients at risk for hepatocellular carcinoma (HCC). When applied to at-risk populations, LI-RADS achieves higher than 95% positive predictive value for the noninvasive diagnosis of HCC on computed tomography (CT), MRI and contrast-enhanced ultrasound (CEUS). This article focuses on similarities and differences between the CT/MRI diagnostic algorithm (CT/MRI LI-RADS) and the CEUS diagnostic algorithm (CEUS LI-RADS) to inform health care professionals for efficient and appropriate clinical decisions through the management of patients at risk.

Efficacy of a 2-Month Very Low-Calorie Ketogenic Diet (VLCKD) Compared to a Standard Low-Calorie Diet in Reducing Visceral and Liver Fat Accumulation in Patients With Obesity.

Background: Currently the treatment of non-alcoholic fatty liver disease (NAFLD) is based on weight loss through lifestyle changes, such as exercise combined with calorie-restricted dieting. Objectives: To assess the effects of a commercially available weight loss program based on a very low-calorie ketogenic diet (VLCKD) on visceral adipose tissue (VAT) and liver fat content compared to a standard low-calorie (LC) diet. As a secondary aim, we evaluated the effect on liver stiffness measurements. Methods: Open, randomized controlled, prospective pilot study. Patients were randomized and treated either with an LC or a VLCKD and received orientation and encouragement to physical activity equally for both groups. VAT, liver fat fraction, and liver stiffness were measured at baseline and after 2 months of treatment using magnetic resonance imaging. Paired t-tests were used for comparison of continuous variables between visits and unpaired test between groups. Categorical variables were compared using the χ2-test. Pearson correlation was used to assess the association between VAT, anthropometric measures, and hepatic fat fraction. A significance level of the results was established at p < 0.05. Results: Thirty-nine patients (20 with VLCKD and 19 with LC) were evaluated at baseline and 2 months of intervention. Relative weight loss at 2 months was -9.59 ± 2.87% in the VLCKD group and -1.87 ± 2.4% in the LC group (p < 0.001). Mean reductions in VAT were -32.0 cm2 for VLCKD group and -12.58 cm2 for LC group (p < 0.05). Reductions in liver fat fraction were significantly more pronounced in the VLCKD group than in the LC group (4.77 vs. 0.79%; p < 0.005). Conclusion: Patients undergoing a VLCKD achieved superior weight loss, with significant VAT and liver fat fraction reductions when compared to the standard LC diet. The weight loss and rapid mobilization of liver fat demonstrated with VLCKD could serve as an effective alternative for the treatment of NAFLD. Clinical Trial Registration: ClinicalTrials.gov, identifier: NCT04322110.

Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time.

PURPOSE: To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations. METHODS: We retrospectively identified EOB-enhanced MRI-HBP series from examinations performed 2011-2018 (internal and external datasets). Our algorithm, comprising a liver segmentation and classification CNN, produces an adequacy score. Two abdominal radiologists independently classified series as adequate or suboptimal. The consensus determination of HBP adequacy was used as ground truth for CNN model training and validation. Reader agreement was evaluated with Cohen's kappa. Performance of the algorithm was assessed by receiver operating characteristics (ROC) analysis and computation of the area under the ROC curve (AUC). Potential examination duration reduction was evaluated descriptively. RESULTS: 1408 HBP series from 484 patients were included. Reader kappa agreement was 0.67 (internal dataset) and 0.80 (external dataset). AUCs were 0.97 (0.96-0.99) for internal and 0.95 (0.92-96) for external and were not significantly different from each other (p = 0.24). 48 % (50/105) examinations could have been shorter by applying the algorithm. CONCLUSION: A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.

Accuracy of common proton density fat fraction thresholds for magnitude- and complex-based chemical shift-encoded MRI for assessing hepatic steatosis in patients with obesity.

PURPOSE: MRI proton density fat fraction (PDFF) can be calculated using magnitude (MRI-M) or complex (MRI-C) MRI data. The purpose of this study was to identify, assess, and compare the accuracy of common PDFF thresholds for MRI-M and MRI-C for assessing hepatic steatosis in patients with obesity, using histology as reference. METHODS: This two-center prospective study included patients undergoing MRI-C- and MRI-M-PDFF estimations within 3 days before weight loss surgery. Liver biopsy was performed, and histology-determined steatosis grades were used as reference standard. Using receiver operating characteristics (ROC) analysis on data pooled from both methods, single common thresholds for diagnosing and differentiating none or mild (0-1) from moderate to severe steatosis (2-3) were selected as the ones achieving the highest sensitivity while providing at least 90% specificity. Selection methods were cross-validated. Performances were compared using McNemar's tests. RESULTS: Of 81 included patients, 54 (67%) had steatosis. The common PDFF threshold for diagnosing steatosis was 5.4%, which provided a cross-validated 0.88 (95% CI 0.77-0.95) sensitivity and 0.92 (0.75-0.99) specificity for MRI-M and 0.87 sensitivity (0.75-0.94) with 0.81 (0.61-0.93) specificity for MRI-C. The common PDFF threshold to differentiate steatosis grades 0-1 from 2 to 3 was 14.7%, which provided cross-validated 0.86 (95% CI 0.59-0.98) sensitivity and 0.95 (0.87-0.99) specificity for MRI-M and 0.93 sensitivity (0.68-0.99) with 0.97(0.89-0.99) specificity for MRI-C. CONCLUSION: If independently validated, diagnostic thresholds of 5.4% and 14.7% could be adopted for both techniques for detecting and differentiating none to mild from moderate to severe steatosis, respectively, with high diagnostic accuracy.

Fully automated convolutional neural network-based affine algorithm improves liver registration and lesion co-localization on hepatobiliary phase T1-weighted MR images.

BACKGROUND: Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning or motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series and compared its performance to manual image registration. METHODS: Three hundred fourteen patients, including internal and external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance imaging for clinical care from 2011 to 2018, were retrospectively selected. Automated registration was applied to all 2,663 within-patient series pairs derived from these datasets. Additionally, 100 within-patient series pairs from the internal dataset were independently manually registered by expert readers. Liver overlap, image correlation, and intra-observation distances for manual versus automated registrations were compared using paired t tests. Influence of patient demographics, imaging characteristics, and liver uptake function was evaluated using univariate and multivariate mixed models. RESULTS: Compared to the manual, automated registration produced significantly lower intra-observation distance (p < 0.001) and higher liver overlap and image correlation (p < 0.001). Intra-exam automated registration achieved 0.88 mean liver overlap and 0.44 mean image correlation for the internal dataset and 0.91 and 0.41, respectively, for the external dataset. For inter-exam registration, mean overlap was 0.81 and image correlation 0.41. Older age, female sex, greater inter-series time interval, differing uptake, and greater voxel size differences independently reduced automated registration performance (p ≤ 0.020). CONCLUSION: A fully automated algorithm accurately registered the liver within and between examinations, yielding better liver and focal observation co-localization compared to manual registration.