Search

Introduction: Leg length is an important consideration in total hip arthroplasty (THA) as leg length discrepancies (LLD) after THA cause poor outcomes and medical litigation. This study aimed to investigate the accuracy of computed tomography (CT)-based navigation with augmented reality (AR) technology for measuring intra-operative leg length change using anteroposterior radiography (two-dimensional, 2D) and CT (three-dimensional, 3D). Materials and methods: This study included 71 patients (75 hips) who underwent primary cementless THA in the supine position between June 2022 and November 2023 using the HoloNavi One. To assess the accuracy of the HoloNavi One based on 2D and 3D measurements, the absolute error between the intra-operative leg length change and the 2D and 3D measurements was evaluated, and the correlations were investigated. Additionally, factors affecting the absolute error were examined using multivariate analysis. Results: The mean intra-operative leg length change when using the HoloNavi One was 6.5 ± 5.0 mm, while the mean leg length change on the 2D and 3D measurements were 5.9 ± 4.8 mm and 4.6 ± 5.7 mm, respectively. The mean absolute errors were 2.3 ± 2.7 mm between the HoloNavi One and 2D measurements, and 3.8 ± 3.3 mm between HoloNavi One and 3D measurements. The absolute errors in leg length changes for the 3D measurements were greater than those for the 2D measurements (p < 0.01). Positive correlations of leg length changes were found between the HoloNavi One and the 2D and 3D measurements. In the multiple regression analysis, no significant factors affecting the absolute error were identified in either the 2D or 3D measurements. Conclusions: CT-based navigation with AR technology in the supine position provided acceptable accuracy for leg length change measurements. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the effect of deep learning reconstruction (DLR) on vascular depiction, tumor enhancement, and image quality of computed tomography hepatic arteriography (CTHA) images acquired during transcatheter arterial chemoembolization (TACE). Methods: Institutional review board approval was obtained. Twenty-seven patients (18 men and 9 women, mean age, 75.7 years) who underwent CTHA immediately before TACE were enrolled. All images were reconstructed using three reconstruction algorithms: hybrid-iterative reconstruction (hybrid-IR), DLR with mild strength (DLR-M), and DLR with strong strength (DLR-S). Vascular depiction, tumor enhancement, feeder visualization, and image quality of CTHA were quantitatively and qualitatively assessed by two radiologists and compared between the three reconstruction algorithms. Results: The mean signal-to-noise ratios (SNR) of sub-segmental arteries and sub-sub-segmental arteries, and the contrast-to-noise ratio (CNR) of tumors, were significantly higher on DLR-S than on DLR-M and hybrid-IR (P < 0.001). The mean qualitative score for sharpness of sub-segmental and sub-sub-segmental arteries was significantly better on DLR-S than on DLR-M and hybrid-IR (P < 0.001). There was no significant difference in the feeder artery detection rate of automated feeder artery detection software among three reconstruction algorithms (P = 0.102). The contrast, continuity, and confidence level of feeder artery detection was significantly better on DLR-S than on DLR-M (P = 0.013, 0.005, and 0.001) and hybrid-IR (P < 0.001, P = 0.002, and P < 0.001). The weighted kappa values between two readers for qualitative scores of feeder artery visualization were 0.807–0.874. The mean qualitative scores for sharpness, granulation, and diagnostic acceptability of CTHA were better on DLR-S than on DLR-M and hybrid-IR (P < 0.001). Conclusions: DLR significantly improved the SNR of small hepatic arteries, the CNR of tumor, and feeder artery visualization on CTHA images. DLR-S seems to be better suited to routine CTHA in TACE than does hybrid-IR. [ABSTRACT FROM AUTHOR]

Obtaining an imaging diagnosis of various hepatobiliary and pancreatic disorders caused by certain drugs can often be challenging. Familiarity with these conditions may improve diagnostic accuracy and patient management. This review aimed to describe the imaging findings of drug-associated hepatobiliary and pancreatic disorders and identify suggestions for obtaining a correct diagnosis. We focused on relatively common disorders or those that can present with characteristic imaging findings, such as drug-induced acute hepatitis, sinusoidal obstruction syndrome, focal nodular hyperplasia-like lesions, hepatocellular adenoma, pseudocirrhosis, chemotherapy-associated steatohepatitis, amiodarone deposition in the liver, secondary iron overload, drug-induced pancreatitis, pancreatic enlargement after epoprostenol therapy, ceftriaxone-associated gallbladder pseudolithiasis, immune-related adverse events, and methotrexate-associated lymphoproliferative disorders. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the diagnostic performance of MRI-based radiomics model for differentiating phyllodes tumors of the breast from fibroadenomas. Methods: This retrospective study included 88 patients (32 with phyllodes tumors and 56 with fibroadenomas) who underwent MRI. Radiomic features were extracted from T2-weighted image, pre-contrast T1-weighted image, and the first-phase and late-phase dynamic contrast-enhanced MRIs. To create stable machine learning models and balanced classes, data augmentation was performed. A least absolute shrinkage and selection operator (LASSO) regression was performed to select features and build the radiomics model. A radiological model was constructed from conventional MRI features evaluated by radiologists. A combined model was constructed using both radiomics features and radiological features. Machine learning classifications were done using support vector machine, extreme gradient boosting, and random forest. The area under the receiver operating characteristic (ROC) curve (AUC) was computed to assess the performance of each model. Results: Among 1070 features, the LASSO logistic regression selected 35 features. Among three machine learning classifiers, support vector machine had the best performance. Compared to the radiological model (AUC: 0.77 ± 0.11), the radiomics model (AUC: 0.96 ± 0.04) and combined model (0.97 ± 0.03) had significantly improved AUC values (both p < 0.01) in the validation set. The combined model had a relatively higher AUC than that of the radiomics model in the validation set, but this was not significantly different (p = 0.391). Conclusions: Radiomics analysis based on MRI showed promise for discriminating phyllodes tumors from fibroadenomas. Key Points: • The radiomics model and the combined model were superior to the radiological model for differentiating phyllodes tumors from fibroadenomas. • The SVM classifier performed best in the current study. • MRI-based radiomics model could help accurately differentiate phyllodes tumors from fibroadenomas. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Purpose: To compare computed diffusion-weighted imaging (cDWI) feasibility with that of directly acquired DWI for visualizing pancreatic ductal adenocarcinoma (PDAC) and focal autoimmune pancreatitis (AIP). Methods: From April 2012 to January 2017, 135 patients with PDAC (n = 111) or focal AIP (n = 24) were retrospectively enrolled. They underwent DWI with b-values of 0, 500, and 1000 s/mm2. From DWI0 and DWI1000, we generated cDWIs with targeted b-values of 1500, 2000, and 3000 s/mm2. The lesions' signal intensities, image quality, signal intensity ratio (SIR) of lesions and pancreatic parenchyma to spinal cord, and lesion-to-pancreatic parenchyma contrast ratio (CR) were compared among the five DWI protocols (DWI500, DWI1000, cDWI1500, cDWI2000, and cDWI3000). SIR was analyzed by receiver operating characteristic (ROC) analyses. Results: DWI500, DWI1000, and cDWI1500 had higher image quality than cDWI2000 and cDWI3000 (P < 0.001). The incidence of clear hyperintense PDAC was highest on cDWI2000, followed by cDWI1500, and cDWI3000 (P < 0.001–0.002), while the incidence of clear hyperintense AIP was higher on DWI1000, cDWI1500, and cDWI2000 than on DWI500 and cDWI3000 (P = 0.001–0.022). SIRs decreased whereas CRs increased as the b-value increased, for both PDAC and AIP. The area under the ROC curve (AUC) of SIRlesion was significantly lower on cDWI1500 than on cDWI2000 and cDWI3000 (P < 0.001). Conclusion: cDWI1500 or cDWI2000 generated from b-values of 0 and 1000 s/mm2 were the most effective for visualizing PDAC and focal AIP; however, the SIRlesion AUC was significantly lower on cDWI1500 than on cDWI2000 and cDWI3000. [ABSTRACT FROM AUTHOR]

Objectives: To determine imaging hallmarks for distinguishing intrahepatic mass-forming biliary carcinomas (IMBCs) from hepatocellular carcinoma (HCC) and to validate their diagnostic ability using Bayesian statistics. Methods: Study 1 retrospectively identified clinical and imaging hallmarks that distinguish IMBCs (n = 41) from HCC (n = 247) using computed tomography (CT) and magnetic resonance imaging (MRI). Study 2 retrospectively assessed the diagnostic ability of these hallmarks to distinguish IMBCs (n = 37) from HCC (n = 111) using Bayesian statistics with images obtained from a different institution. We also assessed the diagnostic ability of the hallmarks in the patient subgroup with high diagnostic confidence (≥ 80% of post-test probability). Two radiologists independently evaluated the imaging findings in studies 1 and 2. Results: In study 1, arterial phase peritumoral parenchymal enhancement on CT/MRI, delayed enhancement on CT/MRI, diffusion-weighted imaging peripheral hyperintensity, and bile duct dilatation were hallmarks indicating IMBCs, whereas chronic liver disease, non-rim arterial phase hyperenhancement on CT/MRI, enhancing capsule on CT/MRI, and opposed-phase signal drop were hallmarks indicating HCC (p = 0.001–0.04). In study 2, Bayesian statistics-based post-test probability combining all hallmark features had a diagnostic accuracy of 89.2% (132/148) in distinguishing IMBCs from HCC for both readers. In the high diagnostic confidence subgroup (n = 120 and n = 124 for readers 1 and 2, respectively), the accuracy improved (95.0% (114/120) and 93.5% (116/124) for readers 1 and 2, respectively). Conclusions: Combined interpretation of CT and MRI to identify hallmark features is useful in discriminating IMBCs from HCCs. High post-test probability by Bayesian statistics allows for a more reliable non-invasive diagnosis. Key Points: • Combined interpretation of CT and MRI to identify hallmark features was useful in discriminating intrahepatic mass-forming biliary carcinomas from hepatocellular carcinoma. • Bayesian method-based post-test probability combining all hallmark features determined in study 1 showed high (> 90%) sensitivity and specificity for distinguishing intrahepatic mass-forming biliary carcinomas from hepatocellular carcinoma. • If the post-test probability or the confidence was ≥ 80% when combining the imaging features of CT and MRI, the high specificity of > 95% was achieved without any loss of sensitivity to distinguish hepatocellular carcinoma from intrahepatic mass-forming biliary carcinomas. [ABSTRACT FROM AUTHOR]

Purpose: To identify gadoxetate disodium-enhanced MRI features distinguishing hepatic IPT from CLM. Methods: From February 2008 to December 2019, 162 lesions (IPT, n = 31 and CLM, n = 131) from 94 patients (mean age 65.1 ± 12.2 years; 65 men and 29 women) were retrospectively assessed for the presence or absence of obscure boundary, rim enhancement on arterial phase (AP), persistent rim enhancement during AP to transitional phase (TP), blood vessel penetration, peritumoral parenchymal enhancement on AP, peritumoral parenchymal hypointensity on hepatobiliary phase (HBP), peritumoral parenchymal hyperintensity on T2-weighted imaging (T2WI), biliary dilatation, central hypointensity with a relatively hyperintense periphery on HBP, peripheral hyperintensity on diffusion-weighted imaging (DWI) and T2WI, and lesion to liver signal intensity ratio (SIRlesion/liver) on HBP and DWI. Relevant features for differentiating between ITP and CLM were identified by univariate and multivariate analyses. Results: Univariate analysis revealed significantly higher frequencies of the following features in IPT than CLM: younger age, obscure boundary, blood vessel penetration, central hypointensity with a relatively hyperintense periphery on HBP, higher SIRlesion/liver on HBP, and lower SIRlesion/liver on DWI (P < 0.001‒0.035). Rim enhancement on AP and persistent rim enhancement during AP to TP were significantly more common in CLM than in IPT (P ≤ 0.001). Multivariate analysis revealed that a central hypointensity with a relatively peripheral hyperintensity on HBP, higher SIRlesion/liver on HBP, and lower SIRlesion/liver on DWI were predictive of IPT (P = 0.003‒0.039). Conclusion: Central hypointensity with a relatively peripheral hyperintensity on HBP and SIRlesion/liver on HBP and DWI may be reliable gadoxetate disodium-enhanced MRI features for distinguishing IPT from CLM. [ABSTRACT FROM AUTHOR]

Objective: To evaluate the usefulness of longitudinal observation of liver stiffness measured using magnetic resonance elastography (MRE) to stratify the risk of hepatocellular carcinoma (HCC) in patients with chronic liver disease.Materials and Methods: We retrospectively reviewed data for 161 patients with chronic liver disease using the following inclusion criteria: two MRE examinations separated by at least a 12-month interval, no history of HCC, no development of HCC between the two examinations and availability of laboratory results. Liver stiffness was classified as low (< 3 kPa), moderate (3-4.7 kPa) or high (> 4.7 kPa). The patients were divided into three groups according to sequential changes in liver stiffness as follows: high on the first MRE (group A, n = 60), low on both MRE examinations (group C, n = 36) and other combinations (group B, n = 65). Cox analyses and Kaplan-Meier methods were used to determine the risk of developing HCC.Results: Forty-seven patients (29.2%) developed HCC during follow-up (46.7% [28/60] in group A, 26.2% [17/65] in group B, and 5.6% [2/36] in group C). There was a significant difference in the rate of development of HCC between groups A (45.1%), B (26.1%) and C (12.4%) at 3 years (p = 0.0002). The independent risk factors for development of HCC were group A classification, age and a high alanine aminotransferase level (risk ratio 1.018-6.030; p = 0.0028-0.0268).Conclusion: Longitudinal observation of liver stiffness using MRE can stratify the risk of HCC during follow-up of chronic liver disease.Key Points: • The results of MRE can stratify the risk for development of HCC during follow-up in patients with chronic liver disease. • Patients with chronic liver disease and high liver stiffness (> 4.7 kPa) on a previous MRE examination are at high risk for developing HCC, regardless of current liver stiffness. • Management of patients with chronic liver disease becomes more appropriate using longitudinally acquired two-point MRE data. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the prognostic value of preoperative 18-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) in patients with potentially resectable pancreatic cancer.Methods: The study included 103 consecutive patients with potentially resectable pancreatic cancer who underwent preoperative FDG-PET/CT. Age, sex, blood glucose level, tumor marker levels (carcinoembryonic antigen (CEA), carbohydrate antigen 19-9 (CA19-9)), PET-related parameters (maximum standardized uptake value (SUVmax)), and contrast-enhanced CT-related factors (tumor size, location, enhancement pattern, and CT-based T and N factors by tumor nodes metastasis (TNM) classification) were assessed for their ability to independently predict postoperative tumor recurrence using Cox proportional hazards model.Results: Median follow-up was 23.1 months. Univariate analyses revealed that SUVmax (P = 0.0004), tumor size (P = 0.0002), T factor (P = 0.0102), N factor (P = 0.0049), and CA19-9 levels (P = 0.0059) were significantly associated with disease-free survival (DFS). In multivariate analysis, SUVmax (P = 0.0163) and CA19-9 levels (P = 0.0364) independently predicted DFS. Kaplan-Meier analysis revealed that patients with low (< 2.5) SUVmax had a significantly better prognosis than those with higher SUVmax (P = 0.0006). The DFS in patients with SUVmax < 2.5 (n = 23) and SUVmax ≥ 2.5 (n = 80) was 61.9% and 9.7%, respectively, 3 years postoperatively.Conclusions: SUVmax can predict DFS in patients with resectable pancreatic cancer. A SUVmax < 2.5 heralds a better prognosis. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the longitudinal risk to patients with cirrhosis of hypervascular hepatocellular carcinoma (HCC) developing from hypovascular hepatic nodules that show positive uptake of gadoxetic acid (hyperintensity) on hepatocyte phase images.Methods: In 69 patients, we evaluated findings from serial follow-up examinations of 633 hepatic nodules that appeared hypovascular and hyperintense on initial gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI) until the nodules demonstrated hypervascularity and were diagnosed as hypervascular HCC. Cox analyses were performed to identify risk factors for the development of hypervascular HCCs from the nodules.Results: The median follow-up was 663 days (range, 110 to 1215 days). Hypervascular HCCs developed in six of the 633 nodules (0.9 %) in five of the 69 patients. The only independent risk factor, the nodule's initial maximum diameter of 10 mm or larger, demonstrated a hazard ratio of 1.25. The one-year risk of hypervascular HCC developing from a nodule was 0.44 %. The risk was significantly higher for nodules of larger diameter (1.31 %) than those smaller than 10 mm (0.10 %, p < 0.01).Conclusions: Hypervascular HCC rarely develops from hypovascular, hyperintense hepatic nodules. We observed low risk even for nodules of 10 mm and larger diameter at initial examination.Key Points: • Hypervascularization was rare on follow-up examination of hypovascular, hyperintense nodules • The risk of hypervascularization in a nodule increased with large size • Hypovascular, hyperintense nodules require neither treatment nor more intense follow-up. [ABSTRACT FROM AUTHOR]

Objective: To examine if liver stiffness measured by magnetic resonance elastography (MRE) is a risk factor for hepatocellular carcinoma (HCC) in patients with chronic liver disease.Methods: By reviewing the records of magnetic resonance (MR) examinations performed at our institution, we selected 301 patients with chronic liver disease who did not have a previous medical history of HCC. All patients underwent MRE and gadoxetic acid-enhanced MR imaging. HCC was identified on MR images in 66 of the 301 patients, who were matched to controls from the remaining patients without HCC according to age. MRE images were obtained by visualising elastic waves generated in the liver by pneumatic vibration transferred via a cylindrical passive driver. Risk factors of HCC development were determined by the odds ratio with logistic regression analysis; gender and liver stiffness by MRE and serum levels of aspartate transferase, alanine transferase, alpha-fetoprotein, and protein induced by vitamin K absence-II.Results: Multivariate analysis revealed that only liver stiffness by MRE was a significant risk factor for HCC with an odds ratio (95 % confidence interval) of 1.38 (1.05-1.84).Conclusion: Liver stiffness measured by MRE is an independent risk factor for HCC in patients with chronic liver disease. [ABSTRACT FROM AUTHOR]

Aim: To examine if it is possible to shorten the examination time of gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid (Gd-EOB)-enhanced MRI by omitting hepatocyte-phase images of 20-min delay time (Im-20) for detecting focal liver lesions.Materials and Methods: Four hundred ninety-five malignant focal liver lesions observed on Im-20 in 265 patients were included. The hepatocyte phase was obtained 10 min (Im-10) and 20 min (Im-20) after Gd-EOB injection. Liver enhancement was evaluated using a 4-point scale [excellent/good/poor/non-diagnostic; visual liver-spleen contrast (V-LSC)] and a quantitative liver-spleen contrast ratio (Q-LSC). Two radiologists evaluated lesion conspicuity for assessing the sensitivity of lesion detection. As Im-20 was used as the standard of reference for the lesions, Im-20 artificially had 100% sensitivity.Results: The results showed that although sensitivities and Q-LSC significantly increased from Im-10 to Im-20 (sensitivity/mean Q-LSC: Im-5, 81%/1.4 Im-10, 96%/1.7: Im-20, 100%/1.9), the sensitivity of Im-10 achieved 100% (the same as Im-20) in patients with good/excellent V-LSC or Q-LSC of more than 1.5. On Im-10, 202 patients (77%) were assigned as having good/excellent V-LSC (78%), and 161 (61%) were assigned as having Q-LSC of more than 1.5.Conclusion: We concluded that Im-20 can be omitted in at least 61% of the patients. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]