Color stability and translucency of newly developed composites for splinting teeth.

This study aimed to investigate the colorimetric properties of newly developed composites for dental trauma splints using various staining solutions during the clinical splinting period. The clear shades of G-Fix (GF), Ortho Connect Flow (OC), Light Fix (LF), and Filtek Z350XT (FZ) were fabricated into 96 disk-shaped specimens. Specimens from each composite group were stored in distilled water, coffee, tea, and red wine solutions at 37ºC. CIE values were measured using a spectrophotometer at 24 h after specimen preparation and at 1 day, 1 week, 2 weeks, 3 weeks, and 4 weeks after storage in each solution. Color differences and translucency parameters were calculated using the initial and measured values. Within the experiment period, the color differences of GF, OC, and LF compared to the initial measurement were smaller than that for FZ for all staining solutions except distilled water. There were no significant color differences between the GF, OC, and LF groups.

Image segmentation of impacted mesiodens using deep learning.

This study aimed to evaluate the performance of deep learning algorithms for the classification and segmentation of impacted mesiodens in pediatric panoramic radiographs. A total of 850 panoramic radiographs of pediatric patients (aged 3-9 years) was included in this study. The U-Net semantic segmentation algorithm was applied for the detection and segmentation of mesiodens in the upper anterior region. For enhancement of the algorithm, pre-trained ResNet models were applied to the encoding path. The segmentation performance of the algorithm was tested using the Jaccard index and Dice coefficient. The diagnostic accuracy, precision, recall, F1-score and time to diagnosis of the algorithms were compared with those of human expert groups using the test dataset. Cohen's kappa statistics were compared between the model and human groups. The segmentation model exhibited a high Jaccard index and Dice coefficient (>90%). In mesiodens diagnosis, the trained model achieved 91-92% accuracy and a 94-95% F1-score, which were comparable with human expert group results (96%). The diagnostic duration of the deep learning model was 7.5 seconds, which was significantly faster in mesiodens detection compared to human groups. The agreement between the deep learning model and human experts is moderate (Cohen's kappa = 0.767). The proposed deep learning algorithm showed good segmentation performance and approached the performance of human experts in the diagnosis of mesiodens, with a significantly faster diagnosis time.

Fully automated deep learning approach to dental development assessment in panoramic radiographs.

BACKGROUND: Dental development assessment is an important factor in dental age estimation and dental maturity evaluation. This study aimed to develop and evaluate the performance of an automated dental development staging system based on Demirjian's method using deep learning. METHODS: The study included 5133 anonymous panoramic radiographs obtained from the Department of Pediatric Dentistry database at Seoul National University Dental Hospital between 2020 and 2021. The proposed methodology involves a three-step procedure for dental staging: detection, segmentation, and classification. The panoramic data were randomly divided into training and validating sets (8:2), and YOLOv5, U-Net, and EfficientNet were trained and employed for each stage. The models' performance, along with the Grad-CAM analysis of EfficientNet, was evaluated. RESULTS: The mean average precision (mAP) was 0.995 for detection, and the segmentation achieved an accuracy of 0.978. The classification performance showed F1 scores of 69.23, 80.67, 84.97, and 90.81 for the Incisor, Canine, Premolar, and Molar models, respectively. In the Grad-CAM analysis, the classification model focused on the apical portion of the developing tooth, a crucial feature for staging according to Demirjian's method. CONCLUSIONS: These results indicate that the proposed deep learning approach for automated dental staging can serve as a supportive tool for dentists, facilitating rapid and objective dental age estimation and dental maturity evaluation.

Correlation between dental and skeletal maturity in Korean children based on dental maturity percentile: a retrospective study.

BACKGROUND: The correlation between dental maturity and skeletal maturity has been proposed, but its clinical application remains challenging. Moreover, the varying correlations observed in different studies indicate the necessity for research tailored to specific populations. AIM: To compare skeletal maturity in Korean children with advanced and delayed dental maturity using dental maturity percentile. DESIGN: Dental panoramic radiographs and cephalometric radiographs were obtained from 5133 and 395 healthy Korean children aged between 4 and 16 years old. Dental maturity was assessed with Demirjian's method, while skeletal maturity was assessed with the cervical vertebral maturation method. Standard percentile curves were developed through quantile regression. Advanced (93 boys and 110 girls) and delayed (92 boys and 100 girls) dental maturity groups were defined by the 50th percentile. RESULTS: The advanced group showed earlier skeletal maturity in multiple cervical stages (CS) in both boys (CS 1, 2, 3, 4, and 6) and girls (CS 1, 3, 4, 5, and 6). Significant differences, as determined by Mann-Whitney U tests, were observed in CS 1 for boys (p = 0.004) and in CS 4 for girls (p = 0.037). High Spearman correlation coefficients between dental maturity and cervical vertebral maturity exceeded 0.826 (p = 0.000) in all groups. CONCLUSION: A correlation between dental and skeletal maturity, as well as advanced skeletal maturity in the advanced dental maturity group, was observed. Using percentile curves to determine dental maturity may aid in assessing skeletal maturity, with potential applications in orthodontic diagnosis and treatment planning.

LI-RADS CT and MRI Ancillary Feature Association with Hepatocellular Carcinoma and Malignancy: An Individual Participant Data Meta-Analysis.

Background The independent contribution of each Liver Imaging Reporting and Data System (LI-RADS) CT or MRI ancillary feature (AF) has not been established. Purpose To evaluate the association of LI-RADS AFs with hepatocellular carcinoma (HCC) and malignancy while adjusting for LI-RADS major features through an individual participant data (IPD) meta-analysis. Materials and Methods Medline, Embase, Cochrane Central Register of Controlled Trials, and Scopus were searched from January 2014 to January 2022 for studies evaluating the diagnostic accuracy of CT and MRI for HCC using LI-RADS version 2014, 2017, or 2018. Using a one-step approach, IPD across studies were pooled. Adjusted odds ratios (ORs) and 95% CIs were derived from multivariable logistic regression models of each AF combined with major features except threshold growth (excluded because of infrequent reporting). Liver observation clustering was addressed at the study and participant levels through random intercepts. Risk of bias was assessed using a composite reference standard and Quality Assessment of Diagnostic Accuracy Studies 2. Results Twenty studies comprising 3091 observations (2456 adult participants; mean age, 59 years ± 11 [SD]; 1849 [75.3%] men) were included. In total, 89% (eight of nine) of AFs favoring malignancy were associated with malignancy and/or HCC, 80% (four of five) of AFs favoring HCC were associated with HCC, and 57% (four of seven) of AFs favoring benignity were negatively associated with HCC and/or malignancy. Nonenhancing capsule (OR = 3.50 [95% CI: 1.53, 8.01]) had the strongest association with HCC. Diffusion restriction (OR = 14.45 [95% CI: 9.82, 21.27]) and mild-moderate T2 hyperintensity (OR = 10.18 [95% CI: 7.17, 14.44]) had the strongest association with malignancy. The strongest negative associations with HCC were parallels blood pool enhancement (OR = 0.07 [95% CI: 0.01, 0.49]) and marked T2 hyperintensity (OR = 0.18 [95% CI: 0.07, 0.45]). Seventeen studies (85%) had a high risk of bias. Conclusion Most LI-RADS AFs were independently associated with HCC, malignancy, or benignity as intended when adjusting for major features. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Crivellaro in this issue.

Combined Hepatocellular-Cholangiocarcinoma With Ductal Plate Malformation Pattern: A Case Report With Molecular Analysis.

Combined hepatocellular-cholangiocarcinoma with a ductal plate malformation pattern is an extremely rare entity with unelucidated pathogenesis. We present the case of a 60-year-old male patient who underwent a sectionectomy for pre-operative diagnosis of hepatocellular carcinoma based on clinical and image findings. Gross examination of the specimen revealed a well-defined tumor with cystic change measuring 6.7 × 6.2 cm. Microscopically, the lesion had classical features of hepatocellular carcinoma and intrahepatic cholangiocarcinoma exhibited neoplastic glands with irregular-sized dilated lumens, resembling a ductal plate malformation. Postoperative diagnosis was combined hepatocellular-cholangiocarcinoma with ductal plate malformation pattern. Next-generation sequencing revealed genomic alteration in 15 genes: CDKN2A, CHD4, CYP2D6, ERBB3, KIR3DL1, KRAS, MDM2, PIM1, STAT6, TPMT amplification, FANCD2, FAT1, FLT4, RASA1, and TP53 point mutation. This is the first case report of molecular alteration in combined hepatocellular-cholangiocarcinoma with ductal plate malformation pattern.

Individual Participant Data Meta-Analysis of LR-5 in LI-RADS Version 2018 versus Revised LI-RADS for Hepatocellular Carcinoma Diagnosis.

Background A simplification of the Liver Imaging Reporting and Data System (LI-RADS) version 2018 (v2018), revised LI-RADS (rLI-RADS), has been proposed for imaging-based diagnosis of hepatocellular carcinoma (HCC). Single-site data suggest that rLI-RADS category 5 (rLR-5) improves sensitivity while maintaining positive predictive value (PPV) of the LI-RADS v2018 category 5 (LR-5), which indicates definite HCC. Purpose To compare the diagnostic performance of LI-RADS v2018 and rLI-RADS in a multicenter data set of patients at risk for HCC by performing an individual patient data meta-analysis. Materials and Methods Multiple databases were searched for studies published from January 2014 to January 2022 that evaluated the diagnostic performance of any version of LI-RADS at CT or MRI for diagnosing HCC. An individual patient data meta-analysis method was applied to observations from the identified studies. Quality Assessment of Diagnostic Accuracy Studies version 2 was applied to determine study risk of bias. Observations were categorized according to major features and either LI-RADS v2018 or rLI-RADS assignments. Diagnostic accuracies of category 5 for each system were calculated using generalized linear mixed models and compared using the likelihood ratio test for sensitivity and the Wald test for PPV. Results Twenty-four studies, including 3840 patients and 4727 observations, were analyzed. The median observation size was 19 mm (IQR, 11-30 mm). rLR-5 showed higher sensitivity compared with LR-5 (70.6% [95% CI: 60.7, 78.9] vs 61.3% [95% CI: 45.9, 74.7]; P < .001), with similar PPV (90.7% vs 92.3%; P = .55). In studies with low risk of bias (n = 4; 1031 observations), rLR-5 also achieved a higher sensitivity than LR-5 (72.3% [95% CI: 63.9, 80.1] vs 66.9% [95% CI: 58.2, 74.5]; P = .02), with similar PPV (83.1% vs 88.7%; P = .47). Conclusion rLR-5 achieved a higher sensitivity for identifying HCC than LR-5 while maintaining a comparable PPV at 90% or more, matching the results presented in the original rLI-RADS study. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Sirlin and Chernyak in this issue.

Estimation of right lobe graft weight for living donor liver transplantation using deep learning-based fully automatic computed tomographic volumetry.

This study aimed at developing a fully automatic technique for right lobe graft weight estimation using deep learning algorithms. The proposed method consists of segmentation of the full liver region from computed tomography (CT) images, classification of the entire liver region into the right and left lobes, and estimation of the right lobe graft weight from the CT-measured right lobe graft volume using a volume-to-weight conversion formula. The first two steps were performed with a transformer-based deep learning model. To train and evaluate the model, a total of 248 CT datasets (188 for training, 40 for validation, and 20 for testing and clinical evaluation) were used. The Dice similarity coefficient (DSC), mean surface distance (MSD), and the 95th percentile Hausdorff distance (HD95) were used for evaluating the segmentation accuracy of the full liver region and the right liver lobe. The correlation coefficient (CC), percentage error (PE), and percentage absolute error (PAE) were used for the clinical evaluation of the estimated right lobe graft weight. The proposed method achieved high accuracy in segmentation for DSC, MSD, and HD95 (95.9% ± 1.0%, 1.2 ± 0.4 mm, and 5.2 ± 1.9 mm for the entire liver region; 92.4% ± 2.7%, 2.0 ± 0.7 mm, and 8.8 ± 2.9 mm for the right lobe) and in clinical evaluation for CC, PE, and PAE (0.859, - 1.8% ± 9.6%, and 8.6% ± 4.7%). For the right lobe graft weight estimation, the present study underestimated the graft weight by - 1.8% on average. A mean difference of - 21.3 g (95% confidence interval: - 55.7 to 13.1, p = 0.211) between the estimated graft weight and the actual graft weight was achieved in this study. The proposed method is effective for clinical application.

Criteria for early diagnosis of mandibular third molar agenesis based on the developmental stages of mandibular canine, first and second premolars, and second molar: a retrospective cohort study.

BACKGROUND: Permanent first molars with severe dental caries, developmental defects, or involved in oral pathologies are at risk of poor prognosis in children. Accordingly, using the third molar to replace the first molar can be a good treatment option when third molar agenesis is predicted early. Thus, this retrospective cohort study aimed to develop criteria for early detection of mandibular third molar (L8) agenesis based on the developmental stages of mandibular canine (L3), first premolar (L4), second premolar (L5), and second molar (L7). METHOD: Overall, 1,044 and 919 panoramic radiographs of 343 males and 317 females, respectively, taken between the ages of 6 and 12 years were included. All developmental stages of L3, L4, L5, L7, and L8 were analyzed based on the dental age, as suggested by Demirjian et al. The independent t-test was used to assess age differences between males and females. The rank correlation coefficients were examined using Kendall's tau with bootstrap analysis and Bonferroni's correction to confirm the teeth showing developmental stages most similar to those of L8s. Finally, a survival analysis was performed to determine the criteria for the early diagnosis of mandibular third molar agenesis. RESULTS: Some age differences were found in dental developmental stages between males and females. Correlation coefficients between all stages of L3, L4, L5, and L7 and L8 were high. In particular, the correlation coefficient between L7 and L8 was the highest, whereas that between L3 and L8 was the lowest. CONCLUSION: If at least two of the following criteria (F stage of L3, F stage of L4, F stage of L5, and E stage of L7) are met in the absence of L8 crypt, agenesis of L8 can be confirmed.

Non-Invasive Imaging Methods to Evaluate Non-Alcoholic Fatty Liver Disease with Fat Quantification: A Review.

Hepatic steatosis without specific causes (e.g., viral infection, alcohol abuse, etc.) is called non-alcoholic fatty liver disease (NAFLD), which ranges from non-alcoholic fatty liver (NAFL) to non-alcoholic steatohepatitis (NASH), fibrosis, and NASH-related cirrhosis. Despite the usefulness of the standard grading system, liver biopsy has several limitations. In addition, patient acceptability and intra- and inter-observer reproducibility are also concerns. Due to the prevalence of NAFLD and limitations of liver biopsies, non-invasive imaging methods such as ultrasonography (US), computed tomography (CT), and magnetic resonance imaging (MRI) that can reliably diagnose hepatic steatosis have developed rapidly. US is widely available and radiation-free but cannot examine the entire liver. CT is readily available and helpful for detection and risk classification, significantly when analyzed using artificial intelligence; however, it exposes users to radiation. Although expensive and time-consuming, MRI can measure liver fat percentage with magnetic resonance imaging proton density fat fraction (MRI-PDFF). Specifically, chemical shift-encoded (CSE)-MRI is the best imaging indicator for early liver fat detection. The purpose of this review is to provide an overview of each imaging modality with an emphasis on the recent progress and current status of liver fat quantification.

Reproducibility of MRI-derived liver surface nodularity score: analysis of patients with repeated MRI in various scanners.

PURPOSE: To assess trans-regional differences, reproducibility across different MRI scanners, and interobserver agreement of liver surface nodularity (LSN) score from routine liver MRI and to evaluate the correlation between LSN score and liver stiffness (LS) value on MR elastography. MATERIALS AND METHODS: Ninety patients who underwent gadoxetic acid-enhanced liver MRI twice using different MRI scanners within a year were evaluated. On axial hepatobiliary phase images, right anterior (LSNRT_ANT), right posterior (LSNRT_POST), and left anterior hepatic surface (LSNLT) were chosen for the quantification of LSN score. Repeated-measures ANOVA, paired t test, Pearson's correlation coefficient analysis, and intraclass correlation coefficient (ICC) were used for statistical analysis. RESULTS: LSN scores from high to low were LSNRT_POST, LSNRT_ANT, and LSNLT, representing trans-regional differences (p < 0.001). Reproducibility of LSN measurement across different MRI scanners was high to excellent (ICC = 0.838-0.921). The mean difference between first and second examinations in LSNRT_ANT, LSNRT_POST, and LSNLT were 0.032 (p = 0.013), 0.002 (p = 0.910), and 0.010 (p = 0.285) for reader 1 and 0.051 (p = 0.004), 0.061 (p = 0.002), and 0.023 (p = 0.005) for reader 2. The first and second examinations were highly correlated in all hepatic regions (r = 0.712-0.839, p < 0.001). There was a low to moderate correlation between LSN score and LS value (r = 0.364-0.592, p ≤ 0.001), which was higher in the chronic hepatitis B (CHB) group than in the non-CHB group in all hepatic regions. CONCLUSIONS: In our study, LSN measurement on liver MRI showed trans-regional differences and excellent reproducibility across different MRI scanners. To use LSN score more widely, standardization of quantification software and selected hepatic regions is needed.

Improved Single Breath-Hold SSFSE Sequence for Liver MRI Based on Compressed Sensing: Evaluation of Image Quality Compared with Conventional T2-Weighted Sequences.

The purpose of this study was to evaluate the image quality of compressed-sensing accelerated single-shot fast spin-echo (SSFSECS) sequences acquired within a single breath-hold in comparison with conventional SSFSE (SSFSECONV) and multishot TSE (mTSE). A total of 101 patients who underwent liver MRI at 3 T, including SSFSECONV (acquisition time (TA) = 58−62 s), mTSE (TA = 108 s), and SSFSECS (TA = 18 s), were included in this retrospective study. Two radiologists assessed the three sequences with respect to artifacts, organ sharpness, small structure visibility, overall image quality, and conspicuity of main lesions of liver and pancreas using a five-point evaluation scale system. Descriptive statistics and the Wilcoxon signed-rank test were used for statistical analysis. SSFSECS was significantly better than SSFSECONV and mTSE for artifacts, small structure visibility, overall image quality, and conspicuity of main lesions (p < 0.005). Regarding organ sharpness, mTSE and SSFSECS did not significantly differ (p = 0.554). Conspicuity of liver lesion did not significantly differ between SSFSECONV and mTSE (p = 0.404). SSFSECS showed superior image quality compared with SSFSECONV and mTSE despite a more than three-fold reduction in TA, suggesting a remarkable potential for saving time in liver imaging.

Can Bone Erosion in Axial Spondyloarthropathy be Detected by Ultrashort Echo Time Imaging? A Comparison With Computed Tomography in the Sacroiliac Joint.

BACKGROUND: Structural lesion evaluation in axial spondyloarthropathy (SpA) can improve accuracy of diagnosis. However, structural lesions (bone erosions) are difficult to be assessed using conventional MRI compared to computed tomography (CT). PURPOSE: To evaluate the diagnostic performance of ultrashort echo time (UTE) for detecting bone erosion in axial SpA compared to T1WI and three-dimensional double-echo steady-state (3D DESS) imaging using CT as the reference standard. STUDY TYPE: Retrospective. POPULATION: Fourteen patients (eight females, 57.1%) and 14 healthy controls (seven females, 50.0%) who underwent sacroiliac (SI) joint MRI and CT. FIELD STRENGTH/SEQUENCE: 3 T; TSE T1WI, 3D DESS, 2D UTE. ASSESSMENT: The bilateral SI joints were assessed for bone erosion. Three observers scored bone erosion for all three sequences of MRI. CT was used as the gold standard. Diagnostic confidence in axial SpA was measured based on a four-point confidence score. STATISTICAL TESTS: Correlation of erosion scores between CT and MRI were evaluated using Spearman's correlation test. Sensitivity, specificity, and positive-negative predictive values were calculated. Confidence scores were compared using the Wilcoxon sum rank test. Statistical significance was set at P < 0.05. RESULTS: Compared with erosion scores of CT, the correlation coefficients for each MRI sequence showed significant low-to-high positive correlations (0.39-0.72). UTE imaging showed the highest correlation coefficients for all observers (0.70, 0.72, and 0.67, respectively). The specificity of UTE imaging was equal or higher than those of T1WI and 3D DESS for all observers (0.86 vs. 0.71 vs. 0.57; 0.93 vs. 0.71 vs. 0.57; 0.79 vs. 0.79 vs. 0.43). All observers had the highest confidence in interpreting UTE imaging for detecting bone erosion among the three sequences (3.5, 3.4, and 3.3 for UTE; 3.1, 3.0, and 2.6 for T1WI; and 3.2, 2.7, and 2.4 for DESS). DATA CONCLUSION: UTE imaging can detect bone erosions in patients with axial SpA and show higher specificity than conventional T1WI and 3D DESS. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Identification of a Novel FAM83H Mutation and Management of Hypocalcified Amelogenesis Imperfecta in Early Childhood.

Amelogenesis imperfecta (AI) is a heterogeneous group of rare genetic disorders affecting amelogenesis during dental development. Therefore, the molecular genetic etiology of AI can provide information about the nature and progress of the disease. To confirm the genetic etiology of AI in a Korean family with an autosomal dominant inheritance, pedigree and mutational analyses were performed. DNA was isolated from the participating family members and whole-exome sequencing was performed with the DNA sample of the father of the proband. The identified mutation was confirmed by Sanger sequencing. The mutational analysis revealed a novel nonsense mutation in the FAM83H gene (NM_198488.5: c.1363C > T, p.(Gln455*)), confirming autosomal dominant hypocalcified AI. Full-mouth restorative treatments of the affected children were performed after the completion of the deciduous dentition. Early diagnosis of AI can be useful for understanding the nature of the disease and for managing the condition and treatment planning.

Intraindividual comparison of MRI-derived liver surface nodularity score at 1.5 T and 3 T.

PURPOSE: To compare the MRI-derived liver surface nodularity (LSN) scores acquired on both 1.5 T and 3 T. MATERIALS AND METHODS: Forty chronic liver disease patients who underwent gadoxetic acid-enhanced MRI at both 1.5 and 3 T were included. Axial hepatobiliary phase images with the same voxel size were used to calculate the LSN score in both liver lobes with a quantitative software. Rank correlation, Wilcoxon test, and Bland-Altman limits of agreement were used for statistical analysis. RESULTS: There was a weak correlation between the right and left liver lobe on 1.5 T (rs = 0.331, p = 0.037) and 3 T (rs = 0.381, p = 0.015). The correlation between 1.5 T and 3 T on both liver lobes showed a very strong correlation (right, rs = 0.927, p < 0.001; left, rs = 0.845, p < 0.001). LSN scores differed significantly between both lobes on 1.5 T (median, 1.201 vs. 0.674, right vs. left) and 3 T (1.076 vs. 0.592) (all p < 0.001). LSN scores differed significantly between 1.5 T and 3 T on both lobes (all p < 0.001). The Bland-Altman plot comparing 1.5 T and 3 T on right and left liver lobes showed a systemic bias of 0.08 and 0.07, respectively. CONCLUSIONS: LSN scores differed significantly on 1.5 T vs. 3 T and right vs. left liver lobe. Caution should be made when comparing LSN scores derived from different field strengths or the hepatic lobe. Interplatform, interlobar reproducibility should be resolved to use LSN scores, which is relatively easy to perform without additional hardware or images.

Noninvasive staging of liver fibrosis: review of current quantitative CT and MRI-based techniques.

Liver fibrosis features excessive protein accumulation in the liver interstitial space resulting from repeated tissue injury due to chronic liver disease. Liver fibrosis eventually proceeds to cirrhosis and associated complications. So, early diagnosis and staging of liver fibrosis are of vital importance for clinical treatment. Liver biopsy remains the gold standard for the diagnosing and staging of fibrosis, but it is suboptimal due to various limitations. Recently, efforts have been made to migrate toward noninvasive techniques for assessing liver fibrosis. CT is relatively easy to perform, relatively standardized for different scanners, and does not require additional hardware in liver fibrosis staging. MRI is frequently performed to characterize indeterminate liver lesions. Because it does not use ionizing radiation and features high image contrast, its role has increased in the staging of liver fibrosis. More recently, several studies on liver fibrosis staging using deep learning algorithms in CT or MRI have been proposed and have shown meaningful results. In this review, we summarize the basic concept, diagnostic performance, and advantages and limitations of each technique to noninvasively stage liver fibrosis.

CT/MRI and CEUS LI-RADS Major Features Association with Hepatocellular Carcinoma: Individual Patient Data Meta-Analysis.

Background The Liver Imaging Reporting and Data System (LI-RADS) assigns a risk category for hepatocellular carcinoma (HCC) to imaging observations. Establishing the contributions of major features can inform the diagnostic algorithm. Purpose To perform a systematic review and individual patient data meta-analysis to establish the probability of HCC for each LI-RADS major feature using CT/MRI and contrast-enhanced US (CEUS) LI-RADS in patients at high risk for HCC. Materials and Methods Multiple databases (MEDLINE, Embase, Cochrane Central Register of Controlled Trials, and Scopus) were searched for studies from January 2014 to September 2019 that evaluated the accuracy of CT, MRI, and CEUS for HCC detection using LI-RADS (CT/MRI LI-RADS, versions 2014, 2017, and 2018; CEUS LI-RADS, versions 2016 and 2017). Data were centralized. Clustering was addressed at the study and patient levels using mixed models. Adjusted odds ratios (ORs) with 95% CIs were determined for each major feature using multivariable stepwise logistic regression. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) (PROSPERO protocol: CRD42020164486). Results A total of 32 studies were included, with 1170 CT observations, 3341 MRI observations, and 853 CEUS observations. At multivariable analysis of CT/MRI LI-RADS, all major features were associated with HCC, except threshold growth (OR, 1.6; 95% CI: 0.7, 3.6; P = .07). Nonperipheral washout (OR, 13.2; 95% CI: 9.0, 19.2; P = .01) and nonrim arterial phase hyperenhancement (APHE) (OR, 10.3; 95% CI: 6.7, 15.6; P = .01) had stronger associations with HCC than enhancing capsule (OR, 2.4; 95% CI: 1.7, 3.5; P = .03). On CEUS images, APHE (OR, 7.3; 95% CI: 4.6, 11.5; P = .01), late and mild washout (OR, 4.1; 95% CI: 2.6, 6.6; P = .01), and size of at least 20 mm (OR, 1.6; 95% CI: 1.04, 2.5; P = .04) were associated with HCC. Twenty-five studies (78%) had high risk of bias due to reporting ambiguity or study design flaws. Conclusion Most Liver Imaging Reporting and Data System major features had different independent associations with hepatocellular carcinoma; for CT/MRI, arterial phase hyperenhancement and washout had the strongest associations, whereas threshold growth had no association. © RSNA, 2021 Online supplemental material is available for this article.