Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT.

OBJECTIVES: To develop and validate a combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT. METHODS: One hundred sixty-five patients with vertebral compression fractures were allocated to training (n = 110 [62 acute benign and 48 malignant fractures]) and validation (n = 55 [30 acute benign and 25 malignant fractures]) cohorts. Radiomics features (n = 144) were extracted from non-contrast-enhanced CT images. Radiomics score was constructed by applying least absolute shrinkage and selection operator regression to reproducible features. A combined radiomics-clinical model was constructed by integrating significant clinical parameters with radiomics score using multivariate logistic regression analysis. Model performance was quantified in terms of discrimination and calibration. The model was internally validated on the independent data set. RESULTS: The combined radiomics-clinical model, composed of two significant clinical predictors (age and history of malignancy) and the radiomics score, showed good calibration (Hosmer-Lemeshow test, p > 0.05) and discrimination in both training (AUC, 0.970) and validation (AUC, 0.948) cohorts. Discrimination performance of the combined model was higher than that of either the radiomics score (AUC, 0.941 in training cohort and 0.852 in validation cohort) or the clinical predictor model (AUC, 0.924 in training cohort and 0.849 in validation cohort). The model stratified patients into groups with low and high risk of malignant fracture with an accuracy of 98.2% in the training cohort and 90.9% in the validation cohort. CONCLUSIONS: The combined radiomics-clinical model integrating clinical parameters with radiomics score could predict malignancy in vertebral compression fractures on CT with high discriminatory ability. KEY POINTS: • A combined radiomics-clinical model was constructed to predict malignancy of vertebral compression fractures on CT by combining clinical parameters and radiomics features. • The model showed good calibration and discrimination in both training and validation cohorts. • The model showed high accuracy in the stratification of patients into groups with low and high risk of malignant vertebral compression fractures.

Preoperative prediction of postsurgical outcomes in mass-forming intrahepatic cholangiocarcinoma based on clinical, radiologic, and radiomics features.

OBJECTIVES: Current prognostic systems for intrahepatic cholangiocarcinoma (IHCC) rely on surgical pathology data and are not applicable to a preoperative setting. We aimed to develop and validate preoperative models to predict postsurgical outcomes in mass-forming IHCC patients based on clinical, radiologic, and radiomics features. METHODS: This multicenter retrospective cohort study included patients who underwent curative-intent resection for mass-forming IHCC. In the development cohort (single institution data), three preoperative multivariable Cox models for predicting recurrence-free survival (RFS) were constructed, including the clinical-radiologic, radiomics, and clinical-radiologic-radiomics (CRR) models based on clinical and CT findings, CT-radiomics features, and a combination of both, respectively. Model performance was evaluated in the test cohort (data from five institutions) using Harrell's C-index and compared with postoperative prognostic systems. RESULTS: A total of 345 patients (233, development cohort; 112, test cohort) were evaluated. The clinical-radiologic model included five independent CT predictors (infiltrative contour, multiplicity, periductal infiltration, extrahepatic organ invasion, and suspicious metastatic lymph node) and showed similar performance in predicting RFS to the radiomics model (C-index, 0.65 vs. 0.68; p = 0.43 in the test cohort). The CRR model showed significantly improved performance (C-index, 0.71; p = 0.01) than the clinical-radiologic model and demonstrated similar performance to the postoperative prognostic systems in predicting RFS (C-index, 0.71-0.73 vs. 0.70-0.73; p ≥ 0.40) and overall survival (C-index, 0.68-0.71 vs. 0.64-0.74; p ≥ 0.27) in the test cohort. CONCLUSIONS: A model integrating clinical, CT, and radiomics information may be useful for the preoperative assessment of postsurgical outcomes in patients with mass-forming IHCC. KEY POINTS: • The radiomics analysis had incremental value in predicting recurrence-free survival of patients with intrahepatic mass-forming cholangiocarcinoma. • The clinical-radiologic-radiomics model demonstrated similar performance to the postoperatively available prognostic systems (including 8th AJCC system) in predicting recurrence-free survival and overall survival. • The clinical-radiologic-radiomics model may be useful for the preoperative assessment of postsurgical outcomes in patients with mass-forming intrahepatic cholangiocarcinoma.

Radiomics and deep learning in liver diseases.

Recently, radiomics and deep learning have gained attention as methods for computerized image analysis. Radiomics and deep learning can perform diagnostic or predictive tasks using high-dimensional image-derived features and have the potential to expand the capabilities of liver imaging beyond the scope of traditional visual image analysis. Recent research has demonstrated the potential of these techniques in various fields of liver imaging, including staging of liver fibrosis, prognostication of malignant liver tumors, automated detection and characterization of liver tumors, automated abdominal organ segmentation, and body composition analysis. However, because most of the previous studies were preliminary and focused mainly on technical feasibility, further clinical validation is required for the application of radiomics and deep learning in clinical practice. In this review, we introduce the technical aspects of radiomics and deep learning and summarize the recent studies on the application of these techniques in liver radiology.

Netrin-1/DCC-mediated PLCγ1 activation is required for axon guidance and brain structure development.

Coordinated expression of guidance molecules and their signal transduction are critical for correct brain wiring. Previous studies have shown that phospholipase C gamma1 (PLCγ1), a signal transducer of receptor tyrosine kinases, plays a specific role in the regulation of neuronal cell morphology and motility in vitro However, several questions remain regarding the extracellular stimulus that triggers PLCγ1 signaling and the exact role PLCγ1 plays in nervous system development. Here, we demonstrate that PLCγ1 mediates axonal guidance through a netrin-1/deleted in colorectal cancer (DCC) complex. Netrin-1/DCC activates PLCγ1 through Src kinase to induce actin cytoskeleton rearrangement. Neuronal progenitor-specific knockout of Plcg1 in mice causes axon guidance defects in the dorsal part of the mesencephalon during embryogenesis. Adult Plcg1-deficient mice exhibit structural alterations in the corpus callosum, substantia innominata, and olfactory tubercle. These results suggest that PLCγ1 plays an important role in the correct development of white matter structure by mediating netrin-1/DCC signaling.

Radiomics Analysis of Gadoxetic Acid-enhanced MRI for Staging Liver Fibrosis.

Purpose To develop and validate a radiomics-based model for staging liver fibrosis by using gadoxetic acid-enhanced hepatobiliary phase MRI. Materials and Methods In this retrospective study, 436 patients (mean age, 51 years; age range, 18-86 years; 319 men [mean age, 51 years; age range, 18-86 years]; 117 women [mean age, 50 years; age range, 18-79 years]) with pathologic analysis-proven liver fibrosis who underwent gadoxetic acid-enhanced MRI from June 2015 to December 2016 were randomized in a three-to-one ratio into development (n = 329) and test (n = 107) cohorts, respectively. In the development cohort, a model was developed to calculate radiomics fibrosis index (RFI) by using logistic regression with elastic net regularization to differentiate stage F3-F4 from stage F0-F2. Optimal RFI cutoffs to diagnose clinically significant fibrosis (stage F2-F4), advanced fibrosis (stage F3-F4), and cirrhosis (stage F4) were determined by receiver operating characteristic curve analysis. In the test cohort, the diagnostic performance of RFI was compared with that of normalized liver enhancement, aspartate transaminase-to-platelet ratio index (APRI), and fibrosis-4 index by using the Obuchowski index. Results In the test cohort, RFI (Obuchowski index, 0.86) significantly outperformed normalized liver enhancement (Obuchowski index, 0.77; P < .03), APRI (Obuchowski index, 0.60; P < .001), and fibrosis-4 index (Obuchowski index, 0.62; P < .001) for staging liver fibrosis. By using the cutoffs, RFI had sensitivities and specificities as follows: 81% (95% confidence interval: 71%, 89%) and 78% (95% confidence interval: 63%, 89%) for diagnosing stage F2-F4, respectively; 79% (95% confidence interval: 67%, 88%) and 82% (95% confidence interval: 69%, 91%), respectively, for diagnosing stage F3-F4; and 92% (95% confidence interval: 79%, 98%) and 75% (95% confidence interval: 62%, 83%), respectively, for diagnosing stage F4. Conclusion Radiomics analysis of gadoxetic acid-enhanced hepatobiliary phase images allows for accurate diagnosis of liver fibrosis. © RSNA, 2018 Online supplemental material is available for this article.

Amide proton transfer-weighted MRI can detect tissue acidosis and monitor recovery in a transient middle cerebral artery occlusion model compared with a permanent occlusion model in rats.

OBJECTIVES: To assess whether increases in amide proton transfer (APT)-weighted signal reflect the effects of tissue recovery from acidosis using transient rat middle cerebral artery occlusion (MCAO) models, compared to permanent occlusion models. MATERIALS AND METHODS: Twenty-four rats with MCAO (17 transient and seven permanent occlusions) were prepared. APT-weighted signal (APTw), apparent diffusion coefficient (ADC), cerebral blood flow (CBF), and MR spectroscopy were evaluated at three stages in each group (occlusion, reperfusion/1 h post-occlusion, and 3 h post-reperfusion/4 h post-occlusion). Deficit areas showing 30% reduction to the contralateral side were measured. Temporal changes were compared with repeated measures of analysis of variance. Relationship between APTw and lactate concentration was calculated. RESULTS: Both APTw and CBF values increased and APTw deficit area reduced at reperfusion (largest p = .002) in transient occlusion models, but this was not demonstrated in permanent occlusion. No significant temporal change was demonstrated with ADC at reperfusion. APTw deficit area was between ADC and CBF deficit areas in transient occlusion model. APTw correlated with lactate concentration at occlusion (r = - 0.49, p = .04) and reperfusion (r = - 0.32, p = .02). CONCLUSIONS: APTw values increased after reperfusion and correlated with lactate content, which suggests that APT-weighted MRI could become a useful imaging technique to reflect tissue acidosis and its reversal. KEY POINTS: • APT-weighted signal increases in the tissue reperfusion, while remains stable in the permanent occlusion. • APTw deficit area was between ADC and CBF deficit areas in transient occlusion model, possibly demonstrating metabolic penumbra. • APTw correlated with lactate concentration during ischemia and reperfusion, indicating tissue acidosis.

Gadoxetate-enhanced dynamic contrast-enhanced MRI for evaluation of liver function and liver fibrosis in preclinical trials.

BACKGROUND: To facilitate translational drug development for liver fibrosis, preclinical trials need to be run in parallel with clinical research. Liver function estimation by gadoxetate-enhanced dynamic contrast-enhanced MRI (DCE-MRI) is being established in clinical research, but still rarely used in preclinical trials. We aimed to evaluate feasibility of DCE-MRI indices as translatable biomarkers in a liver fibrosis animal model. METHODS: Liver fibrosis was induced in Sprague-Dawley rats by thioacetamide (200 mg, 150 mg, and saline for the high-dose, low-dose, and control groups, respectively). Subsequently, DCE-MRI was performed to measure: relative liver enhancement at 3-min (RLE-3), RLE-15, initial area-under-the-curve until 3-min (iAUC-3), iAUC-15, and maximum-enhancement (Emax). The correlation coefficients between these MRI indices and the histologic collagen area, indocyanine green retention at 15-min (ICG-R15), and shear wave elastography (SWE) were calculated. Diagnostic performance to diagnose liver fibrosis was also evaluated by receiver-operating-characteristic (ROC) analysis. RESULTS: Animal model was successful in that the collagen area of the liver was the largest in the high-dose group, followed by the low-dose group and control group. The correlation between the DCE-MRI indices and collagen area was high for iAUC-15, Emax, iAUC-3, and RLE-3 but moderate for RLE-15 (r, - 0.81, - 0.81, - 0.78, - 0.80, and - 0.51, respectively). The DCE-MRI indices showed moderate correlation with ICG-R15: the highest for iAUC-15, followed by iAUC-3, RLE-3, Emax, and RLE-15 (r, - 0.65, - 0.63, - 0.62, - 0.58, and - 0.56, respectively). The correlation coefficients between DCE-MRI indices and SWE ranged from - 0.59 to - 0.28. The diagnostic accuracy of RLE-3, iAUC-3, iAUC-15, and Emax was 100% (AUROC 1.000), whereas those of RLE-15 and SWE were relatively low (AUROC 0.777, 0.848, respectively). CONCLUSION: Among the gadoxetate-enhanced DCE-MRI indices, iAUC-15 and iAUC-3 might be bidirectional translatable biomarkers between preclinical and clinical research for evaluating histopathologic liver fibrosis and physiologic liver functions in a non-invasive manner.

Dynamic contrast-enhanced MRI for oncology drug development.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a promising tool for evaluating tumor vascularity, as it can provide vasculature-derived, functional, and quantitative parameters. To implement DCE-MRI parameters as biomarkers for monitoring the effect of antiangiogenic or vascular-disrupting treatment, two crucial elements of surrogate endpoint, ie, validation and qualification, should be satisfied. Although early studies have shown the accuracy and reliability of DCE-MRI parameters for evaluating treatment-driven vascular alterations, there have been an increasing number of studies demonstrating the limitations of DCE-MRI parameters as surrogate endpoints. Therefore, in order to improve the application of DCE-MRI parameters in drug development, it is necessary to establish a standardized evaluation method and to determine the correct therapeutics-oriented meaning of individual DCE-MRI parameter. In this regard, this article describes the biophysical background and data acquisition/analysis techniques of DCE-MRI while focusing on the validation and qualification issues. Specifically, the causes of disagreement and confusion encountered in the preclinical and clinical trials using DCE-MRI are presented in detail. Finally, considering these limitations, we present potential strategies to optimize implementation of DCE-MRI. J. Magn. Reson. Imaging 2016;44:251-264.

Dual MRI T1 and T2(*) contrast with size-controlled iron oxide nanoparticles.

Contrast-enhancing magnetic resonance mechanism, employing either positive or negative signal changes, has contrast-specific signal characteristics. Although highly sensitive, negative contrast typically decreases the resolution and spatial specificity of MRI, whereas positive contrast lacks a high contrast-to-noise ratio but offers high spatial accuracy. To overcome these individual limitations, dual-contrast acquisitions were performed using iron oxide nanoparticles and a pair of MRI acquisitions. Specifically, vascular signals in MR angiography were positively enhanced using ultrashort echo (UTE) acquisition, which provided highly resolved vessel structures with increased vessel/tissue contrast. In addition, fast low angle shot (FLASH) acquisition yielded strong negative vessel contrast, resulting in the higher number of discernible vessel branches than those obtained from the UTE method. Taken together, the high sensitivity of the negative contrast delineated ambiguous vessel regions, whereas the positive contrast effectively eliminated the false negative contrast areas (e.g., airways and bones), demonstrating the benefits of the dual-contrast method. FROM THE CLINICAL EDITOR: In this study, the MRI properties of iron oxide nanoparticles were studied in an animal model. These contrast agents are typically considered negative contrast materials, leading to signal loss on T2* weighted images, but they also have known T1 effects as well, which is lower than that of standard positive contrast agents (like gadolinium or manganese) but is still detectable. This dual property was utilized in this study, demonstrating high sensitivity of the negative contrast in delineating ambiguous vessel regions, whereas the positive contrast eliminated false negative contrast areas (areas giving rise to susceptibility effects).

Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution.

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

Association Between Taurine Level in the Hippocampus and Major Depressive Disorder in Young Women: A Proton Magnetic Resonance Spectroscopy Study at 7T.

BACKGROUND: Major depressive disorder (MDD) is characterized by depressed mood or loss of interest or pleasure. Generally, women are twice as likely as men to have depression. Taurine, a type of amino acid, plays critical roles in neuronal generation, differentiation, arborization, and formation of synaptic connections. Importantly, it enhances proliferation and synaptogenesis in the hippocampus. When injected into animals, taurine has an antidepressant effect. However, there is no in vivo evidence to show an association between taurine concentration in the human brain and the development of MDD. METHODS: Forty-one unmedicated young women with MDD (ages 18-29) and 43 healthy control participants matched for gender and age were recruited in South Korea. Taurine concentration was measured in the hippocampus, anterior cingulate cortex, and occipital cortex of the MDD and healthy control groups using proton magnetic resonance spectroscopy at 7T. Analysis of covariance was used to examine differences in taurine concentration, adjusting for age as a covariate. RESULTS: Taurine concentration in the hippocampus was lower (F1,75 = 5.729, p = .019, Δη2 = 0.073) for the MDD group (mean [SEM] = 0.91 [0.06] mM) than for the healthy control group (1.13 [0.06] mM). There was no significant difference in taurine concentration in the anterior cingulate cortex or occipital cortex between the two groups. CONCLUSIONS: This study demonstrates that a lower level of taurine concentration in the hippocampus may be a novel characteristic of MDD.

The rate of resolution of clot burden measured by pulmonary CT angiography in patients with acute pulmonary embolism.

OBJECTIVE: The purpose of this article is to quantitatively assess the rate of resolution of clot burden detected on pulmonary CT angiography (CTA) in patients with acute pulmonary embolism (PE). MATERIALS AND METHODS: We evaluated 111 consecutive patients (55 men and 56 women) in a retrospective cohort who were diagnosed with PE by pulmonary CTA and had at least one follow-up pulmonary CTA within 1 year. Two radiologists in consensus measured the volume of each clot using a semiautomated quantification program. Semiquantitative measures of clot burden were also computed. The resolution rates of the total clot volume, as well as clot volumes of the central (main and lobar) and peripheral vessels (segmental and subsegmental), were analyzed. RESULTS: The mean (± SD) clot volume per study was 3403.3 ± 6505.6 mm(3) at baseline and 531.6 ± 2383.5 mm(3) at the follow-up pulmonary CTA. Overall, 85 patients (77% ) showed complete resolution at the follow-up pulmonary CTA. Complete resolution was seen in 17 of 30 patients (56.7%) at a follow-up interval of 1-14 days, in 24 of 31 patients (77.4%) at 29-90 days, and in 32 of 34 patients (94.1%) after 90 days. The total clot volume measurements summed for all patients decreased by 78% (central clot, 69.4%; peripheral clot, 86.0%) at 14 days, by 96.6% (central clot, 93.4%; peripheral clot, 100%) at 90 days, and by 97.7% (central clot, 95.9%; peripheral clot, 100%) after 90 days. CONCLUSION: Clot burden resolved completely in 77% of patients during the follow-up period. Our analysis showed that clots resolved faster in the peripheral arteries than in the central pulmonary arteries.

Short-term mortality in acute pulmonary embolism: clot burden and signs of right heart dysfunction at CT pulmonary angiography.

PURPOSE: To assess the correlation between volumetric measurements of clot, semiquantitative clot burden indexes, and signs of right heart dysfunction at computed tomographic (CT) pulmonary angiography in patients with acute pulmonary embolism (PE) and to determine whether clot burden and signs of right heart dysfunction are associated with short-term mortality. MATERIALS AND METHODS: This retrospective study was institutional review board approved and HIPAA compliant. CT pulmonary angiographic studies (January 2007 through December 2007) with findings positive for PE were retrieved. Two readers evaluated signs of right heart dysfunction at CT pulmonary angiography, measured clot volume using a dedicated software program, and assessed clot burden using semiquantitative scores (Qanadli and Mastora). Spearman rank coefficient was used to investigate correlation between clot burden measures and signs of right heart dysfunction. Uni- and multivariate analyses were used to test association between CT pulmonary angiographic findings and short-term mortality. RESULTS: A total of 635 CT pulmonary angiographic studies from 635 patients (304 men, 331 women; mean age, 59 years) were included; 39 (6%) patients died within 30 days. Clot volume was strongly correlated with Qanadli score (ρ=0.841, P<.01) and Mastora score (ρ=0.863, P<.01) and moderately correlated (ρ=0.378, P<.01) with the ratio of right ventricle diameter to left ventricle diameter (RV/LV ratio). Among the pulmonary angiographic signs, only increase in RV/LV ratio (cut-off value, 1.0) was independently associated with short-term mortality in multivariate analysis. CONCLUSION: Clot volume strongly correlated with semiquantitative CT scores of clot burden, and greater clot volume was associated with higher incidence of right heart dilatation. Increase in RV/LV ratio was associated with short-term mortality; however, measures of clot burden were not.

Reproducibility of measurement of apparent diffusion coefficients of malignant hepatic tumors: effect of DWI techniques and calculation methods.

PURPOSE: To evaluate the effect of diffusion-weighted imaging (DWI) methods, apparent diffusion coefficient (ADC) calculation methods, and selection of b-values on the ADCs and the measurement reproducibility of malignant hepatic tumors. MATERIALS AND METHODS: Nineteen patients with pathologically confirmed malignant hepatic tumors underwent breath-hold DWI (b-values = 0, 50, 500 s/mm(2)) and respiratory-triggered DWI (0, 50, 300, 500, 1000 s/mm(2)) twice on a 1.5 T magnetic resonance imaging (MRI) scanner. ADCs were calculated using a two b-value and/or a multiple b-value method. The reproducibility of the ADC measurements was evaluated from the intraclass correlation coefficients (ICCs) and the 95% Bland-Altman limit-of-agreement (LOA). RESULTS: The ADCs were different according to the DWI methods (P = 0.040-0.282), ADC calculation methods (P = 0.003-0.825), and the choice of b-values (P < 0.001). The ADC tended to be more reproducible with use of breath-hold DWI (ICC: 0.898-0.933; LOA, 18.8%-24.0%) than respiratory-triggered DWI (ICC: 0.684-0.928; LOA, 15.0%-31.9%) (P = 0.008-0.122). For respiratory-triggered DWI, the multiple b-value method using five b-values had better reproducibility than the two b-value method for measurement of ADC (P = 0.009-0.221). CONCLUSION: The DWI method, ADC calculation method, and selection of b-values potentially influence the ADCs and the reproducibility of malignant hepatic tumors. ADCs calculated from breath-hold DWI are more reproducible than from respiratory-triggered DWI. A multiple b-value method may improve the reproducibility of respiratory-triggered DWI.

Deep Learning-Based Assessment of Functional Liver Capacity Using Gadoxetic Acid-Enhanced Hepatobiliary Phase MRI.

OBJECTIVE: We aimed to develop and test a deep learning algorithm (DLA) for fully automated measurement of the volume and signal intensity (SI) of the liver and spleen using gadoxetic acid-enhanced hepatobiliary phase (HBP)-magnetic resonance imaging (MRI) and to evaluate the clinical utility of DLA-assisted assessment of functional liver capacity. MATERIALS AND METHODS: The DLA was developed using HBP-MRI data from 1014 patients. Using an independent test dataset (110 internal and 90 external MRI data), the segmentation performance of the DLA was measured using the Dice similarity score (DSS), and the agreement between the DLA and the ground truth for the volume and SI measurements was assessed with a Bland-Altman 95% limit of agreement (LOA). In 276 separate patients (male:female, 191:85; mean age ± standard deviation, 40 ± 15 years) who underwent hepatic resection, we evaluated the correlations between various DLA-based MRI indices, including liver volume normalized by body surface area (LVBSA), liver-to-spleen SI ratio (LSSR), MRI parameter-adjusted LSSR (aLSSR), LSSR × LVBSA, and aLSSR × LVBSA, and the indocyanine green retention rate at 15 minutes (ICG-R15), and determined the diagnostic performance of the DLA-based MRI indices to detect ICG-R15 ≥ 20%. RESULTS: In the test dataset, the mean DSS was 0.977 for liver segmentation and 0.946 for spleen segmentation. The Bland-Altman 95% LOAs were 0.08% ± 3.70% for the liver volume, 0.20% ± 7.89% for the spleen volume, -0.02% ± 1.28% for the liver SI, and -0.01% ± 1.70% for the spleen SI. Among DLA-based MRI indices, aLSSR × LVBSA showed the strongest correlation with ICG-R15 (r = -0.54, p < 0.001), with area under receiver operating characteristic curve of 0.932 (95% confidence interval, 0.895-0.959) to diagnose ICG-R15 ≥ 20%. CONCLUSION: Our DLA can accurately measure the volume and SI of the liver and spleen and may be useful for assessing functional liver capacity using gadoxetic acid-enhanced HBP-MRI.

Preliminary Study for Quantitative Assessment of Sacroiliitis Activity Using Bone SPECT/CT: Comparison of Diagnostic Performance of Quantitative Parameters.

Purpose: We compared the feasibility of quantitative analysis methods using bone SPECT/CT with those using planar bone scans to assess active sacroiliitis. Methods: We retrospectively reviewed whole-body bone scans and pelvic bone SPECT/CTs of 8 patients who had clinically confirmed sacroiliitis and enrolled 24 patients without sacroiliitis as references. The volume of interest of each sacroiliac joint, including both the ilium and sacrum, was drawn. Active arthritis zone (AAZ) was defined as the zone of voxels with higher SUV than sacral mean SUV within the VOI of SI joint. Then, the following SPECT/CT quantitative parameters, SUVmax (maximum SUV), SUV50% (mean SUV in highest 50% of SUV), and SUV-AAZ, and the ratio of those values to sacral mean SUV (SUVmax/S, SUV50%/S, SUV-AAZ/S) were calculated. For the planar bone scan, the mean count ratio of SI joint/sacrum (SI/S) was conventionally measured. Results: Most of the SPECT/CT parameters of the sacroiliitis group were significantly higher than the normal group, whereas SI/S of the planar bone scan was not significantly different between the two groups. In receiver operating characteristic curve analysis, SUV-AAZ/S showed the highest AUC of 0.992, followed by SUV50%/S and SUVmax/S. All ratio parameters of the SPECT/CT showed higher AUC values than the SUV parameters of SI joint or SI/S of the planar scan. Conclusions: The quantitative analyses of bone SPECT/CT showed better performance in assessing active sacroiliitis than the planar bone scan. SPECT/CT parameters using the ratio of the SI joint to sacrum showed more favorable results than SUV parameters such as SUVmax, SUV50%, and SUV-AAZ.

Prediction of the Acuity of Vertebral Compression Fractures on CT Using Radiologic and Radiomic Features.

RATIONALE AND OBJECTIVES: To develop and validate prediction models to differentiate acute and chronic vertebral compression fractures based on radiologic and radiomic features on CT. MATERIALS AND METHODS: This study included acute and chronic compression fractures in patients who underwent both spine CT and MRI examinations. For each fractured vertebra, three CT findings ([1] cortical disruption, [2] hypoattenuating cleft or sclerotic line, and [3] relative bone marrow attenuation) were assessed by two radiologists. A radiomic score was built from 280 radiomic features extracted from non-contrast-enhanced CT images. Weighted multivariable logistic regression analysis was performed to build a radiologic model based on CT findings and an integrated model combining the radiomic score and CT findings. Model performance was evaluated and compared. Models were externally validated using an independent test cohort. RESULTS: A total to 238 fractures (159 acute and 79 chronic) in 122 patients and 58 fractures (39 acute and 19 chronic) in 32 patients were included in the training and test cohorts, respectively. The AUC of the radiomic score was 0.95 in the training and 0.93 in the test cohorts. The AUC of the radiologic model was 0.89 in the training and 0.83 in the test cohorts. The discriminatory performance of the integrated model was significantly higher than the radiologic model in both the training (AUC, 0.97; p<0.01) and the test (AUC, 0.95; p=0.01) cohorts. CONCLUSION: Combining radiomics with radiologic findings significantly improved the performance of CT in determining the acuity of vertebral compression fractures.

Prediction of Decompensation and Death in Advanced Chronic Liver Disease Using Deep Learning Analysis of Gadoxetic Acid-Enhanced MRI.

OBJECTIVE: This study aimed to evaluate the usefulness of quantitative indices obtained from deep learning analysis of gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and their longitudinal changes in predicting decompensation and death in patients with advanced chronic liver disease (ACLD). MATERIALS AND METHODS: We included patients who underwent baseline and 1-year follow-up MRI from a prospective cohort that underwent gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance between November 2011 and August 2012 at a tertiary medical center. Baseline liver condition was categorized as non-ACLD, compensated ACLD, and decompensated ACLD. The liver-to-spleen signal intensity ratio (LS-SIR) and liver-to-spleen volume ratio (LS-VR) were automatically measured on the HBP images using a deep learning algorithm, and their percentage changes at the 1-year follow-up (ΔLS-SIR and ΔLS-VR) were calculated. The associations of the MRI indices with hepatic decompensation and a composite endpoint of liver-related death or transplantation were evaluated using a competing risk analysis with multivariable Fine and Gray regression models, including baseline parameters alone and both baseline and follow-up parameters. RESULTS: Our study included 280 patients (153 male; mean age ± standard deviation, 57 ± 7.95 years) with non-ACLD, compensated ACLD, and decompensated ACLD in 32, 186, and 62 patients, respectively. Patients were followed for 11-117 months (median, 104 months). In patients with compensated ACLD, baseline LS-SIR (sub-distribution hazard ratio [sHR], 0.81; p = 0.034) and LS-VR (sHR, 0.71; p = 0.01) were independently associated with hepatic decompensation. The ΔLS-VR (sHR, 0.54; p = 0.002) was predictive of hepatic decompensation after adjusting for baseline variables. ΔLS-VR was an independent predictor of liver-related death or transplantation in patients with compensated ACLD (sHR, 0.46; p = 0.026) and decompensated ACLD (sHR, 0.61; p = 0.023). CONCLUSION: MRI indices automatically derived from the deep learning analysis of gadoxetic acid-enhanced HBP MRI can be used as prognostic markers in patients with ACLD.