Unenhanced Images Research Articles

Unenhanced magnetic resonance imaging of papillary thyroid carcinoma with emphasis on diffusion kurtosis imaging.

The aim of this study was to investigate the value of unenhanced magnetic resonance imaging (MRI) with diffusion kurtosis imaging (DKI) in diagnosing papillary thyroid carcinoma (PTC). In all, 77 consecutive patients comprising a total of 77 thyroid nodules were enrolled in this study. Of these nodules, 41 were histopathologically confirmed PTCs and 36 were benign nodules. All patients underwent thyroid MRI including T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and DKI. All the images were assessed by 2 radiologists. The signal intensity ratio (SIR) of these nodules on T1WI and T2WI, the apparent diffusion coefficient (ADC) from DWI, and mean diffusivity (MD) and mean kurtosis (MK) from DKI were measured. Morphological features on these images were also evaluated. Univariate and multivariate logistic regression analyses were used to evaluate the value of these parameters as potential predictors of PTC. In the univariate analyses, the features that significantly indicated PTC were decreased ADC value (P<0.001), decreased MD value (P<0.001), increased MK value (P<0.001), younger age (P=0.001), female tendency (P=0.049), smaller tumor diameter (P<0.001), solid component (P<0.001), and irregular margin (P<0.001). In the multivariate analysis, decreased MD value (odds ratio =25.321; P=0.001), smaller diameter (odds ratio =13.751; P=0.006), and irregular margin (odds ratio =16.003; P=0.003) were independent risk factors for PTC. The combined predictor of MD, diameter, and margin showed an area under the receiver operating characteristic (ROC) curve of 0.996 in diagnosing PTC, with an optimal cutoff value of 0.69 (95.1% sensitivity, 100.0% specificity). Lower MD value from DKI, smaller diameter, and irregular margin are useful predictive biomarkers for PTC.

Using Machine Learning to Reduce the Need for Contrast Agents in Breast MRI through Synthetic Images.

Background Reducing the amount of contrast agent needed for contrast-enhanced breast MRI is desirable. Purpose To investigate if generative adversarial networks (GANs) can recover contrast-enhanced breast MRI scans from unenhanced images and virtual low-contrast-enhanced images. Materials and Methods In this retrospective study of breast MRI performed from January 2010 to December 2019, simulated low-contrast images were produced by adding virtual noise to the existing contrast-enhanced images. GANs were then trained to recover the contrast-enhanced images from the simulated low-contrast images (approach A) or from the unenhanced T1- and T2-weighted images (approach B). Two experienced radiologists were tasked with distinguishing between real and synthesized contrast-enhanced images using both approaches. Image appearance and conspicuity of enhancing lesions on the real versus synthesized contrast-enhanced images were independently compared and rated on a five-point Likert scale. P values were calculated by using bootstrapping. Results A total of 9751 breast MRI examinations from 5086 patients (mean age, 56 years ± 10 [SD]) were included. Readers who were blinded to the nature of the images could not distinguish real from synthetic contrast-enhanced images (average accuracy of differentiation: approach A, 52 of 100; approach B, 61 of 100). The test set included images with and without enhancing lesions (29 enhancing masses and 21 nonmass enhancement; 50 total). When readers who were not blinded compared the appearance of the real versus synthetic contrast-enhanced images side by side, approach A image ratings were significantly higher than those of approach B (mean rating, 4.6 ± 0.1 vs 3.0 ± 0.2; P < .001), with the noninferiority margin met by synthetic images from approach A (P < .001) but not B (P > .99). Conclusion Generative adversarial networks may be useful to enable breast MRI with reduced contrast agent dose. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bahl in this issue.

Use of Non-Contrast-Enhanced MR Angiography to Assess Recanalization after Uterine Artery Embolization

The purpose of this study was to examine the use of non-contrast-enhanced MR angiography (MRA) for assessing recanalization of uterine arteries (UAs) after uterine artery embolization (UAE) for symptomatic fibroids. Pre-procedural and follow-up unenhanced MRA images of 30 patients were reviewed, and the extent to which the UAs could be visualized was classified on a 4-point scale. An increase in the score between consecutive time points indicates that a previously inconspicuous segment of the UA became visible on follow-up images. Patients were divided into two groups according to the presence (or absence) of recanalization. The median UA visualization score at each follow-up was significantly lower than that at baseline (p < 0.01), but there was no significant difference between the scores of the follow-up images. Recanalization was detected in 63% (19/30) of patients. In these patients, the mean decrease in uterine and largest fibroid volume at 12 months after UAE was inferior to the mean decrease in patients for whom recanalization was not detected. Based on MRA assessment, recanalization after UAE occurred in 63% of patients but did not compromise the reduction in uterine and dominant fibroid volumes within 12 months after UAE.

Development and validation of a MRI-based combined radiomics nomogram for differentiation in chondrosarcoma.

This study aims to develop and validate the performance of an unenhanced magnetic resonance imaging (MRI)-based combined radiomics nomogram for discrimination between low-grade and high-grade in chondrosarcoma. A total of 102 patients with 44 in low-grade and 58 in high-grade chondrosarcoma were enrolled and divided into training set (n=72) and validation set (n=30) with a 7:3 ratio in this retrospective study. The demographics and unenhanced MRI imaging characteristics of the patients were evaluated to develop a clinic-radiological factors model. Radiomics features were extracted from T1-weighted (T1WI) images to construct radiomics signature and calculate radiomics score (Rad-score). According to multivariate logistic regression analysis, a combined radiomics nomogram based on MRI was constructed by integrating radiomics signature and independent clinic-radiological features. The performance of the combined radiomics nomogram was evaluated in terms of calibration, discrimination, and clinical usefulness. Using multivariate logistic regression analysis, only one clinic-radiological feature (marrow edema OR=0.29, 95% CI=0.11-0.76, P=0.012) was found to be independent predictors of differentiation in chondrosarcoma. Combined with the above clinic-radiological predictor and the radiomics signature constructed by LASSO [least absolute shrinkage and selection operator], a combined radiomics nomogram based on MRI was constructed, and its predictive performance was better than that of clinic-radiological factors model and radiomics signature, with the AUC [area under the curve] of the training set and the validation set were 0.78 (95%CI =0.67-0.89) and 0.77 (95%CI =0.59-0.94), respectively. DCA [decision curve analysis] showed that combined radiomics nomogram has potential clinical application value. The MRI-based combined radiomics nomogram is a noninvasive preoperative prediction tool that combines clinic-radiological feature and radiomics signature and shows good predictive effect in distinguishing low-grade and high-grade bone chondrosarcoma, which may help clinicians to make accurate treatment plans.

Can 3-Phase Computed Tomography Urography Be Used to Characterize Adrenal Nodules? Results in 145 Patients.

The aim of the study is to determine whether computed tomography (CT) urography (CTU) can characterize incidental adrenal nodules. This retrospective cohort study was performed at an academic medical center. Patients were identified by free text search of CTU reports that contained the terms "adrenal mass" "adrenal nodule" and "adrenal lesion." Computed tomography urography technique consisted of unenhanced images and postcontrast images obtained at 100 seconds and 15 minutes. The final cohort included 145 patients with 151 adrenal nodules. Nodules were considered lipid-rich adenomas or myelolipomas based on unenhanced imaging characteristics. Absolute and relative washout values were calculated for the remaining nodules, using a cutoff of 60% and 40%, respectively, to diagnose adenomas. Reference standard for lipid-poor adenomas and malignant nodules was histopathology or imaging/clinical follow-up. Mann-Whitney U test was used for comparison of continuous variables, and Fisher exact test was used for categorical variables. One hundred nodules were lipid-rich adenomas and 3 were myelolipomas. Forty-eight nodules were indeterminate at unenhanced CT, corresponding to 39 lipid-poor adenomas and 9 malignant nodules based on reference standards. Both absolute and relative washout correctly characterized 71% of nodules (34/48), with a sensitivity of 67% and specificity of 89%. Overall, 91% of all adrenal nodules (137/151) were correctly characterized by CTU alone. Lipid-poor adenomas were smaller than malignant nodules (P < 0.01) and were lower in attenuation on unenhanced and delayed images (P < 0.01). Adrenal nodules detected at 3-phase CTU can be accurately characterized, potentially eliminating the need for subsequent adrenal protocol CT or magnetic resonance imaging.

Extracellular volume fraction determined by equilibrium contrast-enhanced computed tomography: correlation with histopathological findings in gastric cancer

PurposeTo assess the relationship between histopathological features of gastric cancer and the extracellular volume fraction (ECV) measured by preoperative equilibrium contrast-enhanced computed tomography (CECT).Materials and methodsThe study group consisted of 66 patients with surgically resected gastric adenocarcinoma who underwent preoperative multiphasic CECT. Tumor ECVs were calculated using region-of-interest measurements within the gastric cancer and aorta of each case on unenhanced and equilibrium-phase images. The relationship between the mean ECV values and clinicopathological parameters was examined by univariate analysis. Parameters showing a significant difference in the former test were further tested by linear regression and receiver operating characteristic (ROC) curve analyses.ResultsIn the univariate analysis, the values of venous invasion (p = 0.0487) and tumor infiltration (INF) pattern (p < 0.0001) were significantly correlated with the tumor ECV. INF was significantly correlated (β = 0.57, p < 0.0001) in the linear regression analysis. The tumor ECV showed better diagnostic accuracy for predicting INF (INFa/b vs INFc), and the area under the ROC curve value was 0.89.ConclusionTumor ECV determined by equilibrium CECT is significantly correlated with the pathological INF of gastric cancer.

Temporal evolution of new T1-weighted hypo-intense lesions and central brain atrophy in patients with a first clinical demyelinating event treated with subcutaneous interferon β-1a

ObjectiveEvaluate the effect of subcutaneous interferon β-1a (sc IFN β-1a) versus placebo on the evolution of T1-weighted MRI lesions and central brain atrophy in in patients with a first clinical demyelinating event (FCDE).MethodsPost hoc analysis of baseline-to-24 month MRI data from patients with an FCDE who received sc IFN β-1a 44 μg once- (qw) or three-times-weekly (tiw), or placebo, in REFLEX. Patients were grouped according to treatment regimen or conversion to clinically definite MS (CDMS) status. The intensity of new lesions on unenhanced T1-weighted images was classified as T1 iso- or hypo-intense (black holes) and percentage ventricular volume change (PVVC) was assessed throughout the study.ResultsIn patients not converting to CDMS, sc IFN β-1a tiw or qw, versus placebo, reduced the overall number of new lesions (P < 0.001 and P = 0.005) and new T1 iso-intense lesions (P < 0.001 and P = 0.002) after 24 months; only sc IFN β-1a tiw was associated with fewer T1 hypo-intense lesions versus placebo (P < 0.001). PVVC findings in patients treated with sc IFN β-1a suggested pseudo-atrophy that was ~ fivefold greater versus placebo in the first year of treatment (placebo 1.11%; qw 4.28%; tiw 6.76%; P < 001); similar findings were apparent for non-converting patients.ConclusionsIn patients with an FCDE, treatment with sc IFN β-1a tiw for 24 months reduced the number of new lesions evolving into black holes.

Feasibility of thoracic CT in assessing anemia for aplastic anemia patients undergoing allogeneic hematopoietic stem cell transplantation.

Anemia is an important clinical symptom for aplastic anemia (AA) patients who are suffered with peripheral pancytopenia. To evaluate the accuracy of diagnosing anemia with non-invasive chest computed tomography (CT) for AA patients. The CT attenuation of left ventricular (LV) cavity and interventricular septum (IVS) on unenhanced thoracic CT images of AA patients are retrospectively analyzed, including 84 AA patients in pre-transplant and 1-month (n = 82), 2-month (n = 72), 3-month (n = 75), 6-month (n = 74) and 12-month (n = 70) followed patients in post-transplant. The difference (IVS-LV) and ratio (LV/IVS) of the CT attenuation between LV cavity and interventricular septum are calculated. Serum hemoglobin is estimated within 24 hours of CT imaging. The CT attenuations of IVS-LV and LV/IVS are correlated with hemoglobin, and their variation tendency is analyzed during the treatment of a-HSCT. A receiver operating characteristic (ROC) curve analysis is then performed for the diagnosis of anemia. The CT attenuations of IVS-LV and LV/IVS well correlate with hemoglobin (r = -0.618 and 0.628, respectively, P < 0.001). The variation tendency of IVS-LV and LV/IVS is similar to that of hemoglobin with opposite directions during one-year follow-up of a-HSCT. When a threshold of CT attenuation of IVS-LV and LV/IVS is set at 11.5HU and 0.77, respectively, both the sensitivity and specificity in diagnosing anemia are good (74.7% and 73.8% in CT attenuation of IVS-LV; 77.4% and 70.4% in LV/LVS, respectively). Both CT attenuation of LV/IVS and IVS-LV had similar accuracy in diagnosing anemia for AA patients. The non-invasive chest CT can offer a new possibility to complementarily evaluate anemia for AA patients in the diagnostic radiology reports.

Machine learning analysis of adrenal lesions: preliminary study evaluating texture analysis in the differentiation of adrenal lesions

This study aimed to determine the accuracy of texture analysis in differentiating adrenal lesions on unenhanced computed tomography (CT) images. In this single-center retrospective study, 166 adrenal lesions in 140 patients (64 women, 76 men; mean age 56.58 ± 13.65 years) were evaluated between January 2015 and December 2019. The lesions consisted of 54 lipid-rich adrenal adenomas, 37 lipid-poor adrenal adenomas (LPAs), 56 adrenal metastases (ADM), and 19 adrenal pheochromocytomas (APhs). Each adrenal lesion was segmented by manually contouring the borders of the lesion on unenhanced CT images. A texture analysis of the CT images was performed using Local Image Feature Extraction software. First-order and second-order texture parameters were assessed, and 45 features were extracted from each lesion. One-Way analysis of variance with Bonferroni correction and the Mann-Whitney U test was performed to determine the relationships between the texture features and adrenal lesions. Receiver operating characteristic curves were performed for lesion discrimination based on the texture features. Logistic regression analysis was used to generate logistic models, including only the texture parameters with a high-class separation capacity (i.e., P < 0.050). SPSS software was used for all statistical analyses. First-order and second-order texture parameters were identified as significant factors capable of differentiating among the four lesion types (P < 0.050). The logistic models were evaluated to ascertain the relationships between LPA and ADM, LPA and APh, and ADM and APh. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the first model (LPA vs. ADM) were 85.7%, 70.3%, 81.3%, 76.4%, and 79.5%, respectively. The sensitivity, specificity, PPV, NPV, and accuracy of the second model (LPA vs. APh) were all 100%. The sensitivity, specificity, PPV, NPV, and accuracy of the third model (ADM vs. APh) were 87.5%, 82%, 36.8%, 98.2%, and 82.7%, respectively. Texture features may help in the characterization of adrenal lesions on unenhanced CT images.

CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study

BackgroundTo establish and verify a radiomics nomogram for differentiating isolated micronodular adrenal hyperplasia (iMAD) from lipid-poor adenoma (LPA) based on computed tomography (CT)-extracted radiomic features.MethodsA total of 148 patients with iMAD or LPA were divided into three cohorts: a training cohort (n = 72; 37 iMAD and 35 LPA), a validation cohort (n = 36; 22 iMAD and 14 LPA), and an external validation cohort (n = 40; 20 iMAD and 20 LPA). Radiomics features were extracted from contrast-enhanced and non-contrast CT images. The least absolute shrinkage and selection operator (LASSO) method was applied to develop a triphasic radiomics model and unenhanced radiomics model using reproducible radiomics features. A clinical model was constructed using certain laboratory variables and CT findings. Radiomics nomogram was established by selected radiomics signature and clinical factors. Nomogram performance was assessed by calibration curve, the areas under receiver operating characteristic curves (AUC), and decision curve analysis (DCA).ResultsEleven and eight extracted features were finally selected to construct an unenhanced radiomics model and a triphasic radiomics model, respectively. There was no significant difference in AUC between the two models in the external validation cohort (0.838 vs. 0.843, p = 0.949). The radiomics nomogram inclusive of the unenhanced model, maximum diameter, and aldosterone showed the AUC of 0.951, 0.938, and 0.893 for the training, validation, and external validation cohorts, respectively. The nomogram showed good calibration, and the DCA demonstrated the superiority of the nomogram compared with the clinical factors model alone in terms of clinical usefulness.ConclusionsA radiomics nomogram based on unenhanced CT images and clinical variables showed favorable performance for distinguishing iMAD from LPA. In addition, an efficient unenhanced model can help avoid extra contrast-enhanced scanning and radiation risk.

Pancreatic fat fraction in dual-energy computed tomography as a potential quantitative parameter in the detection of type 2 diabetes mellitus

PurposeTo investigate the clinical value of measuring pancreatic fat fraction using dual-energy computed tomography (DECT) in association with type 2 diabetes mellitus (T2DM). Materials and methodsThis retrospective study included patients who underwent abdominal DECT between September 2021 and July 2022. The fat fractions in the head, body, and tail of the pancreas were calculated using fat maps generated from unenhanced DECT images, and CT values were measured at the same locations. The intraclass correlation coefficient (ICC) was used to analyze the reproducibility of measurements from two observers. Diagnostic performance was assessed using receiver operating characteristic curves. ResultsSeventy-eight patients, including 45 T2DM patients and 33 controls, were enrolled. The fat fractions of the pancreas were significantly higher in the T2DM group than in the control group (pancreatic head: 8.4 ± 6.3 % vs 5.1 ± 3.9 %; pancreatic body: 4.8 ± 4.0 % vs 2.7 ± 3.9 %; and pancreatic tail: 5.3 ± 3.2 % vs 2.7 ± 2.9 %, all p < 0.05). And the CT values of the pancreas were significantly lower in the T2DM group than in the control group (pancreatic head: 41.1 ± 8.5 HU vs 45.7 ± 4.6 HU; pancreatic body: 44.4 ± 5.0 HU vs 47.4 ± 3.7 HU; and pancreatic tail: 44.5 ± 5.0 HU vs 47.6 ± 3.2 HU, all p < 0.05).The fat fraction of the pancreatic tail was the best indicator for distinguishing T2DM patients from the controls (area under the curve: 0.716 (95 % CI: 0.601, 0.832), sensitivity: 64.4 % (95 % CI: 48.7 %, 77.7 %), and specificity: 78.8 % (95 % CI: 60.6 %, 90.4 %)). ConclusionThe DECT fat fractions of the pancreas could be a valuable additional parameter in the detection of T2DM.

Prediction of the characteristics of aggressiveness of pancreatic neuroendocrine neoplasms (PanNENs) based on CT radiomic features.

To predict tumor grade (G1 vs. G2/3), presence of distant metastasis (M+), metastatic lymph nodes (N+), and microvascular invasion (VI) of pancreatic neuroendocrine neoplasms (PanNEN) based on preoperative CT radiomic features (RFs), by applying a machine learning approach aimed to limit overfit. This retrospective study included 101 patients who underwent surgery for PanNEN; the entire population was split into training (n = 70) and validation cohort (n = 31). Based on a previously validated methodology, after tumor segmentation on contrast-enhanced CT, RFs were extracted from unenhanced CT images. In addition, conventional radiological and clinical features were combined with RFs into multivariate logistic regression models using minimum redundancy and a bootstrap-based machine learning approach. For each endpoint, models were trained and validated including only RFs (RF_model), and both (radiomic and clinicoradiological) features (COMB_model). Twenty-five patients had G2/G3 tumor, 37 N+, and 14 M+ and 38 were shown to have VI. From a total of 182 RFs initially extracted, few independent radiomic and clinicoradiological features were identified. For M+ and G, the resulting models showed moderate to high performances: areas under the curve (AUC) for training/validation cohorts were 0.85/0.77 (RF_model) and 0.81/0.81 (COMB_model) for M+ and 0.67/0.72 and 0.68/0.70 for G. Concerning N+ and VI, only the COMB_model could be built, with poorer performance for N+ (AUC = 0.72/0.61) compared to VI (0.82/0.75). For all endpoints, the negative predictive value was good (≥ 0.75). Combining few radiomic and clinicoradiological features resulted in presurgical prediction of histological characteristics of PanNENs. Despite the limited risk of overfit, external validations are warranted. • Histology is the only tool currently available allowing characterization of PanNEN biological characteristics important for prognostic assessment; significant limitations to this approach exist. • Based upon preoperative contrast-enhanced CT images, a machine learning approach optimized to favor models' generalizability was successfully applied to train predictive models for tumor grading (G1 vs. G2/3), microvascular invasion, metastatic lymph nodes, and distant metastatic spread. • Moderate to high discriminative models (AUC: 0.67-0.85) based on few parameters (≤ 3) showing high negative predictive value (0.75-0.98) were generated and then successfully validated.

Safe Follow-Up after Endovascular Aortic Repair with Unenhanced MRI: The SAFEVAR Study.

We aimed to investigate whether unenhanced magnetic resonance imaging (MRI) could represent a safe and highly sensitive tool for endoleak screening in patients treated with endovascular aneurysm repair (EVAR) using computed tomography angiography (CTA) as a reference standard. Patients who underwent CTA for EVAR follow-up at our institution were prospectively enrolled. All MRI examinations were performed with a 1.5 T unit. The true-FISP and HASTE sequences of the MRI scans were assessed for the presence of hyperintensity within the aneurysm sac outside the graft, whereas phase-contrast through-plane sequences were used for blood flow quantification. We included 45 patients, 5 (11%) of whom were female. The median age was 73 years (IQR 68−78 years). Among our patients, 19 (42%) were positive for endoleaks at CTA, of whom 13 (68%) had type II endoleaks and 6 (32%) had type I endoleaks. There were no significant differences in age, sex, aneurysm type, prosthesis type, or contrast-to-noise ratio between hyperintensity and thrombus between patients with and without endoleaks (p > 0.300). The combined evaluation of true-FISP and HASTE yielded 100% sensitivity (95% CI: 79−100%) and 19% specificity (95% CI: 7−40%). Patients with a positive CTA had a median thrombus flow of 0.06 L/min (IQR 0.03−0.23 L/min), significantly greater than that of patients with a negative CTA (p = 0.007). Setting a threshold at 0.01 L/min, our MRI protocol yielded 100% sensitivity, 56% specificity, and an AUC of 0.76 (95% CI 0.60−0.91). In conclusion, unenhanced MRI has perfect sensitivity for endoleak detection, although with subpar specificity that could be improved with phase-contrast flow analysis.

Differentiation of focal nodular hyperplasia and hepatocellular adenoma using qualitative and quantitative imaging features and classification and regression tree analysis.

To assess qualitative and quantitative analysis of gadoxetate disodium-enhanced hepatobiliary phase MR imaging (MRI) and assess the performance of classification and regression tree analysis for the differentiation of focal nodular hyperplasia (FNH) and hepatocellular adenoma (HCA). This retrospective study was approved by our local ethics committee. One hundred seventy patients suspected of having FNH or HCA underwent gadoxetate disodium-enhanced MRI. The reference standard was either pathology or follow-up imaging. Two readers reviewed images to identify qualitative imaging features and measure signal intensity on unenhanced, dynamic, and hepatobiliary phase images. For quantitative analysis, contrast enhancement ratio (CER), lesion-to-liver contrast (LLC), signal intensity ratio (SIR), and relative signal enhancement ratio (RSER) were calculated. A classification and regression tree (CART) analysis was developed. Eighty-five patients met the inclusion criteria, with a total of 97 FNHs and 43 HCAs. For qualitative analysis, the T1 signal intensity on the hepatobiliary phase provided the highest overall classification performance (91.9% sensitivity, 90.1% specificity, and 90.9% accuracy). For quantitative analysis, RSER in the hepatobiliary phase with a threshold of 0.723 provided the highest classification performance (92.6% sensitivity and 89.4% specificity) to differentiate FNHs from HCAs. A CART model based on five qualitative imaging features provided an accuracy of 94.4% (95% confidence interval 90.0-98.9%). Gadoxetate disodium-enhanced hepatobiliary phase provides high diagnostic performance as demonstrated in quantitative and qualitative analysis in differentiation of FNH and HCA, supported by a CART decision model.

Juvenile idiopathic arthritis of the knee: is contrast needed to score disease activity when using an augmented MRI protocol comprising PD-weighted sequences?

ObjectiveTo compare unenhanced versus enhanced knee joint magnetic resonance imaging (MRI) to assess disease activity of juvenile idiopathic arthritis (JIA).MethodsFifty-three knee joint MRI examinations were performed on a 3-Tesla system in 27 patients (age: 11.40 ± 3.61 years; 21 females, 6 males). MRI protocols comprised PD-weighted sequences in addition to the widely used standard protocol. JIA subgroups comprised oligoarticular arthritis (n = 16), extended oligoarthritis (n = 6), rheumatoid factor-negative polyarticular arthritis (n = 3), enthesitis-related arthritis (n = 1), and psoriatic arthritis (n = 1). MR images were retrospectively analyzed by 3 experienced radiologists in two readings, using JAMRIS (juvenile arthritis MRI scoring) system and a modified IPSG (international prophylaxis study group) classification. In the first reading session, only unenhanced MR images were evaluated. In a second reading session, all images before and after contrast medium application were included. In order to avoid bias, an interval of at least 2 weeks was set between the two readings. The clinical JADAS10 (juvenile arthritis disease activity score) was calculated including clinical assessment and laboratory workup and correlated with MRI scores. Statistical analysis comprised Pearson’s correlation for correlating two scoring results of unenhanced and the enhanced MRI, intra-class correlation coefficient (ICC) for inter- and intra-reader agreement. Diagnostic accuracy was calculated using ROC (receiver operating characteristics) curve analysis.ResultsInter-reader agreement determined by ICC for unenhanced and enhanced MRI scores for IPSG was moderate (0.65, 95% CI 0.51–0.76, and 0.62, 95% CI 0.48–0.75) and high for JAMRIS (0.83, 95% CI 0.75–0.89, and 0.82, 95% CI 0.74–0.89). Intra-reader agreement was good to very good for JAMRIS (0.85 95% CI 0.81–0.88, 0.87 95% CI 0.83–0.89 and 0.96 95% CI 0.92–0.98) and IPSG (0.76 95% CI 0.62–0.86, 0.86 95% CI 0.77–0.92 and 0.92 95% CI 0.86–0.96). Scores of unenhanced MRI correlated with contrast-enhanced MRI: JAMRIS (r = 0.97, R2 = 0.93, p < 0.01), modified IPSG (r = 0.95, R2 = 0.91, p < 0.01). When using JADAS10 as a reference standard, moderate accuracy for both unenhanced and enhanced MRI scores was noted: JAMRIS (AUC = 0.68, 95% CI 0.51–0.85, and AUC = 0.66, 95% 0.49–0.82), IPSG score (AUC = 0.68, 95% 0.50–0.86, and AUC = 0.61, 95% 0.41–0.81).ConclusionsOur results suggest that contrast agent application could be omitted in JIA patients with an augmented knee MRI protocol comprising PD-weighted sequence.Key Points• Unenhanced MRI can detect disease activity of the knee joint in patients with JIA with equally high accuracy compared to contrast-enhanced MRI.• The intra- and inter-reader agreement was high for unenhanced and enhanced MRI JAMRIS scores, which indicate relatively good applicability of the scoring system, even for less experienced readers.• When using the clinical JADAS10 as a reference standard for the detection of disease activity, moderate accuracy for both unenhanced and enhanced MRI scores, both JAMRIS and IPSG, was noted, which might be caused by the fact that the majority of patients had either no or minimal clinical disease activity.

Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity.

To evaluate the value of radiomics models created based on non-contrast enhanced T1 weighted (T1W) and T2W fat-saturated (T2WFS) images for staging hepatic fibrosis (HF) and grading inflammatory activity. Data of 280 patients with pathologically confirmed HF and 48 healthy volunteers were included. The participants were divided into the training set and the test set at the proportion of 4:1 by the random seed method. We used the Pyradiomics software to extract radiomics features, and then use the least absolute shrinkage and selection operator to select the optimal subset. Finally, we used the stochastic gradient descent classifier to build the prediction models. DeLong test was used to compare the diagnostic performance of the models. Receiver operating characteristics was used to evaluate the prediction ability of the models. The diagnostic efficiency of the models based on T1W & T2WFS images were the highest (all p < 0.05). When discriminating significant fibrosis (≥ F2), there were significant differences in the AUCs between the machine learning models based on T1W and T2WFS images (p < 0.05), but there were no significant differences in area under the receiver operating characteristic curves between the two models in other groups (all p > 0.05). The radiomics models built on T1W and T2WFS images are effective in assessing HF and inflammatory activity. Based on conventional MR sequences that are readily available in the clinic, namely unenhanced T1W and T2W images. Radiomics can be used for diagnosis and differential diagnosis of liver fibrosis staging and inflammatory activity grading.

NIMG-01. PREDICTING POST-STEREOTACTIC RADIOTHERAPY MAGNETIC RESONANCE IMAGE OUTCOMES OF BREAST CANCER METASTASES TO THE BRAIN

Abstract BACKGROUND Stereotactic radiosurgery (SRS) is a cornerstone in the management of Breast Cancer Metastases to the Brain (BCMB). While control rates are high following SRS, radiation necrosis is a rare but potentially devastating long-term toxicity. There is a clinical need for automated/semi-automated methods to assess tumor response and optimize the RT plans for local control with minimal long-term toxicity. Multiparametric MRI (mpMRI), particularly Apparent Diffusion Coefficient of water (ADC) maps, contain information that is mechanistically relatable to voxel-level tumor response to RT. We report a deep learning-based approach to predict post-SRS ADC maps, FLAIR, T2-weighted (T2W), T1-weighted unenhanced (T1W) and contrast-enhanced (T1WCE) images, from pre-SRS T1W, T1WCE, T2W and FLAIR images, ADC maps, and the delivered RT dose map. These “forward models” will enable the radiation oncologist to simulate radiologic outcomes and iteratively optimize RT plans for local control with minimal toxicity. METHODS We trained a variant of the pix2pix Generative Adversarial Network (GAN) on MRI and RT dose map data from 18 BCMB patients treated with stereotactic radiation with confirmed controlled and locally recurrent metastases. Patients were treated with stereotactic radiation dose of 1-40 Gy between 2013-2019. RESULTS On test data from 6 BCMB patients, the trained forward model predicted post-SRS ADC values within the Gross Tumor Volume (GTV) that were broadly in agreement with ground truth post-SRS ADC maps. In agreement with expectations, the forward model also predicts increasing post-RT ADC within the GTV with increasing simulated RT doses in the range of 1-71 Gy. We have also explored an inverse model to predict the RT dose map required to produce “prescribed” post-SRS ADC values within the GTV. CONCLUSIONS We envision that the forward models will assist the radiation oncologist in initial RT dose plan optimization, while the inverse model may be useful for daily RT plan optimization.

The influence of bone marrow edema for the assessment of the boundaries of necrotic lesions in patients with osteonecrosis of the femoral head

This study aimed to investigate the influence of bone marrow edema (BME) for the assessment of the boundaries of necrotic lesions using unenhanced and contrast-enhanced (CE) magnetic resonance (MR) images in patients with osteonecrosis of the femoral head (ONFH). We retrospectively reviewed 72 consecutive hips in 55 patients of ONFH that were Association Research Circulation Osseous (ARCO) stage III or higher and underwent both unenhanced and contrast-enhanced MR imaging between January 2005 and February 2016. The degree of extension of BMEs, and the boundaries of the necrotic lesions were compared using unenhanced and CE MR images on both mid coronal and mid oblique-axial slices. Forty-two percent of the coronal T1 images, 40% of the coronal fat-saturated T2 images, and 48% of the oblique-axial T1 images showed differences in the boundaries of necrotic lesion, by comparison with those of CET1-weighted MR images. The boundaries of necrotic lesions were clearly detected in all hips on CE coronal slices and 97% of all hips on CE oblique-axial slices. The BME grade in the difference group was significantly higher than in the non-difference group on the coronal plane (P = 0.0058). There were significant differences between the BME grade and duration from the onset of hip pain to MR imaging examination. Multivariate analyses revealed that the duration from the onset to MR imaging examination in both coronal (P = 0.0008) and oblique-axial slices (P = 0.0143) were independently associated with differences in the boundary of necrotic lesion between T1 and CET1-weighted MR images. Our findings suggest that unenhanced MR image may be insufficient for a precise assessment of the boundaries of the necrotic lesions for ONFH cases in the early phase of subchondral collapse due to the diffuse BME.

Development and external validation of a multiparametric MRI-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer: a retrospective multicenter study.

To establish and validate a radiomics model based on multiparametric magnetic resonance imaging (MRI), and to predict microsatellite instability (MSI) status in rectal cancer patients. A total of 199 patients with pathologically confirmed rectal cancer were included. The MSI status was confirmed by immunohistochemistry (IHC) staining. Clinical factors and laboratory data associated with MSI status were analyzed. The imaging data of 100 patients from one of the hospitals were used as the training set. The remaining 99 patients from the other two hospitals were used as the external validation set. The regions of interest (ROIs) were delineated from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1WI (CE-T1WI) sequence to extract the radiomics features. The Tree-based approach was used for feature selection. The models were constructed based on the four single sequences and a combination of the four sequences using the random forest (RF) algorithm. The external validation set was used to verify the generalization ability of each model. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were plotted to evaluate and compare the predictive performance of each model. In the four single-series models, the CE-T1WI model performed the best. The AUCs of the T1WI, T2WI, DWI, and CE-T1WI prediction models in the training set were 0.74, 0.71, 0.71, and 0.78, respectively, while in the external validation set, the corresponding AUCs were 0.67, 0.66, 0.70, and 0.77. The prediction and generalization performance of the combined model of multi-sequences was comparable to that of the CE-T1WI model and it was better than that of the remaining three single-series models, with AUC values of 0.78 and 0.78 in the training and validation sets, respectively. The established radiomics models based on CE-T1WI or multiparametric MRI have similar predictive performance. They have the potential to predict MSI status in rectal cancer patients. • A radiomics model for the prediction of MSI status in patients with rectal cancer was established and validated using external validation. • The models based on CE-T1WI or multiparametric MRI have better predictive performance than those based on single unenhanced sequence images. • The radiomics model has the potential to suggest MSI status in rectal cancer patients; however, it is not yet a substitute for histological confirmation.

Diagnostic performance of dual-energy computed tomography for HCC after transarterial chemoembolization: Utility of virtual unenhanced and low keV virtual monochromatic images.

The purpose of this study is to evaluate the usefulness of virtual unenhanced (VUE) and low keV virtual monochromatic images (VMI) for diagnosing viable hepatocellular carcinomas (HCC) after transarterial chemoembolization (TACE). This retrospective study included 53 patients with suspected viable HCC after TACE who underwent multiphasic liver computed tomography including true unenhanced (TUE) phase and conventional (CV) enhanced phases on a dual-energy scanner. VUE images, 40 keV and 55 keV VMIs of enhanced phases were reconstructed using dual-energy computed tomography data. For every patient, six combination image sets (TUE-CV; TUE-55; TUE-40; VUE-CV; VUE-55; VUE-40) were evaluated by two readers and compared with the reference standard.There was no statistically significant difference (P > .05) in sensitivity or specificity among all image combinations. In most combinations, interobserver agreements were almost perfect. The diagnostic odds ratio showed a higher trend in combinations with conventional images. Currently, with regards to diagnostic performance, liver computed tomography including TUE and CV enhanced phases is recommended for tumor surveillance after TACE because VUE and VMIs do not have a distinct advantage compared to conventional images.