Contrast-enhanced T1-weighted Research Articles

Assessment of multi-modal magnetic resonance imaging for glioma based on a deep learning reconstruction approach with the denoising method.

Deep learning reconstruction (DLR) with denoising has been reported as potentially improving the image quality of magnetic resonance imaging (MRI). Multi-modal MRI is a critical non-invasive method for tumor detection, surgery planning, and prognosis assessment; however, the DLR on multi-modal glioma imaging has not been assessed. To assess multi-modal MRI for glioma based on the DLR method. We assessed multi-modal images of 107 glioma patients (49 preoperative and 58 postoperative). All the images were reconstructed with both DLR and conventional reconstruction methods, encompassing T1-weighted (T1W), contrast-enhanced T1W (CE-T1), T2-weighted (T2W), and T2 fluid-attenuated inversion recovery (T2-FLAIR). The image quality was evaluated using signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Visual assessment and diagnostic assessment were performed blindly by neuroradiologists. In contrast with conventionally reconstructed images, (residual) tumor SNR for all modalities and tumor to white/gray matter CNR from DLR images were higher in T1W, T2W, and T2-FLAIR sequences. The visual assessment of DLR images demonstrated the superior visualization of tumor in T2W, edema in T2-FLAIR, enhanced tumor and necrosis part in CE-T1, and fewer artifacts in all modalities. Improved diagnostic efficiency and confidence were observed for preoperative cases with DLR images. DLR of multi-modal MRI reconstruction prototype for glioma has demonstrated significant improvements in image quality. Moreover, it increased diagnostic efficiency and confidence of glioma.

The prognostic role of MRI-based radiomics in tongue carcinoma: a multicentric validation study.

Radiomics is an emerging field that utilizes quantitative features extracted from medical images to predict clinically meaningful outcomes. Validating findings is crucial to assess radiomics applicability. We aimed to validate previously published magnetic resonance imaging (MRI) radiomics models to predict oncological outcomes in oral tongue squamous cell carcinoma (OTSCC). Retrospective multicentric study on OTSCC surgically treated from 2010 to 2019. All patients performed preoperative MRI, including contrast-enhanced T1-weighted (CE-T1), diffusion-weighted sequences and apparent diffusion coefficient map. We evaluated overall survival (OS), locoregional recurrence-free survival (LRRFS), cause-specific mortality (CSM). We elaborated different models based on clinical and radiomic data. C-indexes assessed the prediction accuracy of the models. We collected 112 consecutive independent patients from three Italian Institutions to validate the previously published MRI radiomic models based on 79 different patients. The C-indexes for the hybrid clinical-radiomic models in the validation cohort were lower than those in the training cohort but remained > 0.5 in most cases. CE-T1 sequence provided the best fit to the models: the C-indexes obtained were 0.61, 0.59, 0.64 (pretreatment model) and 0.65, 0.69, 0.70 (posttreatment model) for OS, LRRFS and CSM, respectively. Our clinical-radiomic models retain a potential to predict OS, LRRFS and CSM in heterogeneous cohorts across different centers. These findings encourage further research, aimed at overcoming current limitations, due to the variability of imaging acquisition, processing and tumor volume delineation.

PSMA PET/MR is a New Imaging Option for Identifying Glioma Recurrence and Predicting Prognosis.

Glioma is characterized by a high recurrence rate, while the results of the traditional imaging methods (including magnetic resonance imaging, MRI) to distinguish recurrence from treatment-related changes (TRCs) are poor. Prostate-specific membrane antigen (PSMA) (US10815200B2, Deutsches Krebsforschungszentrum, German Cancer Research Center) is a type II transmembrane glycoprotein overexpressed in glioma vascular endothelium, and it is a promising target for imaging and therapy. The study aimed to assess the performance of PSMA positron emission tomography/ magnetic resonance (PET/MR) for diagnosing recurrence and predicting prognosis in glioma patients. Patients suspected of glioma recurrence who underwent 18F-PSMA-1007 PET/MR were prospectively enrolled. Eight metabolic parameters and fifteen texture features of the lesion were extracted from PSMA PET/MR. The ability of PSMA PET/MR to diagnose glioma recurrence was investigated and compared with conventional MRI. The diagnostic agreement was assessed using Cohen κ scores and the predictive parameters of PSMA PET/MR were obtained. Kaplan-Meier method and Cox proportional hazard model were used to analyze recurrence- free survival (RFS) and overall survival (OS). Finally, the expression of PSMA was analyzed by immunohistochemistry (IHC). Nineteen patients with a mean age of 48.11±15.72 were assessed. The maximum tumorto- parotid ratio (TPRmax) and texture features extracted from PET and T1-weighted contrast enhancement (T1-CE) MR showed differences between recurrence and TRCs (all p <0.05). PSMA PET/MR and conventional MRI exhibited comparable power in diagnosing recurrence with specificity and PPV of 100%. The interobserver concordance was fair between the two modalities (κ = 0.542, p = 0.072). The optimal cutoffs of metabolic parameters, including standardized uptake value (SUV, SUVmax, SUVmean, and SUVpeak) and TPRmax for predicting recurrence were 3.35, 1.73, 1.99, and 0.17 respectively, with the area under the curve (AUC) ranging from 0.767 to 0.817 (all p <0.05). In grade 4 glioblastoma (GBM) patients, SUVmax, SUVmean, SUVpeak, TBRmax, TBRmean, and TPRmax showed improved performance of AUC (0.833-0.867, p <0.05). Patients with SUVmax, SUVmean, or SUVpeak more than the cutoff value had significantly shorter RFS (all p <0.05). In addition, patients with SUVmean, SUVpeak, or TPRmax more than the cutoff value had significantly shorter OS (all p <0.05). PSMA expression of glioma vascular endothelium was observed in ten (10/11, 90.9%) patients with moderate-to-high levels in all GBM cases (n = 6/6, 100%). This primitive study shows multiparameter PSMA PET/MR to be useful in identifying glioma (especially GBM) recurrence by providing excellent tumor background comparison, tumor heterogeneity, recurrence prediction and prognosis information, although it did not improve the diagnostic performance compared to conventional MRI. Further and larger studies are required to define its potential clinical application in this setting.

Nomogram of magnetic resonance imaging (MRI) histogram analysis to predict telomerase reverse transcriptase promoter mutation status in glioblastoma.

Telomerase reverse transcriptase promoter (pTERT) status is a strong biomarker to diagnose and predict the prognosis of glioblastoma (GBM). In this study, we explored the predictive value of preoperative magnetic resonance imaging (MRI) histogram analysis in the form of nomogram for evaluating pTERT mutation status in GBM. The clinical and imaging data of 181 patients with GBM at our hospital between November 2018 and April 2023 were retrospectively assessed. We used the molecular sequencing results to classify the datasets into pTERT mutations (C228T and C250T) and pTERT-wildtype groups. FireVoxel software was used to extract preoperative T1-weighted contrast-enhanced (T1C) histogram parameters of GBM patients. The T1C histogram parameters were compared between groups. Univariate and multivariate logistic regression analyses were used to construct the nomogram, and the predictive efficacy of model was evaluated using calibration and decision curves. Receiver operating characteristic curve was used to assess model performance. Patient age and percentage of unenhanced tumor area showed statistically significant differences between the pTERT mutation and pTERT-wildtype groups (P<0.001). Among the T1C histogram features, the maximum, standard deviation (SD), variance, coefficient of variation (CV), skewness, 5th, 10th, 25th, 95th and 99th percentiles were statistically significantly different between groups (P=0.000-0.040). Multivariate logistic regression analysis showed that age, percentage of unenhanced tumor area, SD and CV were independent risk factors for predicting pTERT mutation status in GBM patients. The logistic regression model based on these four features showed a better sample predictive performance, and the area under the curve (AUC) [95% confidence interval (CI)], accuracy, sensitivity, specificity were 0.842 (0.767-0.917), 0.796, 0.820, and 0.729, respectively. There were no significant differences in the T1C histogram parameters between the C228T and C250T groups (P=0.055-0.854). T1C histogram parameters can be used to evaluate pTERT mutations status in GBM. A nomogram based on conventional MRI features and T1C histogram parameters is a reliable tool for the pTERT mutation status, allowing for non-invasive radiological prediction before surgery.

Evaluation of the extracranial “multifocal arcuate sign,” a novel MRI finding for the diagnosis of giant cell arteritis, on STIR and contrast-enhanced T1-weighted images

BackgroundWhile early diagnosis of giant cell arteritis (GCA) based on clinical criteria and contrast-enhanced MRI findings can lead to early treatment and prevention of blindness and cerebrovascular accidents, previously reported diagnostic methods which utilize contrast-enhanced whole head images are cumbersome. Diagnostic delay is common as patients may not be aware of initial symptoms and their significance. To improve current diagnostic capabilities, new MRI-based diagnostic criteria need to be established. This study aimed to evaluate the “multifocal arcuate sign” on short tau inversion recovery (STIR) and contrast-enhanced T1-weighted (CE-T1W) images as a novel extracranial finding for the diagnosis of GCA.MethodsA total of 17 consecutive patients (including five with GCA) who underwent CE-T1W and whole-brain axial STIR imaging simultaneously between June 2010 and April 2020 were enrolled. We retrospectively reviewed their MR images. The “multifocal arcuate sign” was defined as “multiple distant arcuate areas with high signal intensity in extracranial soft tissues such as subcutaneous fat, muscles, and tendons.” Extracranial abnormal high-signal-intensity areas were classified as “None,” when no lesions were detected; “Monofocal,” when lesions were detected only in one place; and “Multifocal,” when lesions were detected in multiple places. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of “Multifocal” areas were calculated using cross tabulation. Fisher’s exact test was used to compare “Multifocal” areas in five patients with GCA and those with other diseases. In addition, mean Cohen’s kappa and Fleiss’ kappa statistics were used to compare inter-reader agreement.ResultsThe sensitivity, specificity, PPV, and NPV of the “multifocal arcuate sign” in patients with GCA were 60%, 92–100%, 75–100%, and 85–86%, respectively. Significantly more patients with GCA had “Multifocal” areas compared to those with other diseases (Fisher’s exact test, p = 0.008–0.027). Mean Cohen’s kappa and Fleiss’ kappa for inter-reader agreement with respect to the five GCA patients were 0.52 and 0.49, respectively, for both STIR and CE-T1W sequences.ConclusionsThe new radiologic finding of “multifocal arcuate sign” on STIR and CE-T1W images may be used as a radiologic criterion for the diagnosis of GCA, which can make plain MRI a promising diagnostic modality.

A combinatorial MRI sequence-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer

This study aimed to develop an optimal radiomics model for preoperatively predicting microsatellite instability (MSI) in patients with rectal cancer (RC) based on multiparametric magnetic resonance imaging. The retrospective study included 308 RC patients who did not receive preoperative antitumor therapy, among whom 51 had MSI. Radiomics features were extracted and dimensionally reduced from T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), diffusion-weighted imaging (DWI), and T1-weighted contrast enhanced (T1CE) images for each patient, and the features of each sequence were combined. Multifactor logistic regression was used to screen the optimal feature set for each combination. Different machine learning methods were applied to construct predictive MSI status models. Relative standard deviation values were determined to evaluate model performance and select the optimal model. Receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses were performed to evaluate model performance. The model constructed using the k-nearest neighbor (KNN) method combined with T2WI and T1CE images performed best. The area under the curve values for prediction of MSI with this model were 0.849 (0.804–0.887), with a sensitivity of 0.784 and specificity of 0.805. The Delong test showed no significant difference in diagnostic efficacy between the KNN-derived model and the traditional logistic regression model constructed using T1WI + DWI + T1CE and T2WI + T1WI + DWI + T1CE data (P > 0.05) and the diagnostic efficiency of the KNN-derived model was slightly better than that of the traditional model. From ROC curve analysis, the KNN-derived model significantly distinguished patients at low- and high-risk of MSI with the optimal threshold of 0.2, supporting the clinical applicability of the model. The model constructed using the KNN method can be applied to noninvasively predict MSI status in RC patients before surgery based on radiomics features from T2WI and T1CE images. Thus, this method may provide a convenient and practical tool for formulating treatment strategies and optimizing individual clinical decision-making for patients with RC.

Multiparametric magnetic resonance imaging-based assessment of the effect of adenomyosis on determining the depth of myometrial invasion in endometrial cancer.

Accurate preoperative diagnosis of endometrial cancer (EC) with deep myometrial invasion (DMI) is critical to deciding whether to perform lymphadenectomy. However, the presence of adenomyosis makes distinguishing DMI from superficial myometrial invasion (SMI) on magnetic resonance imaging (MRI) challenging. We aimed to evaluate the accuracy of multiparametric MRI (mpMRI) in diagnosing DMI in EC coexisting with adenomyosis (EC-A) compared with EC without coexisting adenomyosis and to evaluate the effect of different adenomyosis subtypes on myometrial invasion (MI) depth in EC. Patients with histologically confirmed International Federation of Gynecology and Obstetrics (FIGO) stage I EC who underwent preoperative MRI were consecutively included in this 2-center retrospective study. Institution 1 was searched from January 2017 to November 2022 and institution 2 was searched from June 2017 to March 2021. Patients were divided into 2 groups: group A, patients with EC-A; group B, EC patients without coexisting adenomyosis, matched 1:2 according to age ±5 years and tumor grade. A senior radiologist assessed the MRI adenomyosis classification in group A. Then, 2 radiologists (R1/R2) independently interpreted T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), T1-weighted contrast-enhanced (T1CE), and a combination of all images (mpMRI) respectively, and then assessed MI depth. Accuracy, sensitivity, specificity, and the areas under the receiver operating curve (AUC) were calculated. The chi-square test was used to compare the accuracy of diagnosing DMI. Interobserver agreement was evaluated using the Kappa test. A total of 70 cases in group A and 140 cases in group B were included. The accuracy, sensitivity, and specificity of consensus were 94.3% [95% confidence interval (CI): 88.9-99.7%] vs. 92.1% (95% CI: 87.7-96.6%), 60.0% (95% CI: 17-92.7%) vs. 86.7% (95% CI: 68.4-95.6%), and 96.9% (95% CI: 88.4-95.5%) vs. 93.6% (95% CI: 86.8-97.2%) (group A vs. group B, respectively). There was no significant difference in the diagnostic accuracy of DMI on each sequence between the groups (Reviewer 1/Reviewer 2): PT2WI=0.14/0.17, PDWI=0.50/0.33, PT1CE=0.90/0.18, PmpMRI=0.50/0.37. The AUC for T2WI, DWI, T1CE, and mpMRI (Reviewer 1/Reviewer 2), respectively, were 0.54 (95% CI: 0.42-0.66)/0.78 (95% CI: 0.67-0.87), 0.63 (95% CI: 0.50-0.74)/0.77 (95% CI: 0.65-0.86), 0.69 (95% CI: 0.57-0.80)/0.79 (95% CI: 0.68-0.88), and 0.91 (95% CI: 0.82-0.97)/0.89 (95% CI: 0.79-0.95) (group A) and 0.83 (95% CI: 0.76-0.89)/0.85 (95% CI: 0.78-0.90), 0.83 (95% CI: 0.76-0.89)/0.86 (95% CI: 0.79-0.91), 0.88 (95% CI: 0.82-0.93)/0.86 (95% CI: 0.80-0.92), and 0.91 (95% CI: 0.85-0.95)/0.87 (95% CI: 0.80-0.92) (group B). Interobserver agreement was highest with mpMRI [κ=0.387/0.695 (case/control)]. The consensus results of MRI categorization of adenomyosis revealed no significant difference in the accuracy of diagnosing DMI by adenomyosis subtype (Pspatial relationship>0.99, Paffected area=0.52, Paffected pattern=0.58, Paffected size>0.99). The presence of adenomyosis or adenomyosis subtype had no significant effect on the interpretation of the depth of MI. T1CE can increase the contrast between adenomyosis and cancer foci; therefore, the information provided by T1CE should be valued.

Convolutional neural network-based magnetic resonance image differentiation of filum terminale ependymomas from schwannomas

PurposePreoperative diagnosis of filum terminale ependymomas (FTEs) versus schwannomas is difficult but essential for surgical planning and prognostic assessment. With the advancement of deep-learning approaches based on convolutional neural networks (CNNs), the aim of this study was to determine whether CNN-based interpretation of magnetic resonance (MR) images of these two tumours could be achieved.MethodsContrast-enhanced MRI data from 50 patients with primary FTE and 50 schwannomas in the lumbosacral spinal canal were retrospectively collected and used as training and internal validation datasets. The diagnostic accuracy of MRI was determined by consistency with postoperative histopathological examination. T1-weighted (T1-WI), T2-weighted (T2-WI) and contrast-enhanced T1-weighted (CE-T1) MR images of the sagittal plane containing the tumour mass were selected for analysis. For each sequence, patient MRI data were randomly allocated to 5 groups that further underwent fivefold cross-validation to evaluate the diagnostic efficacy of the CNN models. An additional 34 pairs of cases were used as an external test dataset to validate the CNN classifiers.ResultsAfter comparing multiple backbone CNN models, we developed a diagnostic system using Inception-v3. In the external test dataset, the per-examination combined sensitivities were 0.78 (0.71–0.84, 95% CI) based on T1-weighted images, 0.79 (0.72–0.84, 95% CI) for T2-weighted images, 0.88 (0.83–0.92, 95% CI) for CE-T1 images, and 0.88 (0.83–0.92, 95% CI) for all weighted images. The combined specificities were 0.72 based on T1-WI (0.66–0.78, 95% CI), 0.84 (0.78–0.89, 95% CI) based on T2-WI, 0.74 (0.67–0.80, 95% CI) for CE-T1, and 0.81 (0.76–0.86, 95% CI) for all weighted images. After all three MRI modalities were merged, the receiver operating characteristic (ROC) curve was calculated, and the area under the curve (AUC) was 0.93, with an accuracy of 0.87.ConclusionsCNN based MRI analysis has the potential to accurately differentiate ependymomas from schwannomas in the lumbar segment.

MRI-based radiomics features for the non-invasive prediction of FIGO stage in cervical carcinoma: A multi-center study

PurposeTo develop and validate a model based on MRI radiomics modals for predicting surgical high FIGO(IB3 and ≥ IIA2) and low FIGO(IB1, IB2, and IIA1) stages in patients with cervical carcinoma (CC). MethodsA total of 296 early-stage patients with CC (preoperative FIGO stages IB-IIA) confirmed by surgery and pathology were included in this retrospective study from two institutions For each patient,we extracted radiomics features from spectral attenuated inversion-recovery T2-weighted (SPAIR-T2W) and contrast-enhanced T1-weighted (CE-T1W) images.Manual segmentation was performed using the 3D Slicer software, while radiomics features were extracted, screened using the R software. A 2-stage feature extraction strategy involving univariate analysis and the Least Absolute Shrinkage Selection Operator technique was performed. A support vector machine-based model was eventually constructed. Predictive accuracy of the training and validation datasets was assessed in terms of area under the ROC curve (AUC). ResultsA total of 1130 features were extracted from SPAIR-T2WI and CET1WI images respectively, in which 8 and 7 features significantly were associated with FIGO staging. AUCs of the SPAIR-T2W and CE-T1W models were were 0.803 and 0.790, respectively, in the internal validation group. In the external validation group, the AUCs were 0.767 and 0.749, respectively, which increased to 0.771 in the combined model. ConclusionOur study demonstrated the feasibility of radiomics features from SPAIR-T2W and CE-T1W images for the prediction of surgical FIGO stage in CC. Our proposed model thereby carries the potential as a non-invasive tool for the staging and treatment planning of this disease. Advances in knowledgeA radiomics model provide a non-invasive and objective method for the detection of FIGO staging in patients with cervical cancer before surgery, thus providing a reference for the selection of treatment options for patients.

Noninvasive prediction of IDH mutation status in gliomas using preoperative multiparametric MRI radiomics nomogram: A mutlicenter study

PurposeTo establish and validate a radiomics nomogram for preoperative prediction of isocitrate dehydrogenase (IDH) mutation status of gliomas in a multicenter setting. Methods414 gliomas patients were collected (306 from local institution and 108 from TCGA). 851 radiomics features were extracted from contrast-enhanced T1-weighted (CE-T1W) and fluid attenuated inversion recovery (FLAIR) sequence, respectively. The features were refined using least absolute shrinkage and selection operator (LASSO) regression combing 10-fold cross-validation. The optimal radiomics features with age and sex were processed by multivariate logistic regression analysis to construct a prediction model, which was developed in the training dataset and assessed in the test and validation dataset. Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis were applied in the test and external validation datasets to evaluate the performance of the prediction model. ResultsTen robust radiomics features were selected from the 1702 features (four CE-T1W features and six FLAIR features). A nomogram was plotted to represent the prediction model. The accuracy and AUC of the radiomics nomogram achieved 86.96% and 0.891(0.809–0.947) in the test dataset and 84.26% and 0.881(0.805–0.936) in the external validation dataset (all p < 0.05). The positive predictive value (PPV) and negative predictive value (NPV) were 83.72% and 87.75% in the test dataset and 87.81% and 82.09% in the external validation dataset. ConclusionIDH genotypes of gliomas can be identified by preoperative multiparametric MRI radiomics nomogram and might be clinically meaningful for treatment strategy and prognosis stratification of gliomas.

Whole-tumor histogram analysis of multi-parametric MRI for differentiating brain metastases histological subtypes in lung cancers: relationship with the Ki-67 proliferation index.

This study aims to investigate the predictive value of preoperative whole-tumor histogram analysis of multi-parametric MRI for histological subtypes in patients with lung cancer brain metastases (BMs) and explore the correlation between histogram parameters and Ki-67 proliferation index. The preoperative MRI data of 95 lung cancer BM lesions obtained from 73 patients (42 men and 31 women) were retrospectively analyzed. Multi-parametric MRI histogram was used to distinguish small-cell lung cancer (SCLC) from non-small cell lung cancer (NSCLC), and adenocarcinoma (AC) from squamous cell carcinoma (SCC), respectively. The T1-weighted contrast-enhanced (T1C) and apparent diffusion coefficient (ADC) histogram parameters of the volumes of interest (VOIs) in all BMs lesions were extracted using FireVoxel software. The following histogram parameters were obtained: maximum, minimum, mean, standard deviation (SD), variance, coefficient of variation (CV), skewness, kurtosis, entropy, and 1st-99th percentiles. Then investigated their relationship with the Ki-67 proliferation index. The skewness-T1C, kurtosis-T1C, minimum-ADC, mean-ADC, CV-ADC and 1st - 90th ADC percentiles were significantly different between the SCLC and NSCLC groups (all p < 0.05). When the 10th-ADC percentile was 668, the sensitivity, specificity, and accuracy (90.80%, 76.70% and 86.32%, respectively) for distinguishing SCLC from NSCLC reached their maximum values, with an AUC of 0.895 (0.824 - 0.966). Mean-T1C, CV-T1C, skewness-T1C, 1st - 50th T1C percentiles, maximum-ADC, SD-ADC, variance-ADC and 75th - 99th ADC percentiles were significantly different between the AC and SCC groups (all p < 0.05). When the CV-T1C percentiles was 3.13, the sensitivity, specificity and accuracy (75.00%, 75.60% and 75.38%, respectively) for distinguishing AC and SCC reached their maximum values, with an AUC of 0.829 (0.728-0.929). The 5th-ADC and 10th-ADC percentiles were strongly correlated with the Ki-67 proliferation index in BMs. Multi-parametric MRI histogram parameters can be used to identify the histological subtypes of lung cancer BMs and predict the Ki-67 proliferation index.

Development of clinical and magnetic resonance imaging-based radiomics nomograms for the differentiation of nodular fasciitis from soft tissue sarcoma.

Accurate differentiation of nodular fasciitis (NF) from soft tissue sarcoma (STS) before surgery is essential for the subsequent diagnosis and treatment of patients. To develop and evaluate radiomics nomograms based on clinical factors and magnetic resonance imaging (MRI) for the preoperative differentiation of NF from STS. This retrospective study analyzed the MRI data of 27 patients with pathologically diagnosed NF and 58 patients with STS who were randomly divided into training (n = 62) and validation (n = 23) groups. Univariate and multivariate analyses were performed to identify the clinical factors and semantic features of MRI. Radiomics analysis was applied to fat-suppressed T1-weighted (T1W-FS) images, fat-suppressed T2-weighted (T2W-FS) images, and contrast-enhanced T1-weighted (CE-T1W) images. The radiomics nomograms incorporating the radiomics signatures, clinical factors, and semantic features of MRI were developed. ROC curves and AUCs were carried out to compare the performance of the clinical factors, radiomics signatures, and clinical radiomics nomograms. Tumor location, size, heterogeneous signal intensity on T2W-FS imaging, heterogeneous signal intensity on CE-T1W imaging, margin definitions on CE-T1W imaging, and septa were independent predictors for differentiating NF from STS (P < 0.05). The performance of the radiomics signatures based on T2W-FS imaging (AUC = 0.961) and CE-T1W imaging (AUC = 0.938) was better than that based on T1W-FS imaging (AUC = 0.833). The radiomics nomograms had AUCs of 0.949, which demonstrated good clinical utility and calibration. The non-invasive clinical radiomics nomograms exhibited good performance in the differentiation of NF from STS, and they have clinical application in the preoperative diagnosis of diseases.

Contrast-enhanced MRI synthesis using dense-dilated residual convolutions based 3D network toward elimination of gadolinium in neuro-oncology.

Recent studies have raised broad safety and health concerns about using of gadolinium contrast agents during magnetic resonance imaging (MRI) to enhance identification of active tumors. In this paper, we developed a deep learning-based method for three-dimensional (3D) contrast-enhanced T1-weighted (T1) image synthesis from contrast-free image(s). The MR images of 1251 patients with glioma from the RSNA-ASNR-MICCAI BraTS Challenge 2021 dataset were used in this study. A 3D dense-dilated residual U-Net (DD-Res U-Net) was developed for contrast-enhanced T1 image synthesis from contrast-free image(s). The model was trained on a randomly split training set (n=800) using a customized loss function and validated on a validation set (n=200) to improve its generalizability. The generated images were quantitatively assessed against the ground-truth on a test set (n=251) using the mean absolute error (MAE), mean-squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), normalized mutual information (NMI), and Hausdorff distance (HDD) metrics. We also performed a qualitative visual similarity assessment between the synthetic and ground-truth images. The effectiveness of the proposed model was compared with a 3D U-Net baseline model and existing deep learning-based methods in the literature. Our proposed DD-Res U-Net model achieved promising performance for contrast-enhanced T1 synthesis in both quantitative metrics and perceptual evaluation on the test set (n=251). Analysis of results on the whole brain region showed a PSNR (in dB) of 29.882±5.924, a SSIM of 0.901±0.071, a MAE of 0.018±0.013, a MSE of 0.002±0.002, a HDD of 2.329±9.623, and a NMI of 1.352±0.091 when using only T1 as input; and a PSNR (in dB) of 30.284±4.934, a SSIM of 0.915±0.063, a MAE of 0.017±0.013, a MSE of 0.001±0.002, a HDD of 1.323±3.551, and a NMI of 1.364±0.089 when combining T1 with other MRI sequences. Compared to the U-Net baseline model, our model revealed superior performance. Our model demonstrated excellent capability in generating synthetic contrast-enhanced T1 images from contrast-free MR image(s) of the whole brain region when using multiple contrast-free images as input. Without incorporating tumor mask information during network training, its performance was inferior in the tumor regions compared to the whole brain which requires further improvements to replace the gadolinium administration in neuro-oncology.

An Explainable MRI-Radiomic Quantum Neural Network to Differentiate Between Large Brain Metastases and High-Grade Glioma Using Quantum Annealing for Feature Selection

Solitary large brain metastases (LBM) and high-grade gliomas (HGG) are sometimes hard to differentiate on MRI. The management differs significantly between these two entities, and non-invasive methods that help differentiate between them are eagerly needed to avoid potentially morbid biopsies and surgical procedures. We explore herein the performance and interpretability of an MRI-radiomics variational quantum neural network (QNN) using a quantum-annealing mutual-information (MI) feature selection approach. We retrospectively included 423 patients with HGG and LBM (> 2 cm) who had a contrast-enhanced T1-weighted (CE-T1) MRI between 2012 and 2019. After exclusion, 72 HGG and 129 LBM were kept. Tumors were manually segmented, and a 5-mm peri-tumoral ring was created. MRI images were pre-processed, and 1813 radiomic features were extracted. A set of best features based on MI was selected. MI and conditional-MI were embedded into a quadratic unconstrained binary optimization (QUBO) formulation that was mapped to an Ising-model and submitted to D’Wave’s quantum annealer to solve for the best combination of 10 features. The 10 selected features were embedded into a 2-qubits QNN using PennyLane library. The model was evaluated for balanced-accuracy (bACC) and area under the receiver operating characteristic curve (ROC-AUC) on the test set. The model performance was benchmarked against two classical models: dense neural networks (DNN) and extreme gradient boosting (XGB). Shapley values were calculated to interpret sample-wise predictions on the test set. The best 10-feature combination included 6 tumor and 4 ring features. For QNN, DNN, and XGB, respectively, training ROC-AUC was 0.86, 0.95, and 0.94; test ROC-AUC was 0.76, 0.75, and 0.79; and test bACC was 0.74, 0.73, and 0.72. The two most influential features were tumor Laplacian-of-Gaussian-GLRLM-Entropy and sphericity. We developed an accurate interpretable QNN model with quantum-informed feature selection to differentiate between LBM and HGG on CE-T1 brain MRI. The model performance is comparable to state-of-the-art classical models.

Tumor-liver interface in MRI of liver metastasis enables prediction of EGFR mutation in patients with lung cancer: A proof-of-concept study.

Preoperative prediction of the epidermal growth factor receptor (EGFR) status in non-small-cell lung cancer (NSCLC) patients with liver metastasis (LM) may have potential clinical values for assisting in treatment decision-making. To explore the value of tumor-liver interface (TLI)-based magnetic resonance imaging (MRI) radiomics for detecting the EGFR mutation in NSCLC patients with LM. This retrospective study included 123 and 44 patients from hospital 1 (between Feb. 2018 and Dec. 2021) and hospital 2 (between Nov. 2015 and Aug. 2022), respectively. The patients received contrast-enhanced T1-weighted (CET1) and T2-weighted (T2W) liver MRI scans before treatment. Radiomics features were extracted from MRI images of TLI and the whole tumor region, separately. The least absolute shrinkage and selection operator (LASSO) regression was used to screen the features and establish radiomics signatures (RSs) based on TLI (RS-TLI) and the whole tumor (RS-W). The RSs were evaluated by the receiver operating characteristic (ROC) curve analysis. A total of 5 and 6 features were identified highly correlated with the EGFR mutation status from TLI and the whole tumor, respectively. The RS-TLI showed better prediction performance than RS-W in the training (AUCs, RS-TLI vs. RS-W, 0.842vs. 0.797), internal validation (AUCs, RS-TLI vs. RS-W, 0.771vs. 0.676) and external validation (AUCs, RS-TLI vs. RS-W, 0.733vs. 0.679) cohort. Our study demonstrated that TLI-based radiomics can improve prediction performance of the EGFR mutation in lung cancer patients with LM. The established multi-parametric MRI radiomics models may be used as new markers that can potentially assist in personalized treatment planning.

Explainable machine learning via intra-tumoral radiomics feature mapping for patient stratification in adjuvant chemotherapy for locoregionally advanced nasopharyngeal carcinoma.

This study aimed to discover intra-tumor heterogeneity signature and validate its predictive value for adjuvant chemotherapy (ACT) following concurrent chemoradiotherapy (CCRT) in locoregionally advanced nasopharyngeal carcinoma (LA-NPC). 397 LA-NPC patients were retrospectively enrolled. Pre-treatment contrast-enhanced T1-weighted (CET1-w) MR images, clinical variables, and follow-up were retrospectively collected. We identified single predictive radiomic feature from primary gross tumor volume (GTVnp) and defined predicted subvolume by calculating voxel-wised feature mapping and within GTVnp. We independently validate predictive value of identified feature and associated predicted subvolume. Only one radiomic feature, gldm_DependenceVariance in 3mm-sigma LoG-filtered image, was discovered as a signature. In the high-risk group determined by the signature, patients received CCRT + ACT achieved 3-year disease free survival (DFS) rate of 90% versus 57% (HR, 0.20; 95%CI, 0.05-0.94; P = 0.007) for CCRT alone. The multivariate analysis showed patients receiving CCRT + ACT had a HR of 0.21 (95%CI: 0.06-0.68, P = 0.009) for DFS compared to those receiving CCRT alone. The predictive value can also be generalized to the subvolume with multivariate HR of 0.27 (P = 0.017) for DFS. The signature with its heterogeneity mapping could be a reliable and explainable ACT decision-making tool in clinical practice.

Magnetic resonance imaging characteristics of brain metastases in small cell lung cancer.

Lung is the most common primary site of brain metastases (BMs). For different pathological types of BMs have some similar characteristics, it is still a challenge to confirm the origin based on their characteristics directly. BMs of small cell lung cancer (SCLC) have favorable therapeutic expectations due to their high sensitivity to radiotherapy. This study sought to identify unique characteristics of BMs in SCLC, aiming to assist in clinical decision-making. Patients diagnosed with BMs of lung cancer who received radiotherapy from January 2017 to January 2022 were reviewed (N = 284). Definitive diagnosis of BMs of SCLC was reached for 36 patients. All patients underwent head examination using magnetic resonance imaging. The number, size, location, and signal characteristics of lesions were analyzed. There were 7 and 29 patients with single focus and non-single focus, respectively. Ten patients had diffuse lesions, and the remaining 26 patients had a total of 90 lesions. These lesions were divided into three groups according to size: <1, 1-3, and >3 cm (43.33%, 53.34%, and 3.33%, respectively). Sixty-six lesions were located in the supratentorial area, primarily including cortical and subcortical lesions (55.56%) and deep brain lesions (20%). Moreover, 22 lesions were located in the infratentorial area. According to diffusion-weighted imaging and T1-weighted contrast enhancement, the imaging characteristics were classified into six patterns. Hyperintensity in diffusion-weighted imaging and homogeneous enhancement was the most common pattern of BMs in SCLC (46.67%), while partial lesions showed hyperintensity in diffusion-weighted imaging without enhancement (7.78%). The manifestations of BMs in SCLC were multiple lesions (diameter: 1-3 cm), hyperintensity in diffusion-weighted imaging, and homogeneous enhancement. Interestingly, hyperintensity in diffusion-weighted imaging without enhancement was also one of the characteristics.

LAVA HyperSense and deep-learning reconstruction for near-isotropic (3D) enhanced magnetic resonance enterography in patients with Crohn's disease: utility in noise reduction and image quality improvement.

This study aimed to compare near-isotropic contrast-enhanced T1-weighted (CE-T1W) magnetic resonance enterography (MRE) images reconstructed with vendor-supplied deep-learning reconstruction (DLR) with those reconstructed conventionally in terms of image quality. A total of 35 patients who underwent MRE for Crohn's disease between August 2021 and February 2022 were included in this retrospective study. The enteric phase CE-T1W MRE images of each patient were reconstructed with conventional reconstruction and no image filter (original), with conventional reconstruction and image filter (filtered), and with a prototype version of AIRTM Recon DL 3D (DLR), which were then reformatted into the axial plane to generate six image sets per patient. Two radiologists independently assessed the images for overall image quality, contrast, sharpness, presence of motion artifacts, blurring, and synthetic appearance for qualitative analysis, and the signal-to-noise ratio (SNR) was measured for quantitative analysis. The mean scores of the DLR image set with respect to overall image quality, contrast, sharpness, motion artifacts, and blurring in the coronal and axial images were significantly superior to those of both the filtered and original images (P < 0.001). However, the DLR images showed a significantly more synthetic appearance than the other two images (P < 0.05). There was no statistically significant difference in all scores between the original and filtered images (P > 0.05). In the quantitative analysis, the SNR was significantly increased in the order of original, filtered, and DLR images (P < 0.001). Using DLR for near-isotropic CE-T1W MRE improved the image quality and increased the SNR.

Development and Validation of a Deep Learning Predictive Model Combining Clinical and Radiomic Features for Short-Term Postoperative Facial Nerve Function in Acoustic Neuroma Patients.

This study aims to construct and validate a predictable deep learning model associated with clinical data and multi-sequence magnetic resonance imaging (MRI) for short-term postoperative facial nerve function in patients with acoustic neuroma. A total of 110 patients with acoustic neuroma who underwent surgery through the retrosigmoid sinus approach were included. Clinical data and raw features from four MRI sequences (T1-weighted, T2-weighted, T1-weighted contrast enhancement, and T2-weighted-Flair images) were analyzed. Spearman correlation analysis along with least absolute shrinkage and selection operator regression were used to screen combined clinical and radiomic features. Nomogram, machine learning, and convolutional neural network (CNN) models were constructed to predict the prognosis of facial nerve function on the seventh day after surgery. Receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were used to evaluate model performance. A total of 1050 radiomic parameters were extracted, from which 13 radiomic and 3 clinical features were selected. The CNN model performed best among all prediction models in the test set with an area under the curve (AUC) of 0.89 (95% CI, 0.84-0.91). CNN modeling that combines clinical and multi-sequence MRI radiomic features provides excellent performance for predicting short-term facial nerve function after surgery in patients with acoustic neuroma. As such, CNN modeling may serve as a potential decision-making tool for neurosurgery.

MRI of Peliosis Hepatis: A Case Series Presentation With a 2022 Systematic Literature Update.

Peliosis hepatis (PH) is a rare benign condition, characterized by hepatic sinusoidal dilatation and blood-filled cystic cavities, often found incidentally, with still challenging diagnosis by imaging due to polymorphic appearance. Based on a retrospective analysis of our series (12 patients) and systematic literature review (1990-2022), to organize data about PH and identify features to improve characterization. Retrospective case series and systematic review. Twelve patients (mean age 48 years, 55% female) with pathology-proven PH and 49 patients (mean age 52 years, 67% female) identified in 33 studies from the literature (1990-2022). 1,5-T; T1-weighted (T1W), T2-weighted (T2W), diffusion-weighted (DW), contrast-enhanced (CE) T1W imaging. We compared our series and literature data in terms of demographic (gender/age/ethnicity), clinical characteristics (symptoms/physical examination/liver test), associated conditions (malignancies/infectious/hematologic/genetic or chronic disorders/drugs or toxic exposure) percentage. On magnetic resonance imaging lesion numbers/shape/mean maximum diameter/location/mass effect/signal intensity were compared. PH pathological type/proposed imaging diagnosis/patient follow-up were also considered. Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Case Reports/Series quality assessment. Intraclass correlation and Cohen's kappa coefficients for levels of inter/intrareader agreement in our experience. Patients were mainly asymptomatic (92% vs. 70% in our study and literature) with associated conditions (83% vs. 80%). Lesions showed homogeneous T1W-hypointensity (58% vs. 65%) and T2W-hyperintensity (58% vs. 66%). Heterogeneous nonspecific (25% vs. 51%), centrifugal (34% vs. 8%), or rim-like centripetal (25% vs. 23%) patterns of enhancement were most frequent, with hypointensity on the hepatobiliary phase (HBP), without restricted diffusivity. Good inter- and intrareader agreement was observed in our experience. Concerning JBI Checklist, 19 out of 31 case reports met at least 7 out of 8 criteria, whereas 2 case series fulfilled 5 and 6 out of 10 items respectively. A homogeneous, not well-demarcated T1W-hypointense and T2W-hyperintense mass, with heterogeneous nonspecific or rim-like centripetal or centrifugal pattern of enhancement, and hypointensity on HBP, may be helpful for PH diagnosis. Among associated conditions, malignancies and drug exposures were the most frequent. 4 TECHNICAL EFFICACY: Stage 2.