Contrast-enhanced T1-weighted Magnetic Resonance Imaging Research Articles

Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning.

Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

Intravascular papillary endothelial hyperplasia of the maxillary sinus extending into the contralateral nasal cavity

IntroductionIntravascular papillary endothelial hyperplasia (IPEH) predominantly occurs in the subcutaneous and dermal regions and rarely originates from the sinonasal mucosa.Case presentationWe report on the case of a 58-year-old male patient who presented with progressive bilateral nasal obstruction, left-sided epiphora, and intermittent epistaxis. Computed tomography revealed a soft tissue opacity in the left maxillary sinus with intersinusoidal nasal wall demineralization, extending into the surrounding ethmoid cells and the right nasal cavity through a contralateral deviation of the nasal septum. Contrast-enhanced T1-weighted magnetic resonance imaging further confirmed these findings. The IPEH originating from the maxillary sinus extended into the contralateral nasal cavity, and it was successfully removed using an endoscopic endonasal approach, avoiding overly aggressive treatment.ConclusionThis case report highlights the diagnostic challenges of IPEH in the sinonasal region and the importance of considering IPEH as a differential diagnosis in patients presenting with nasal obstruction, epiphora, and intermittent epistaxis.

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.

Deep learning–based automatic segmentation of meningioma from T1-weighted contrast-enhanced MRI for preoperative meningioma differentiation using radiomic features

BackgroundThis study aimed to establish a dedicated deep-learning model (DLM) on routine magnetic resonance imaging (MRI) data to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations. Another purpose of our work was to develop a radiomics model based on the radiomics features extracted from automatic segmentation to differentiate low- and high-grade meningiomas before surgery.MaterialsA total of 326 patients with pathologically confirmed meningiomas were enrolled. Samples were randomly split with a 6:2:2 ratio to the training set, validation set, and test set. Volumetric regions of interest (VOIs) were manually drawn on each slice using the ITK-SNAP software. An automatic segmentation model based on SegResNet was developed for the meningioma segmentation. Segmentation performance was evaluated by dice coefficient and 95% Hausdorff distance. Intra class correlation (ICC) analysis was applied to assess the agreement between radiomic features from manual and automatic segmentations. Radiomics features derived from automatic segmentation were extracted by pyradiomics. After feature selection, a model for meningiomas grading was built.ResultsThe DLM detected meningiomas in all cases. For automatic segmentation, the mean dice coefficient and 95% Hausdorff distance were 0.881 (95% CI: 0.851–0.981) and 2.016 (95% CI:1.439–3.158) in the test set, respectively. Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636–0.933). Features extracted on manual and automatic segmentation are comparable: the average ICC value was 0.804 (range, 0.636–0.933). For meningioma classification, the radiomics model based on automatic segmentation performed well in grading meningiomas, yielding a sensitivity, specificity, accuracy, and area under the curve (AUC) of 0.778 (95% CI: 0.701–0.856), 0.860 (95% CI: 0.722–0.908), 0.848 (95% CI: 0.715–0.903) and 0.842 (95% CI: 0.807–0.895) in the test set, respectively.ConclusionsThe DLM yielded favorable automated detection and segmentation of meningioma and can help deploy radiomics for preoperative meningioma differentiation in clinical practice.

Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning.

Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning. We trained and validated a deep learning network by using MR images from 335 subjects in the Brain Tumor Segmentation Challenge 2019 training data set. A held out set of 125 subjects from the Brain Tumor Segmentation Challenge 2019 validation data set was used to test the generalization of the model. A residual inception DenseNet network, called T1c-ET, was developed and trained to simultaneously synthesize virtual contrast-enhanced T1-weighted (vT1c) images and segment the enhancing portions of the tumor. Three expert neuroradiologists independently scored the synthesized vT1c images by using a 3-point Likert scale, evaluating image quality and contrast enhancement against ground truth T1c images (1 = poor, 2 = good, 3 = excellent). The synthesized vT1c images achieved structural similarity index, peak signal-to-noise ratio, and normalized mean square error scores of 0.91, 64.35, and 0.03, respectively. There was moderate interobserver agreement between the 3 raters, regarding the algorithm's performance in predicting contrast enhancement, with a Fleiss kappa value of 0.61. Our model was able to accurately predict contrast enhancement in 88.8% of the cases (scores of 2 to 3 on the 3-point scale). We developed a novel deep learning architecture to synthesize virtual postcontrast enhancement by using only conventional noncontrast brain MR images. Our results demonstrate the potential of deep learning methods to reduce the need for gadolinium contrast in the evaluation of primary brain tumors.

Automated volumetry of meningiomas in contrast-enhanced T1-Weighted MRI using deep learning

Background: Meningiomas are among the most common intracranial tumors. In these tumors, volumetric assessment is not only important for planning therapeutic intervention but also for follow-up examination.However, a highly accurate automated volumetric method for meningiomas using single-modality magnetic resonance imaging (MRI) has not yet been reported. Here, we aimed to develop a deep learning-based automated volumetry method for meningiomas in MRI and investigate its accuracy and potential clinical applications. Methods: For deep learning, we used MRI images of patients with meningioma who were referred to Osaka University Hospital between January 2007 and October 2020. Imaging data of eligible patients were divided into three non-overlapping groups: training, validation, and testing. The model was trained and tested using the leave-oneout cross-validation method. Dice index (DI) and root mean squared percentage error (RMSPE) were measured to evaluate the model accuracy. Result: A total of 178 patients (64.6 ± 12.3 years [standard deviation]; 147 women) were evaluated. Comparison of the deep learning model and manual segmentation revealed a mean DI of 0.923 ± 0.051 for tumor lesions. For total tumor volume, RMSPE was 9.5 ± 1.2%, and Mann–Whitney U test did not show a significant difference between manual and algorithm-based measurement of the tumor volume (p = 0.96). Conclusion: The automatic tumor volumetry algorithm developed in this study provides a potential volume-based imaging biomarker for tumor evaluation in the field of neuroradiological imaging, which will contribute to the optimization and personalization of treatment for central nervous system tumors in the near future

A MRI-based radiomics combined prediction model for radiation-induced temporal lobe injury in nasopharyngeal carcinoma patients

PurposeRadiation-induced temporal lobe injury (RTLI) is a common radiation-induced injury in patients with nasopharyngeal carcinoma (NPC). Our aim is to evaluate the potential factors associated with RTLI and to develop a predictive model to assess RTLI. MethodA total of 393 NPC patients who had received full course radiotherapy at two institutions were included. Patients from institution I were divided into a training cohort and a testing cohort according to the time of first-line treatment. Patients from institution II were used for external validation. The pre-treatment T1-weighted, T2-weighted and contrast-enhanced T1-weighted (T1c-weighted) magnetic resonance imaging (MRI) images before treatment were retrieved for radiomics feature extraction. The left and right temporal regions were separately defined and delineated as regions of interest (ROIs) by the MIM segmentation system. The relative contributions of different MRI sequences to the radiomics (Rad) score evaluation were compared. The least absolute shrinkage and selection operator (LASSO) regression algorithm was used to calculate Rad scores and develop comprehensive models. ResultsThe radiomics model consisting of all MRI features (combined T1-weighted, T2-weighted and T1c-weighted) was most associated with RTLI. The AUCs were 0.77 (95% CI: 0.69–0.85) in the testing cohort and 0.74 (95% CI: 0.70–0.79) in the external validation cohort. The AUC for the clinical-only model (including clinical stage and D0.5 cc) was 0.52 (95% CI: 0.31–0.74), whereas models including clinical factors (clinical stage), dosimetric factors (D0.5 cc) and Rad scores from all MRI sequences were more optimal. The AUC was 0.76 (95% CI: 0.67–0.84). ConclusionWe generated a feasible RTLI prediction model with radiomics, clinical and dosimetric factors.

Long-term neurocognitive and psychological outcomes in meningioma survivors: Individual changes over time and radiation dosimetry.

This study investigates long-term changes in neurocognitive performance and psychological symptoms in meningioma survivors and associations with radiation dose to circumscribed brain regions. We undertook a retrospective study of meningioma survivors who underwent longitudinal clinical neurocognitive assessments. Change in neurocognitive performance or psychological symptoms was assessed using reliable change indices. Radiation dosimetry, if prescribed, was evaluated based on treatment-planning computerized tomography co-registered with contrast-enhanced 3D T1-weighted magnetic resonance imaging. Mixed effects analyses were used to explore whether incidental radiation to brain regions outside the tumor influences neurocognitive and psychological outcomes. Most (range = 41%-93%) survivors demonstrated stable-albeit often below average-neurocognitive and psychological trajectories, although some also exhibited improvements (range = 0%-31%) or declines (range = 0%-36%) over time. Higher radiation dose to the parietal-occipital region (partial R2 = 0.462) and cerebellum (partial R2 = 0.276) was independently associated with slower visuomotor processing speed. Higher dose to the hippocampi was associated with increases in depression (partial R2 = 0.367) and trait anxiety (partial R2 = 0.236). Meningioma survivors experience neurocognitive deficits and psychological symptoms many years after diagnosis, and a proportion of them decline over time. This study offers proof of concept that incidental radiation to brain regions beyond the tumor site may contribute to these sequelae. Future investigations should include radiation dosimetry when examining risk factors that contribute to the quality of survivorship in this growing population.

Application of Delayed Contrast Extravasation Magnetic Resonance Imaging for Depicting Subtle Blood-Brain Barrier Disruption in a Traumatic Brain Injury Model.

The blood-brain barrier (BBB) is composed of brain microvasculature that provides selective transport of solutes from the systemic circulation into the central nervous system to protect the brain and spinal microenvironment. Damage to the BBB in the acute phase after traumatic brain injury (TBI) is recognized as a major underlying mechanism leading to secondary long-term damage. Because of the lack of technological ability to detect subtle BBB disruption (BBBd) in the chronic phase, however, the presence of chronic BBBd is disputable. Thus, the dynamics and course of long-term BBBd post-TBI remains elusive. Thirty C57BL/6 male mice subjected to TBI using our weight drop closed head injury model and 19 naïve controls were scanned by magnetic resonance imaging (MRI) up to 540 days after injury. The BBB maps were calculated from delayed contrast extravasation MRI (DCM) with high spatial resolution and high sensitivity to subtle BBBd, enabling depiction and quantification of BBB permeability. At each time point, 2-6 animals were sacrificed and their brains were extracted, sectioned, and stained for BBB biomarkers including: blood microvessel coverage by astrocyte using GFAP, AQP4, ZO-1 gaps, and IgG leakage. We found that DCM provided depiction of subtle yet significant BBBd up to 1.5 years after TBI, with significantly higher sensitivity than standard contrast-enhanced T1-weighted and T2-weighted MRI (BBBd volumes main effect DCM/T1/T2 p < 0.0001 F(2,70) = 107.3, time point p < 0.0001 F(2,133, 18.66) = 23.53). In 33% of the cases, both in the acute and chronic stages, there was no detectable enhancement on standard T1-MRI, nor detectable hyperintensities on T2-MRI, whereas DCM showed significant BBBd volumes. The BBBd values of TBI mice at the chronic stage were found significantly higher compared with age matched naïve animals at 30, 60, and 540 days. The calculated BBB maps were histologically validated by determining significant correlation between the calculated levels of disruption and a diverse set of histopathological parameters obtained from different brain regions, presenting different components of the BBB. Cumulative evidence from recent years points to BBBd as a central component of the pathophysiology of TBI. Therefore, it is expected that routine use of highly sensitive non-invasive techniques to measure BBBd, such as DCM with advanced analysis methods, may enhance our understanding of the changes in BBB function after TBI. Application of the DCM technology to other CNS disorders, as well as to normal aging, may shed light on the involvement of chronic subtle BBBd in these conditions.

Automated segmentation of meningioma from contrast-enhanced T1-weighted MRI images in a case series using a marker-controlled watershed segmentation and fuzzy C-means clustering machine learning algorithm

Introduction and importanceAccurate segmentation of meningiomas from contrast-enhanced T1-weighted (CE T1-w) magnetic resonance imaging (MRI) is crucial for diagnosis and treatment planning. Manual segmentation is time-consuming and prone to variability. To evaluate an automated segmentation approach for meningiomas using marker-controlled watershed segmentation (MCWS) and fuzzy c-means (FCM) algorithms. Case presentation and methodsCE T1-w MRI of 3 female patients (aged 59, 44, 67 years) with right frontal meningiomas were analyzed. Images were converted to grayscale and preprocessed with Otsu's thresholding and FCM clustering. MCWS segmentation was performed. Segmentation accuracy was assessed by comparing automated segmentations to manual delineations. Clinical discussionThe approach successfully segmented meningiomas in all cases. Mean sensitivity was 0.8822, indicating accurate identification of tumors. Mean Dice similarity coefficient between Otsu's and FCM1 was 0.6599, suggesting good overlap between segmentation methods. ConclusionThe MCWS and FCM approach enables accurate automated segmentation of meningiomas from CE T1-w MRI. With further validation on larger datasets, this could provide an efficient tool to assist in delineating meningioma boundaries for clinical management.

Predicting the BRAF mutation with pretreatment MRI radiomics features for melanoma brain metastases receiving Gamma Knife radiosurgery

To develop a model using radiomics features extracted from magnetic resonance imaging (MRI) images of Gamma Knife radiosurgery (GKRS) to predict the BRAF mutation in patients with melanoma brain metastases (MBM). Data of 220 tumours were classified into two groups. One was a group whose BRAF mutation was identified, and the other group whose BRAF mutation was not identified. We extracted 1,962 radiomics features from gadolinium contrast-enhanced T1-weighted MRI treatment-planning images. Synthetic Minority Over-sampling TEchnique (SMOTE) was performed to address the unbalanced data-related issues. A single-layer neural network (NN) was used to build predictive models with radiomics features. The sensitivity, specificity, accuracy, and the area under the curve (AUC) were evaluated to assess the model performance. The prediction performance for the final evaluation without the SMOTE had an accuracy of 77.14%, a specificity of 82.44%, a sensitivity of 81.85%, and an AUC of 0.79. The application of SMOTE improved the prediction model to an accuracy of 83.1%, a specificity of 87.07%, a sensitivity of 78.82%, and an AUC of 0.82. The current study showed the feasibility of generating a highly accurate NN model for the BRAF mutation prediction. The prediction performance improved with SMOTE. The model assists physicians to obtain more accurate expectations of the treatment outcome without a genetic test.

Correlation of tumor-associated macrophage infiltration in glioblastoma with magnetic resonance imaging characteristics: a retrospective cross-sectional study.

Glioblastoma (Gb) is the most common primary malignant tumor of brain with poor prognosis. Immune cells are the main factors affecting the prognosis of Gb, tumor-associated macrophages (TAMs) are the predominant infiltrating immune cell population in the immune microenvironment of Gb. Analyzing the relationship between magnetic resonance imaging (MRI) features and TAMs of Gb, and using imaging features to characterize the infiltration level of TAMs in tumor tissue may provide indicators for clinical decision-making and prognosis evaluation of Gb. Data from 140 in patients with isocitrate dehydrogenase (IDH) wild-type Gb diagnosed via histopathology and molecular diagnosis in the Second Hospital of Lanzhou University from January 2018 to April 2022 were collected in this retrospective, cross-sectional study. MRI images were reviewed for lesion location, cyst, necrosis, hemorrhage, contrast-enhanced T1-weighted MRI signal intensity, average apparent diffusion coefficient (ADCmean), and minimum apparent diffusion coefficient (ADCmin). Immunohistochemical staining with anti-CD163 and anti-CD68 antibodies was employed for macrophage detection. The positive cell percentage was estimated in 9 microscopic fields at 400× magnification per whole-slide image with ImageJ software (National Institutes of Health). Additionally, the relationship between MRI features, molecular, states and the positive CD68 and CD163 expression was analyzed. Our study discovered that the mean or median values of CD68+ and CD163+ TAMs were 7.39% and 14.98%, respectively. There was an obvious correlation between CD163+ TAMs and CD68+ TAMs (r=0.497; P=0.000). CD68+ and CD163+ macrophage infiltration correlated with age at diagnosis in patients with Gb (CD68+: r=0.230, P=0.006; CD163+: r=0.172, P=0.042). The levels of Gb TAM infiltration in different tumor locations varied, with the temporal lobe having the highest CD163+ macrophage and CD68+ macrophage infiltration (18.58% and 9.46%, respectively). CD163+ macrophage infiltration was positively correlated with ADCmean (r=0.208; P=0.014). The infiltration of CD68+ macrophages differed significantly between groups with varying degrees of tumor enhancement (H =4.228; P=0.017). There was a significant difference in CD68+ TAMs and CD163+ TAMs between the wild-type and mutant-type telomerase reverse transcriptase (TERT) types (P=0.004 and P=0.031, respectively). Age, location of the tumor, degree of tumor enhancement, ADC value, and TERT mutation status were associated with macrophage infiltration. These findings may serve as an effective tool for characterizing the tumor microenvironment in patients with Gb.

Temporal muscle thickness has no prognostic relevance in patients with high-grade glioma compared to functional scales.

GBM research is constantly assessing potential valuable prognostic biomarkers to better understand the disease and prognosticate future outcomes. Measuring temporal muscle thickness (TMT) has appeared to be a promising new surrogate marker for skeletal muscle mass and sarcopenia, which further indicates frailty and predicts overall survival (OS). The aim of this study was to determine its usefulness as a prognostic marker in patients with high-grade glioma compared to functional status scales. TMT was measured in preoperative axial T1-weighted contrast-enhanced magnetic resonance images in 277 patients who received surgical treatment of newly diagnosed WHO III and IV gliomas in our institution between 2015 and 2020. Clinical Frailty Scale (CFS) and Karnofsky Performance Scale (KPS) were assessed preoperatively and during a follow-up visit. Female gender has shown significant correlation with TMT, while TMT did not correlate with preoperative and follow-up functional scores, age, WHO classification, IDH mutation, MGMT promoter methylation, EGFR and ATRX expression, or 1p/19q co-deletion. No significant prognostic value of TMT could be shown in 6, 12, and 24 months OS, while changes in CFS and KPS proved to have a significant impact. Only female gender, but no other clinical, histological, or molecular marker showed any interrelation with TMT. Functional scores outclass measuring TMT as a reliable prognostic factor for predicting OS in patients with high-grade glioma.

Development and validation of a machine learning algorithm for predicting diffuse midline glioma, H3 K27-altered, H3 K27 wild-type high-grade glioma, and primary CNS lymphoma of the brain midline in adults.

Preoperative diagnosis of diffuse midline glioma, H3 K27-altered (DMG-A) and midline high-grade glioma without H3 K27 alteration (DMG-W), as well as midline primary CNS lymphoma (PCNSL) in adults, is challenging but crucial. The aim of this study was to develop a model for predicting these three entities using machine learning (ML) algorithms. Thirty-three patients with DMG-A, 35 with DMG-W, and 35 with midline PCNSL were retrospectively enrolled in the study. Radiomics features were extracted from contrast-enhanced T1-weighted MR images. Two radiologists evaluated the conventional MRI features of the tumors, such as shape. Patient age, tumor volume, and conventional MRI features were considered clinical features. The data set was randomly stratified into 70% training and 30% testing cohorts. Predictive models based on the clinical features, radiomics features, and integration of clinical and radiomics features were established through ML. The performances of the models were evaluated by calculating the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. Subsequently, 10 patients with DMG-A, 10 with DMG-W, and 12 with PCNSL were enrolled from another institution to validate the established models. The predictive models based on clinical features, radiomics features, and the integration of clinical and radiomics features through the support vector machine algorithm had the optimal accuracies in the training, testing, and validation cohorts, and the accuracies in the testing cohort were 0.871, 0.892, and 0.903, respectively. Age, 2 radiomics features, and 3 conventional MRI features were the 6 most significant features in the established integrated model. The integrated prediction model established by ML provides high discriminatory accuracy for predicting DMG-A, DMG-W, and midline PCNSL in adults.

Automated Radiomic Analysis of Vestibular Schwannomas and Inner Ears Using Contrast-Enhanced T1-Weighted and T2-Weighted Magnetic Resonance Imaging Sequences and Artificial Intelligence.

To objectively evaluate vestibular schwannomas (VSs) and their spatial relationships with the ipsilateral inner ear (IE) in magnetic resonance imaging (MRI) using deep learning. Cross-sectional study. A total of 490 adults with VS, high-resolution MRI scans, and no previous neurotologic surgery. MRI studies of VS patients were split into training (390 patients) and test (100 patients) sets. A three-dimensional convolutional neural network model was trained to segment VS and IE structures using contrast-enhanced T1-weighted and T2-weighted sequences, respectively. Manual segmentations were used as ground truths. Model performance was evaluated on the test set and on an external set of 100 VS patients from a public data set (Vestibular-Schwannoma-SEG). Dice score, relative volume error, average symmetric surface distance, 95th-percentile Hausdorff distance, and centroid locations. Dice scores for VS and IE volume segmentations were 0.91 and 0.90, respectively. On the public data set, the model segmented VS tumors with a Dice score of 0.89 ± 0.06 (mean ± standard deviation), relative volume error of 9.8 ± 9.6%, average symmetric surface distance of 0.31 ± 0.22 mm, and 95th-percentile Hausdorff distance of 1.26 ± 0.76 mm. Predicted VS segmentations overlapped with ground truth segmentations in all test subjects. Mean errors of predicted VS volume, VS centroid location, and IE centroid location were 0.05 cm 3 , 0.52 mm, and 0.85 mm, respectively. A deep learning system can segment VS and IE structures in high-resolution MRI scans with excellent accuracy. This technology offers promise to improve the clinical workflow for assessing VS radiomics and enhance the management of VS patients.

A radiomics model enables prediction venous sinus invasion in meningioma.

Preoperative prediction of meningioma venous sinus invasion would facilitate the selection of surgical approaches and predicting the prognosis. To predict venous sinus invasion in meningiomas, we used radiomic signatures to construct a model based on preoperative contrast-enhanced T1-weighted (T1C) and T2-weighted (T2) magnetic resonance imaging. In total, 599 patients with pathologically confirmed meningioma were retrospectively enrolled. For each patient enrolled in this study, 1595 radiomic signatures were extracted from T1C and T2 image sequences. Pearson correlation analysis and recursive feature elimination were used to select the most relevant signatures extracted from different image sequences, and logistic regression algorithms were used to build a radiomic model for risk prediction of meningioma sinus invasion. Furthermore, a nomogram was built by incorporating clinical characteristics and radiomic signatures, and a decision curve analysis was used to evaluate the clinical utility of the nomogram. Twenty radiomic signatures that were significantly related to venous sinus invasion were screened from 3190 radiomic signatures. Venous sinus invasion was associated with tumor position, and the clinicoradiomic model that incorporated the above characteristics (20 radiomic signatures and tumor position) had the best discriminating ability. The areas under the curve for the training and validation cohorts were 0.857 (95% confidence interval [CI], 0.824-0.890) and 0.824 (95% CI, 0.752-0.8976), respectively. The clinicoradiomic model had good predictive performance for venous sinus invasion in meningioma, which can aid in devising surgical strategies and predicting prognosis.

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.

Evaluation of Arachnoid Granulations in Cranial Dural Sinuses with Contrast-Enhanced 3-Dimensional T1-Weighted Magnetic Resonance Imaging.

Several studies in the literature have used contrast-enhanced magnetic resonance imaging to investigate arachnoid granulations protruding into the cranial dural sinuses. The current study aimed to investigate the protrusion of arachnoid granulations into the superior sagittal sinus, transverse sinus, straight sinus, and confluence of sinuses and determine the frequency of brain herniation into giant arachnoid granulations using contrast-enhanced 3-dimensional T1-weighted magnetic resonance imaging. Images of 550 patients with intra-sinus arachnoid granulations who underwent contrast-enhanced 3-dimensional T1-weighted thin-slice magnetic resonance imaging were retrospectively re-evaluated. Only 300 patients with at least 1 intra-sinus arachnoid granulation were included in the study. The protrusion of arachnoid granulations into superior sagittal sinus, transverse sinus, straight sinus, and confluence of sinuses was investigated. In addition, large arachnoid granulations and brain herniations into arachnoid granulations were also noted. A total of 889 focal filling defects of arachnoid granulations, at least 1 in the dural sinus, were detected. Of the filling defects of arachnoid granulations, 183 were in the right transverse sinus, 222 in the left transverse sinus, 265 in superior sagittal sinus, 185 in straight sinus, and 34 in confluence of sinuses. Brain herniation into arachnoid granulations was detected in 8 (2.7%) of the patients included in the study. All the filling defects detected in the dural sinuses on post-contrast 3-dimensional T1-weighted images were isointense with cerebrospinal fluid and had round, oval, or lobulated contours. A positive weak correla- tion was found between patient age and the size and number of arachnoid granulations (r = 0.181, P < .01 and r=0.207, P < .001, respectively). It was observed that the size and number of arachnoid granulations increased as the age of the patients increased. The distribution, shape, number, and size of intra-sinus arachnoid granulations can vary considerably. Brain herniation into arachnoid granulation can also be seen. Three-dimensional cranial magnetic resonance imaging sequences can be safely used in the evaluation of arachnoid granulations.

Granulomatous inflammation mimicking a hematoma around the replaced ascending aorta in magnetic resonance imaging: a case report

BackgroundGranulomatous inflammation results from various causes including infections and allergic reactions. It can appear as high signal intensity in T2-weighted or contrast-enhanced T1-weighted magnetic resonance imaging (MRI). Here, we describe a case of granulomatous inflammation looking like a hematoma on an ascending aortic graft in MRI.Case presentationA 75-year-old female was undergoing assessment for chest pain. She had a history of hemi-arch replacement for aortic dissection 10 years earlier. The initial chest computed tomography and subsequent chest MRI were suggestive of a hematoma, implying a pseudoaneurysm of the thoracic aorta, which is associated with high mortality in reoperation. Through redo median sternotomy, severe adhesion was found in the retrosternal space. A sac in the pericardial space contained yellowish and pus-like material, confirming that there was no hematoma around the ascending aortic graft. The pathologic finding was chronic necrotizing granulomatous inflammation. Microbiological tests including polymerase chain reaction analysis were negative.ConclusionOur experience indicates that an MRI finding of a hematoma at the site long after cardiovascular surgery suggests that there may be granulomatous inflammation.

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.