Benchmarking GE-BOLD, SE-BOLD, and SS-SI-VASO sequences for depth-dependent separation of feedforward and feedback signals in high-field MRI

Recent advances in high-field fMRI have allowed differentiating feedforward and feedback information in the grey matter of the human brain. For continued progress in this endeavor, it is critical to understand how MRI data acquisition parameters impact the read-out of information from laminar response profiles. Here, we benchmarked three different MR-sequences at 7T - gradient-echo (GE), spin-echo (SE) and vascular space occupancy imaging (VASO) - in differentiating feedforward and feedback signals in human early visual cortex (V1). The experiment (N=4) consisted of two complementary tasks: a perception task that predominantly evokes feedforward signals and a working memory task that relies on feedback signals. In the perception task, participants saw flickering oriented gratings while detecting orthogonal color-changes. In the working memory task, participants memorized the precise orientation of a grating. We used multivariate pattern analysis to read out the perceived (feedforward) and memorized (feedback) grating orientation from neural signals across cortical depth. Analyses across all the MR-sequences revealed perception signals predominantly in the middle cortical compartment of area V1 and working memory signals in the deep compartment. Despite an overall consistency across sequences, SE-EPI was the only sequence where both feedforward and feedback information were differently pronounced across cortical depth in a statistically robust way. We therefore suggest that in the context of a typical cognitive neuroscience experiment as the one benchmarked here, SE-EPI may provide a favorable trade-off between spatial specificity and signal sensitivity.

Usefulness of arterial spin labeling perfusion as an initial evaluation of status epilepticus

This study aimed to evaluate the sensitivity and prognostic value of arterial spin labeling (ASL) in a large group of status epilepticus (SE) patients and compare them with those of other magnetic resonance (MR) sequences, including dynamic susceptibility contrast (DSC) perfusion imaging. We retrospectively collected data of patients with SE in a tertiary center between September 2016 and March 2020. MR images were visually assessed, and the sensitivity for the detection of SE and prognostication was compared among multi-delay ASL, DSC, fluid-attenuated inversion recovery (FLAIR), and diffusion-weighted imaging (DWI). We included 51 SE patients and 46 patients with self-limiting seizures for comparison. Relevant changes in ASL were observed in 90.2% (46/51) of SE patients, a percentage higher than those for DSC, FLAIR, and DWI. ASL was the most sensitive method for initial differentiation between SE and self-limiting seizures. The sensitivity of ASL for detecting refractory SE (89.5%) or estimating poor outcomes (100%) was higher than those of other MR protocols or electroencephalography and comparable to those of clinical prognostic scores, although the specificity of ASL was very low as 9.4% and 15.6%, respectively. ASL showed a better ability to detect SE and predict the prognosis than other MR sequences, therefore it can be valuable for the initial evaluation of patients with SE.

A Multiparametric MR-Based RadioFusionOmics Model with Robust Capabilities of Differentiating Glioblastoma Multiforme from Solitary Brain Metastasis

This study aimed to evaluate the diagnostic potential of a novel RFO model in differentiating GBM and SBM with multiparametric MR sequences collected from 244 (131 GBM and 113 SBM) patients. Three basic volume of interests (VOIs) were delineated on the conventional axial MR images (T1WI, T2WI, T2_FLAIR, and CE_T1WI), including volumetric non-enhanced tumor (nET), enhanced tumor (ET), and peritumoral edema (pTE). Using the RFO model, radiomics features extracted from different multiparametric MRI sequence(s) and VOI(s) were fused and the best sequence and VOI, or possible combinations, were determined. A multi-disciplinary team (MDT)-like fusion was performed to integrate predictions from the high-performing models for the final discrimination of GBM vs. SBM. Image features extracted from the volumetric ET (VOIET) had dominant predictive performances over features from other VOI combinations. Fusion of VOIET features from the T1WI and T2_FLAIR sequences via the RFO model achieved a discrimination accuracy of AUC = 0.925, accuracy = 0.855, sensitivity = 0.856, and specificity = 0.853, on the independent testing cohort 1, and AUC = 0.859, accuracy = 0.836, sensitivity = 0.708, and specificity = 0.919 on the independent testing cohort 2, which significantly outperformed three experienced radiologists (p = 0.03, 0.01, 0.02, and 0.01, and p = 0.02, 0.01, 0.45, and 0.02, respectively) and the MDT-decision result of three experienced experts (p = 0.03, 0.02, 0.03, and 0.02, and p = 0.03, 0.02, 0.44, and 0.03, respectively).

Differentiation of paediatric posterior fossa tumours by the multiregional and multiparametric MRI radiomics approach: A study on the selection of optimal multiple sequences and multiregions

Objective: To evaluate the diagnostic performance of a radiomics model based on multiregional and multiparametric magnetic resonance imaging (MRI) to classify paediatric posterior fossa tumours (PPFTs), explore the contribution of different MR sequences and tumour subregions in tumour classification, and examine whether contrast-enhanced T1-weighted (T1C) images have irreplaceable added value. Methods: This retrospective study of 136 PPFTs extracted 11,958 multiregional (enhanced, non-enhanced, and total tumour) features from multiparametric MRI (T1- and T2-weighted, T1C, fluid-attenuated inversion recovery, and diffusion-weighted images). These features were subjected to fast correlation-based feature selection and classified by a support vector machine based on different tasks. Diagnostic performances of multiregional and multiparametric MRI features, different sequences, and different tumoral regions were evaluated using multiclass and one-versus-rest strategies. Results: The established model achieved an overall area under the curve (AUC) of 0.977 in the validation cohort. The performance of PPFTs significantly improved after replacing T1C with apparent diffusion coefficient maps added into the plain scan sequences (AUC from 0.812 to 0.917). When oedema features were added to contrast-enhancing tumour volume, the performance did not significantly improve. Conclusion: The radiomics model built by multiregional and multiparametric MRI features allows for the excellent distinction of different PPFTs and provides valuable references for the rational adoption of MR sequences. Advances in knowledge: This study emphasized that T1C has limited added value in predicting PPFTs and should be cautiously adopted. Selecting optimal MR sequences may help guide clinicians to better allocate acquisition sequences and reduce medical costs.

Multispectral co-occurrence of wavelet coefficients for malignancy assessment of brain tumors

Brain tumor is not most common, but truculent type of cancer. Therefore, correct prediction of its aggressiveness nature at an early stage would influence the treatment strategy. Although several diagnostic methods based on different modalities exist, a pre-operative method for determining tumor malignancy state still remains as an active research area. In this regard, the paper presents a new method for the assessment of tumor grades using conventional MR sequences namely, T1, T1 with contrast enhancement, T2 and FLAIR. The proposed method for tumor gradation is mainly based on feature extraction using multiresolution image analysis and classification using support vector machine. Since the wavelet features of different tumor subregions, obtained from single MR sequence, do not carry equally important information, a wavelet fusion technique is proposed based on the texture information content of each voxel. The concept of texture gradient, used in the proposed algorithm, fuses the wavelet coefficients of the given MR sequences. The feature vector is then derived from the co-occurrence of fused wavelet coefficients. As each wavelet subband contains distinct detail information, a novel concept of multispectral co-occurrence of wavelet coefficients is introduced to capture the spatial correlation among different subbands. It enables to convey more informative features to characterize the tumor type. The effectiveness of the proposed method is analyzed, with respect to six classification performance indices, on BRATS 2012 and BRATS 2014 data sets. The classification accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve assessed by the ten-fold cross-validation are 91.3%, 96.8%, 66.7%, 92.4%, 88.4%, and 92.0%, respectively, on real brain MR data.

Improved risk stratification via integration of radiomics and dosiomics features in patients with recurrent high-grade glioma undergoing carbon ion radiotherapy (CIRT).

2043 Background: Unique radiobiological and physical properties of carbon ion radiotherapy (CIRT) may be favorably utilized to improve outcome in recurrent High-Grade Glioma (rHGG). There are currently no standardized criteria for stratification of rHGG patients for re-irradiation (re-RT). This study evaluated the impact of morphological data (radiomics) and physical information (dosiomics) in stratifying rHGG patients for CIRT. Methods: Quantitative radiomics and dosiomics features were extracted from CIRT planning CTs with dose distribution (DD) and multiparametric MRIs (mpMRI, pre re-RT) of 141 patients (recurrent grade III: n=56 40%, grade IV: n=85 60%) treated with a median dose of 42 Gy (RBE) and a median fraction of 13. The MR sequences considered are T1 weighted pre-and post-contrast agent, fluid-attenuated inversion recovery (FLAIR) and apparent diffusion coefficient (ADC). Benefit of a re-RT risk score (RRRS), comprising the initial tumour grade, age and the Karnofsky Performance Score was shown to correlate with superior outcome in CIRT and conventional re-RT and was also studied here in parallel. Feature sets - a) RRRS, b) radiomics, c) dosiomics features - were evaluated both separately and combined. Multiple feature selection methods were used independently on the CT, DD and the MR sequences, followed by a stepwise Cox's Proportional Hazard model selection per modality or combination thereof. Multivariable models were ranked by 10-fold cross-validated concordance index (C-I). Results: Compared to the RRRS model (OS/PFS, C-I: 0.68/0.61), the multimodality model considering radiomics and dosiomics features (RD) allowed improved prognostic separation (OS/PFS, C-I: 0.77/0.70). The RD signature consisted of 12 and 10 textural features for the OS and PFS models. Combining the RD model with RRRS yielded the best performance (OS/PFS, C-I: 0.78/0.73). No significant correlation between the textural features and the prescribed dose, tumor grade and volume was found, with the Spearman's correlation coefficient ranging between -0.06 to 0.17. Conclusions: Integrating multimodal information outperforms unimodal prognostic separation of rHGG following CIRT, highlighting the importance to consider biological, physical and morphological data for patient stratification. Prospective validation studies of this multimodal stratifier is warranted.[Table: see text]

Multiparametric MRI-based radiomics analysis: differentiation of subtypes of cervical cancer in the early stage

Background There are significant differences in outcomes for different histological subtypes of cervical cancer (CC). Yet, it is difficult to distinguish CC subtypes using non-invasive methods. Purpose To investigate whether multiparametric magnetic resonance imaging (MRI)-based radiomics analysis can differentiate CC subtypes and explore tumor heterogeneity. Material and Methods This study retrospectively analyzed 96 patients with CC (squamous cell carcinoma [SCC] = 50, adenocarcinoma [AC] = 46) who underwent pelvic MRI before surgery. Radiomics features were extracted from the tumor volumes on five sequences (sagittal T2-weighted imaging [T2SAG], transverse T2-weighted imaging [T2TRA], sagittal contrast-enhanced T1-weighted imaging [CESAG], transverse contrast-enhanced T1-weighted imaging [CETRA], and apparent diffusion coefficient [ADC]). Clustering and logistic regression were used to examine the distinguishing capabilities of radiomics features extracted from five different MR sequences. Results Among the 105 extracted radiomics features, there were 51, 38, 37, and 2 features that showed intergroup differences for T2SAG, T2TRA, ADC, and CESAG, respectively (all P < 0.05). AC had greater textural heterogeneity than SCC ( P < 0.05). Upon unsupervised clustering of significantly different features, T2SAG achieved the highest accuracy (0.844; sensitivity = 0.920; specificity = 0.761). The largest area under the curve (AUC) for classification ability was 0.86 for T2SAG. Hence, the radiomics model from five combined MR sequences (AUC = 0.89; accuracy = 0.81; sensitivity = 0.67; specificity = 0.94) exhibited better differentiation ability than any MR sequence alone. Conclusion Multiparametric MRI-based radiomics models may be a promising method to differentiate AC and SCC. AC showed more heterogeneous features than SCC.

MRI-Based Radiomics Models for Predicting Risk Classification of Gastrointestinal Stromal Tumors

BackgroundWe conduct a study in developing and validating four MRI-based radiomics models to preoperatively predict the risk classification of gastrointestinal stromal tumors (GISTs).MethodsForty-one patients (low-risk = 17, intermediate-risk = 13, high-risk = 11) underwent MRI before surgery between September 2013 and March 2019 in this retrospective study. The Kruskal–Wallis test with Bonferonni correction and variance threshold was used to select appropriate features, and the Random Forest model (three classification model) was used to select features among the high-risk, intermediate-risk, and low-risk of GISTs. The predictive performance of the models built by the Random Forest was estimated by a 5-fold cross validation (5FCV). Their performance was estimated using the receiver operating characteristic (ROC) curve, summarized as the area under the ROC curve (AUC). Area under the curve (AUC), accuracy, sensitivity, and specificity for risk classification were reported. Linear discriminant analysis (LDA) was used to assess the discriminative ability of these radiomics models.ResultsThe high-risk, intermediate-risk, and low-risk of GISTs were well classified by radiomics models, the micro-average of ROC curves was 0.85, 0.81, 0.87 and 0.94 for T1WI, T2WI, ADC and combined three MR sequences. And ROC curves achieved excellent AUCs for T1WI (0.85, 0.75 and 0.82), T2WI (0.69, 0.78 and 0.78), ADC (0.85, 0.77 and 0.80) and combined three MR sequences (0.96, 0.92, 0.81) for the diagnosis of high-risk, intermediate-risk, and low-risk of GISTs, respectively. In addition, LDA demonstrated the different risk of GISTs were correctly classified by radiomics analysis (61.0% for T1WI, 70.7% for T2WI, 83.3% for ADC, and 78.9% for the combined three MR sequences).ConclusionsRadiomics models based on a single sequence and combined three MR sequences can be a noninvasive method to evaluate the risk classification of GISTs, which may help the treatment of GISTs patients in the future.