Search

Background: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. Methods: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. Results: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ² test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. Conclusions: Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task. [ABSTRACT FROM AUTHOR]

Glioma, the most prevalent type of brain tumor, is categorized into low-grade gliomas (LGGs) and high-grade gliomas (HGGs). Accurate differentiation between these categories is crucial for selecting the appropriate therapeutic approach. Magnetic resonance imaging (MRI) technology offers a noninvasive and rapid diagnostic method for visual interpretation by clinicians. Machine learning plays a pivotal role in intelligently analyzing multiple MRI images, enhancing diagnostic efficiency, and providing an objective diagnosis. Radiomics and deep learning (DL) techniques contribute distinctively to glioma grading by extracting pertinent features from various MRI images. This study aimed to assess the efficacy of fusing radiomic and DL features from multiple MRI images to distinguish between LGGs and HGGs. Image data from four MRI scanning sequences including T1-weighted, postcontrast T1-weighted, T2-weighted, and T2 fluid-attenuated inversion recovery images were collected from various institutions with different instrumental magnetic field strengths. The radiomic features from each MRI sequence were used to construct respective single-sequence radiomic models, while the slice images from each MRI sequence were used to construct corresponding single-sequence DL models. A radiomic fusion model was created by amalgamating signatures from the four single-sequence radiomic models, and a DL fusion model was constructed by integrating information from all four MRI sequences. The radiomic and DL (RDL) model was constructed using two fusion signatures generated by the radiomic and DL fusion models, respectively. The RDL model demonstrated excellent diagnostic performance, achieving an area under the curve (AUC) of 0.959 on a testing cohort with the radiomic fusion signature proving pivotal in differentiating LGGs from HGGs. The RDL model exhibited superior generalization performance compared to the radiomic or DL models constructed solely based on MRI sequences. The results confirmed the feasibility and effectiveness of combining radiomic and DL features through fusion signatures, thereby highlighting the potential of integrating radiomic and DL fusion signatures to enhance preoperative glioma grading performance. [ABSTRACT FROM AUTHOR]

Abstract Background Glioma grading is a critical procedure for selecting the most effective treatment policy. Biopsy result is the gold standard method for glioma grading, but inherent sampling errors in the biopsy procedure could lead to tumor misclassification. Aim This study evaluated grading performances of a more comprehensive collection of the physiological indices quantified using an optimized dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) paradigm for glioma grading. Methods Thirty-five patients with glioma underwent DCE-MR imaging to evaluate the grading performances of DCE-MRI-derived physiological indices. The statistical differences in the physiological indices between the different grades of gliomas were studied, and the grading performances of these parameters were evaluated using the leave-one-out cross-validation method. Results There were significant statistical differences in DCE-MRI-derived physiological indices between the different grades of gliomas. The mean rCBVs for grade II (low-grade glioma, LGG), grade III, grade IV, and high-grade (HGG) gliomas were 2.03 ± 0.78, 3.61 ± 1.64, 7.14 ± 3.19, and 5.28 ± 3.02, respectively. The mean rCBFs of 1.94 ± 0.97, 2.67 ± 0.96, 4.57 ± 1.77, and 3.57 ± 1.68 were, respectively, quantified for grade II (LGG), grade III, grade IV, and high-grade gliomas. The leave-one-out cross-validation method indicates that the grades of glioma tumors could be determined based on a specific threshold for each physiological index; for example, the optimal cutoff values for rCBF, rCBV, Ktrans, Kep, and Vp indices to distinguish between HGGs and LGGs were 2.11, 2.80, 0.025 mL/g min, 0.29 min−1, and 0.065 mL/g, respectively. Conclusions From the results, it could be concluded that glioma grades could be determined using DCE-MRI-derived physiological indices with an acceptable agreement with histopathological results.

Background: Glioma grading is a critical procedure for selecting the most effective treatment policy. Biopsy result is the gold standard method for glioma grading, but inherent sampling errors in the biopsy procedure could lead to tumor misclassification. Aim: This study evaluated grading performances of a more comprehensive collection of the physiological indices quantified using an optimized dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) paradigm for glioma grading. Methods: Thirty-five patients with glioma underwent DCE-MR imaging to evaluate the grading performances of DCE-MRI-derived physiological indices. The statistical differences in the physiological indices between the different grades of gliomas were studied, and the grading performances of these parameters were evaluated using the leave-one-out cross-validation method. Results: There were significant statistical differences in DCE-MRI-derived physiological indices between the different grades of gliomas. The mean rCBVs for grade II (low-grade glioma, LGG), grade III, grade IV, and high-grade (HGG) gliomas were 2.03 ± 0.78, 3.61 ± 1.64, 7.14 ± 3.19, and 5.28 ± 3.02, respectively. The mean rCBFs of 1.94 ± 0.97, 2.67 ± 0.96, 4.57 ± 1.77, and 3.57 ± 1.68 were, respectively, quantified for grade II (LGG), grade III, grade IV, and high-grade gliomas. The leave-one-out cross-validation method indicates that the grades of glioma tumors could be determined based on a specific threshold for each physiological index; for example, the optimal cutoff values for rCBF, rCBV, Ktrans, Kep, and Vp indices to distinguish between HGGs and LGGs were 2.11, 2.80, 0.025 mL/g min, 0.29 min−1, and 0.065 mL/g, respectively. Conclusions: From the results, it could be concluded that glioma grades could be determined using DCE-MRI-derived physiological indices with an acceptable agreement with histopathological results. [ABSTRACT FROM AUTHOR]

Gliomas are the most common type of cerebral tumors; they occur with increasing incidence in the last decade and have a high rate of mortality. For efficient treatment, fast accurate diagnostic and grading of tumors are imperative. Presently, the grading of tumors is established by histopathological evaluation, which is a time-consuming procedure and relies on the pathologists’ experience. Here we propose a supervised machine learning procedure for tumor grading which uses quantitative phase images of unstained tissue samples acquired by digital holographic microscopy. The algorithm is using an extensive set of statistical and texture parameters computed from these images. The procedure has been able to classify six classes of images (normal tissue and five glioma subtypes) and to distinguish between gliomas types from grades II to IV (with the highest sensitivity and specificity for grade II astrocytoma and grade III oligodendroglioma and very good scores in recognizing grade III anaplastic astrocytoma and grade IV glioblastoma). The procedure bolsters clinical diagnostic accuracy, offering a swift and reliable means of tumor characterization and grading, ultimately the enhancing treatment decision-making process.

Objective To explore the effect of magnetic resonance imaging （MRI） and contrast enhanced ultrasound （CEUS） in the grading diagnosis of glioma. MethodsA retrospective analysis was performed on the patients without glioma （control group, n=94） and with glioma （observation group, n=96） treated in No. 215 Hospital of Shaanxi Nuclear Industry from April 2017 to April 2022. All patients received CEUS and MRI examinations before surgery. Time to peak （TTP）, mean transit time （mTT）, pure water diffusion coefficient （D）, perfusion fraction （f） and quantitative indicators were compared between two groups. During six months after operation, 29 cases of residual tumor were found by histopathology examination. ResultsIn observation group, TTP, D, f were statistically higher than those in control group, mTT was lower than that in control group （P ＜ 0.05）. Compared with those in the patients with low-grade tumor, TTP, D and f increased significantly, and mTT decreased in the patients with high-grade tumor （P ＜ 0.05）. ROC curve analysis showed that the AUCs of TTP, mTT, D, f and joint prediction for glioma grading were 0.849, 0.839, 0.914, 0.893 and 0.971, respectively. ConclusionCEUS combined with MRI has a higher efficiency in predicting the grade of glioma and postoperative residual tumors, which can provide a scientific basis for prognosis evaluation.

Background: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. Methods: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. Results: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. Conclusions: Our findings confirm that present radiomics’ diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

Deep networks have shown strong performance in glioma grading; however, interpreting their decisions remains challenging due to glioma heterogeneity. To address these challenges, the proposed solution is the Causal Segmentation Framework (CSF). This framework aims to accurately predict high- and low-grade gliomas while simultaneously highlighting key subregions. Our framework utilizes a shrinkage segmentation method to identify subregions containing essential decision information. Moreover, we introduce a glioma grading module that combines deep learning and traditional approaches for precise grading. Our proposed model achieves the best performance among all models, with an AUC of 96.14%, an F1 score of 93.74%, an accuracy of 91.04%, a sensitivity of 91.83%, and a specificity of 88.88%. Additionally, our model exhibits efficient resource utilization, completing predictions within 2.31s and occupying only 0.12 GB of memory during the test phase. Furthermore, our approach provides clear and specific visualizations of key subregions, surpassing other methods in terms of interpretability. In conclusion, the Causal Segmentation Framework (CSF) demonstrates its effectiveness at accurately predicting glioma grades and identifying key subregions. The inclusion of causality in the CSF model enhances the reliability and accuracy of preoperative decision-making for gliomas. The interpretable results provided by the CSF model can assist clinicians in their assessment and treatment planning. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) image analyses are frequently applied to perform classification tasks. Herein, 3D-based machine learning systems are generally used/generated by examining two designs: a 3D-based deep learning model or a 3D-based task-specific framework. However, except for a new approach named 3t2FTS, a promising feature transform operating from 3D to two-dimensional (2D) space has not been efficiently investigated for classification applications in 3D magnetic resonance imaging (3D MRI). In other words, a state-of-the-art feature transform strategy is not available that achieves high accuracy and provides the adaptation of 2D-based deep learning models for 3D MRI-based classification. With this aim, this paper presents a new version of the 3t2FTS approach (3t2FTS-v2) to apply a transfer learning model for tumor categorization of 3D MRI data. For performance evaluation, the BraTS 2017/2018 dataset is handled that involves high-grade glioma (HGG) and low-grade glioma (LGG) samples in four different sequences/phases. 3t2FTS-v2 is proposed to effectively transform the features from 3D to 2D space by using two textural features: first-order statistics (FOS) and gray level run length matrix (GLRLM). In 3t2FTS-v2, normalization analyses are assessed to be different from 3t2FTS to accurately transform the space information apart from the usage of GLRLM features. The ResNet50 architecture is preferred to fulfill the HGG/LGG classification due to its remarkable performance in tumor grading. As a result, for the classification of 3D data, the proposed model achieves a 99.64% accuracy by guiding the literature about the importance of 3t2FTS-v2 that can be utilized not only for tumor grading but also for whole brain tissue-based disease classification. [ABSTRACT FROM AUTHOR]

To evaluate the diagnostic performance of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) metrics for glioma grading on a point-to-point basis. Forty patients with treatment-naïve glioma underwent DCE-MR examination and stereotactic biopsy. DCE-derived parameters including endothelial transfer constant (K trans ), volume of extravascular-extracellular space (v e), fractional plasma volume (f p v), and reflux transfer rate (k ep) were measured within ROIs on DCE maps accurately matched with biopsies used for histologic grades diagnosis. Differences in parameters between grades were evaluated by Kruskal-Wallis tests. Diagnostic accuracy of each parameter and their combination was assessed using receiver operating characteristic curve. Eighty-four independent biopsy samples from 40 patients were analyzed in our study. Significant statistical differences in K trans and v e were observed between grades except v e between grade 2 and 3. K trans showed good to excellent accuracy in discriminating grade 2 from 3, 3 from 4, and 2 from 4 (area under the curve = 0.802, 0.801 and 0.971, respectively). V e indicated good accuracy in discriminating grade 3 from 4 and 2 from 4 (AUC = 0.874 and 0.899, respectively). The combined parameter demonstrated fair to excellent accuracy in discriminating grade 2 from 3, 3 from 4, and 2 from 4 (AUC = 0.794, 0.899 and 0.982, respectively). Our study had identified K trans , v e and the combination of parameters to be an accurate predictor for grading glioma. [ABSTRACT FROM AUTHOR]

Glioma grading is critical in treatment planning and prognosis. This study aims to address this issue through MRI-based classification to develop an accurate model for glioma diagnosis. Here, we employed a deep learning pipeline with three essential steps: (1) MRI images were segmented using preprocessing approaches and UNet architecture, (2) brain tumor regions were extracted using segmentation, then (3) high-grade gliomas and low-grade gliomas were classified using the VGG and GoogleNet implementations. Among the additional preprocessing techniques used in conjunction with the segmentation task, the combination of data augmentation and Window Setting Optimization was found to be the most effective tool, resulting in the Dice coefficient of 0.82, 0.91, and 0.72 for enhancing tumor, whole tumor, and tumor core, respectively. While most of the proposed models achieve comparable accuracies of about 93 % on the testing dataset, the pipeline of VGG combined with UNet segmentation obtains the highest accuracy of 97.44 %. In conclusion, the presented architecture illustrates a realistic model for detecting gliomas; moreover, it emphasizes the significance of data augmentation and segmentation in improving model performance.

• In the SWE mode, the diagnostic threshold of HGG and LGG is 13.05 kPa. • In the SMI mode, the vascular architectures of the tumor tissue and peritumoral tissues of HGG and LGG were significantly different (P < 0.05). • SWE and SMI are beneficial for the differentiation of HGG and LGG and may help optimize clinical surgical procedures. To explore the diagnostic value and feasibility of shear wave elastography and superb microvascular imaging in the grading diagnosis of glioma intraoperatively. Forty-nine patients with glioma were included in this study. B-mode ultrasonography, Young's modulus in shear-wave elastography (SWE) and vascular architecture in superb microvascular imaging(SMI) of tumor tissue and peritumoral tissue were analyzed. Receiver operating characteristic(ROC) curve analysis was used to evaluate the diagnostic effect of SWE. Logistic regression model was used to calculate the prediction probability of HGG diagnosis. Compared with LGG, HGG was often characterized by peritumoral edema in B mode (P < 0.05). There was a significant difference in Young's modulus between HGG and LGG; the diagnostic threshold of HGG and LGG was 13.05 kPa, the sensitivity was 78.3%, and the specificity was 76.9%. The vascular architectures of the tumor tissue and peritumoral tissues of HGG and LGG were significantly different (P < 0.05). The vascular architectures of peritumoral tissue in HGG often characterized by distorted blood flow signals surrounding the tumor (14/26,53.8%); in the tumor tissue, HGG often presents as dilated and bent vessels(19/26,73.1%). The elasticity value of SWE and the tumor vascular architectures of SMI were correlated with the diagnosis of HGG. Intraoperative ultrasound (ioUS), especially SWE, and SMI are beneficial for the differentiation of HGG and LGG and may help optimize clinical surgical procedures. [ABSTRACT FROM AUTHOR]

Glioma grading is critical for treatment selection, and the fine classification between glioma grades II and III is still a pathological challenge. Traditional systems based on a single deep learning (DL) model can only show relatively low accuracy in distinguishing glioma grades II and III. Introducing ensemble DL models by combining DL and ensemble learning techniques, we achieved annotation-free glioma grading (grade II or III) from pathological images. We established multiple tile-level DL models using residual network ResNet-18 architecture and then used DL models as component classifiers to develop ensemble DL models to achieve patient-level glioma grading. Whole-slide images of 507 subjects with low-grade glioma (LGG) from the Cancer Genome Atlas (TCGA) were included. The 30 DL models exhibited an average area under the curve (AUC) of 0.7991 in patient-level glioma grading. Single DL models showed large variation, and the median between-model cosine similarity was 0.9524, significantly smaller than the threshold of 1.0. The ensemble model based on logistic regression (LR) methods with a 14-component DL classifier (LR-14) demonstrated a mean patient-level accuracy and AUC of 0.8011 and 0.8945, respectively. Our proposed LR-14 ensemble DL model achieved state-of-the-art performance in glioma grade II and III classifications based on unannotated pathological images.

Objective: Despite the critical role of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumours, there are still many pitfalls in the exact grading of them, in particular, gliomas. In this regard, it was aimed to examine the potential of Transfer Learning (TL) and Machine Learning (ML) algorithms in the accurate grading of gliomas on MRI images. Materials and methods: Dataset has included four types of axial MRI images of glioma brain tumours with grades I–IV: T1-weighted, T2-weighted, FLAIR, and T1-weighted Contrast-Enhanced (T1-CE). Images were resized, normalized, and randomly split into training, validation, and test sets. ImageNet pre-trained Convolutional Neural Networks (CNNs) were utilized for feature extraction and classification, using Adam and SGD optimizers. Logistic Regression (LR) and Support Vector Machine (SVM) methods were also implemented for classification instead of Fully Connected (FC) layers taking advantage of features extracted by each CNN. Results: Evaluation metrics were computed to find the model with the best performance, and the highest overall accuracy of 99.38% was achieved for the model containing an SVM classifier and features extracted by pre-trained VGG-16. Discussion: It was demonstrated that developing Computer-aided Diagnosis (CAD) systems using pre-trained CNNs and classification algorithms is a functional approach to automatically specify the grade of glioma brain tumours in MRI images. Using these models is an excellent alternative to invasive methods and helps doctors diagnose more accurately before treatment. [ABSTRACT FROM AUTHOR]

Purpose: Gliomas are the most commonly occurring brain tumour in adults and there remains no cure for these tumours with treatment strategies being based on tumour grade. All treatment options aim to prolong survival, maintain quality of life and slow the inevitable progression from low-grade to high-grade. Despite imaging advancements, the only reliable method to grade a glioma is to perform a biopsy, and even this is fraught with errors associated with under grading. Positron emission tomography (PET) imaging with amino acid tracers such as [18F]fluorodopa (18F-FDOPA), [11C]methionine (11C-MET), [18F]fluoroethyltyrosine (18F-FET), and 18F-FDOPA are being increasingly used in the diagnosis and management of gliomas. Methods: In this review we discuss the literature available on the ability of 18F-FDOPA-PET to distinguish low- from high-grade in newly diagnosed gliomas. Results: In 2016 the Response Assessment in Neuro-Oncology (RANO) and European Association for Neuro-Oncology (EANO) published recommendations on the clinical use of PET imaging in gliomas. However, since these recommendations there have been a number of studies performed looking at whether 18F-FDOPA-PET can identify areas of high-grade transformation before the typical radiological features of transformation such as contrast enhancement are visible on standard magnetic resonance imaging (MRI). Conclusion: Larger studies are needed to validate 18F-FDOPA-PET as a non-invasive marker of glioma grade and prediction of tumour molecular characteristics which could guide decisions surrounding surgical resection. [ABSTRACT FROM AUTHOR]

Background: The focus of neuro‐oncology research has changed from histopathologic grading to molecular characteristics, and medical imaging routinely follows this change. Purpose: To compare the diagnostic performance of amide proton transfer (APT) and four diffusion models in gliomas grading and isocitrate dehydrogenase (IDH) genotype. Study Type: Prospective. Population: A total of 62 participants (37 males, 25 females; mean age, 52 ± 13 years) whose IDH genotypes were mutant in 6 of 14 grade II gliomas, 8 of 20 of grade III gliomas, and 4 of 28 grade IV gliomas. Field Strength/Sequence: APT imaging using sampling perfection with application optimized contrasts by using different flip angle evolutions (SPACE) and DWI with q‐space Cartesian grid sampling were acquired at 3 T. Assessment: The ability of diffusion kurtosis imaging, diffusion kurtosis imaging, neurite orientation dispersion and density imaging (NODDI), mean apparent propagator (MAP), and APT imaging for glioma grade and IDH status were assessed, with histopathological grade and genetic testing used as a reference standard. Regions of interest (ROIs) were drawn by two neuroradiologists after consensus. Statistical Tests: T‐test and Mann–Whitney U test; one‐way analysis of variance (ANOVA); receiver operating curve (ROC) and area under the curve (AUC); DeLong test. P value < 0.05 was considered statistically significant. Results: Compared with IDH‐mutant gliomas, IDH‐wildtype gliomas showed a significantly higher mean, 5th‐percentile (APT5), and 95th‐percentile from APTw, the 95th‐percentile value of axial, mean, and radial diffusivity from DKI, and 95th‐percentile value of isotropic volume fraction from NODDI, and no significantly different parameters from DTI and MAP (P = 0.075–0.998). The combined APT model showed a significantly wider area under the curve (AUC 0.870) for IDH status, when compared with DKI and NODDI. APT5 was significantly different between two of the three groups (glioma II vs. glioma III vs. glioma IV: 1.35 ± 0.75 vs. 2.09 ± 0.93 vs. 2.71 ± 0.81). Data conclusion: APT has higher diagnostic accuracy than DTI, DKI, MAP, and NODDI in glioma IDH genotype. APT5 can effectively identify both tumor grading and IDH genotyping, making it a promising biomarker for glioma classification. Evidence Level: 1 Technical Efficacy: Stage 2 [ABSTRACT FROM AUTHOR]

Gliomas are the brain tumors in glial cells, which are categorized into four numerical grades, I-II-III-IV, to quantize the aggressiveness and severity of the tumors; while divided into two major groups, high-grade (HG) and low-grade (LG), in general. Among many differences between these groups, one of the most distinct and characteristic features could be seen in the shape of the tumor boundaries by magnetic resonance imaging (MRI). Due to aggressive nature of the HG tumors in proliferation phase, the boundaries of HG tumors become more shape-wise complex compared to the LG tumors, which could be differentiated by analyzing the fractal complexity of the cell membranes. However, the complexity cannot be either manually calculated or estimated by eye inspection without a reference point with one single image or sometimes even with an image set. Therefore, we present an automated glioma grading framework to provide an insight on the grades with a novel contouring and fractal dimension analysis system. The primary component of the proposed system is an automated Nakagami imaging module with a specialized fuzzy c-means algorithm to contour the boundaries of the whole tumors. The contoured images, afterwards, are analyzed by the Minkowski–Bouligand and Hausdorff methods for two panning options to generate the fractal dimensions and to estimate the fractal complexities for classifying the gliomas The results are greatly encouraging that the overall classification accuracy is computed as 88.31 % using the basic support vector machines (SVM) classifier; while as 91.96 % with the arbitrary thresholding appended. The outcomes of this paper with implementable mathematical infrastructure would be very useful and beneficial as an expert system in intelligent and automatic glioma grading, for researchers and medical experts. • We proposed a novel automated glioma-grading framework. • 2D FLAIR MRI images consisting of HG and LG gliomas are analyzed. • Raw images are highlighted by Nakagami module and contoured by fuzzy 2-means. • Fractal dimensions of the contoured images are analyzed by two methods. • Overall accuracy is computed as ACC=91.96 % with a SVM classifier. [ABSTRACT FROM AUTHOR]

Objective To explore the diagnostic values of different post-processing modes of dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) in the differentiation of glioma grade. Methods A total of 89 patients with glioma confirmed by postoperative pathology in our hospital from January 2013 to July 2019 were enrolled, including 29 patients of gradeⅡ, 24 of grade Ⅲ and 36 of grade Ⅳ. All patients underwent preoperative DCE-MRI examination, and corresponding parameters were collected and processed using post-processing software Tissue-4D and Omni-Kinetics (OK) respectively. One-way ANOVA was adopted to compare the differences of the obtained parameters among glioma of different grades. Spearman rank correlation analysis was performed to analyze the correlation between each parameter and glioma grade, and receiver operating characteristic (ROC) curve was used to evaluate the area under the curve (AUC) of each parameter. Results In hot spot analysis, the Ktrans values of both post-processing modes, as well as the iAUC value of Tissue-4D and the Vp value of OK were all significantly different among glioma of different grades (P < 0.05). The Kep value of grade Ⅳ glioma was obviously lower than that of grade Ⅱ glioma (P < 0.05), while the Ve values of grade Ⅳ and Ⅲ tumors were notably higher than that of gradeⅡ one (P < 0.05). The AUC value of Ktrans (Tissue-4D) was 0.949 in the differentiation of gradeⅡ from grade Ⅳ glioma (P < 0.01), indicating the highest diagnostic efficiency, and the correlation between Ktrans (OK) and glioma grade was the highest (r=0.775, P < 0.01). In the histogram analysis of OK, the 50th percentile of Ktrans value, the mean and the 75th and 90th percentiles of Ve value, the mean, entropy and the 50th percentile of Kep value, as well as the mean value of Vp showed significances in the differentiation of grade Ⅱ from grade Ⅲ and grade Ⅱ from grade Ⅳ glioma (P < 0.05). Moreover, the energy, entropy and 50th, 75th, 90th percentiles of Vp value, and the energy of Kep value were statistically different in the identification of grade Ⅳ from grade Ⅱ and grade Ⅳ from grade Ⅲ (P < 0.05). Conclusion The Ktrans and Ve values of the 2 post-processing modes have rather high diagnostic efficiency for glioma grading in the hotspot analysis, and the histogram analysis of OK software involves more abundant and comprehensive parameters.

Glioma grading during surgery can help clinical treatment planning and prognosis, but intraoperative pathological examination of frozen sections is limited by the long processing time and complex procedures. Near-infrared fluorescence imaging provides chances for fast and accurate real-time diagnosis. Recently, deep learning techniques have been actively explored for medical image analysis and disease diagnosis. However, issues of near-infrared fluorescence images, including small-scale, noise, and low-resolution, increase the difficulty of training a satisfying network. Multi-modal imaging can provide complementary information to boost model performance, but simultaneously designing a proper network and utilizing the information of multi-modal data is challenging. In this work, we propose a novel neural architecture search method DLS-DARTS to automatically search for network architectures to handle these issues. DLS-DARTS has two learnable stems for multi-modal low-level feature fusion and uses a modified perturbation-based derivation strategy to improve the performance on the area under the curve and accuracy. White light imaging and fluorescence imaging in the first near-infrared window (650-900 nm) and the second near-infrared window (1,000-1,700 nm) are applied to provide multi-modal information on glioma tissues. In the experiments on 1,115 surgical glioma specimens, DLS-DARTS achieved an area under the curve of 0.843 and an accuracy of 0.634, which outperformed manually designed convolutional neural networks including ResNet, PyramidNet, and EfficientNet, and a state-of-the-art neural architecture search method for multi-modal medical image classification. Our study demonstrates that DLS-DARTS has the potential to help neurosurgeons during surgery, showing high prospects in medical image analysis. [ABSTRACT FROM AUTHOR]

Introduction: Glioma grading is an important clinical procedure that determines the procedure of the patient's treatment. There is an increasing interest in other complementary techniques in addition to histo-pathological evaluation as the gold standard method. Perfusion indices have shown promising correlations with histo-pathological grades and neovascularization degrees in gliomas. In this study, the processing times and classification performances of cerebral blood flow (CBF) parameters calculated using singular value decomposition (SVD) and Fourier deconvolution methods were evaluated. Materials and Methods: The statistical differences between the CBF magnitudes of the high- and low-grade gliomas were evaluated for eighteen patients with pathologically proven gliomas (Low-grade gliomas, 5; High-grade gliomas, 13). The classification performances of the calculated indices were evaluated using the receiver operating curve analysis. Results: The deconvolution processing times for the SVD method were significantly higher than those of the Fourier deconvolution method (about ~9 times). There were statistically significant differences in both CBF indices between the high- and low-grade gliomas (P<0.05). In ROC curve analysis, CBF indices calculated by the SVD method had a higher area under the curve (about 8538.5 vs. 8153.8). Conclusion: Based on the study, the glioma grade might be determined using the Fourier-based CBF index with an almost similar grading efficiency and a much lower processing time than the CBF index calculated by the SVD method. [ABSTRACT FROM AUTHOR]

Deep networks have shown strong performance in glioma grading; however, interpreting their decisions remains challenging due to glioma heterogeneity. To address these challenges, the proposed solution is the Causal Segmentation Framework (CSF). This framework aims to accurately predict high- and low-grade gliomas while simultaneously highlighting key subregions. Our framework utilizes a shrinkage segmentation method to identify subregions containing essential decision information. Moreover, we introduce a glioma grading module that combines deep learning and traditional approaches for precise grading. Our proposed model achieves the best performance among all models, with an AUC of 96.14%, an F1 score of 93.74%, an accuracy of 91.04%, a sensitivity of 91.83%, and a specificity of 88.88%. Additionally, our model exhibits efficient resource utilization, completing predictions within 2.31s and occupying only 0.12 GB of memory during the test phase. Furthermore, our approach provides clear and specific visualizations of key subregions, surpassing other methods in terms of interpretability. In conclusion, the Causal Segmentation Framework (CSF) demonstrates its effectiveness at accurately predicting glioma grades and identifying key subregions. The inclusion of causality in the CSF model enhances the reliability and accuracy of preoperative decision-making for gliomas. The interpretable results provided by the CSF model can assist clinicians in their assessment and treatment planning.

Purpose: To evaluate the efficacy of three‐dimensional (3D) segmentation‐based radiomics analysis of multiparametric MRI combined with proton magnetic resonance spectroscopy (1H‐MRS) and diffusion tensor imaging (DTI) in glioma grading. Method: A total of 100 patients with histologically confirmed gliomas (grade II–IV) were examined using conventional MRI, 1H‐MRS, and DTI. Tumor segmentations of T1‐weighted imaging (T1WI), contrast‐enhanced T1WI (T1WI+C), T2‐weighted imaging (T2WI), apparent diffusion coefficient (ADC) mapping, and fractional anisotropy (FA) mapping were performed. In total, 396 radiomics features were extracted and reduced using basic tests and least absolute shrinkage and selection operator (LASSO) regression. The selected features of each sequence were combined, and logistic regression with ten‐fold cross‐validation was applied to develop the grading model. Sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were compared. The model developed from the training set was applied to the test set to measure accuracy. One optimal grading quantitative parameter was selected for each 1H‐MRS and DTI analysis. A radiomics nomogram model including radiomics signature, quantitative parameters, and clinical features was developed. Results: T1WI+C exhibited the highest grading efficacy among single sequences (AUC, 0.92; sensitivity, 0.89; specificity, 0.85), but the efficacy of the combined model was higher (AUC, 0.97; sensitivity, 0.94; specificity, 0.91). The AUCs of all models exhibited high accuracy, and no significant differences were observed in AUCs between the training and test sets. The visualized nomogram was developed based on the combined radiomics signature and choline (Cho)/N‐acetyl aspartate (NAA) from 1H‐MRS. Conclusion: Multiparametric MRI can be used to predict the pathological grading of high‐grade gliomas (HGGs) and low‐grade gliomas (LGGs) by combining radiomics features with quantitative parameters. The visualized nomogram may provide an intuitive assessment tool in clinical practice. Clinical trial registration: This trial was not registered, as it was a retrospective study and was approved by the local institutional review board. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) image analyses are frequently applied to perform classification tasks. Herein, 3D-based machine learning systems are generally used/generated by examining two designs: a 3D-based deep learning model or a 3D-based task-specific framework. However, except for a new approach named 3t2FTS, a promising feature transform operating from 3D to two-dimensional (2D) space has not been efficiently investigated for classification applications in 3D magnetic resonance imaging (3D MRI). In other words, a state-of-the-art feature transform strategy is not available that achieves high accuracy and provides the adaptation of 2D-based deep learning models for 3D MRI-based classification. With this aim, this paper presents a new version of the 3t2FTS approach (3t2FTS-v2) to apply a transfer learning model for tumor categorization of 3D MRI data. For performance evaluation, the BraTS 2017/2018 dataset is handled that involves high-grade glioma (HGG) and low-grade glioma (LGG) samples in four different sequences/phases. 3t2FTS-v2 is proposed to effectively transform the features from 3D to 2D space by using two textural features: first-order statistics (FOS) and gray level run length matrix (GLRLM). In 3t2FTS-v2, normalization analyses are assessed to be different from 3t2FTS to accurately transform the space information apart from the usage of GLRLM features. The ResNet50 architecture is preferred to fulfill the HGG/LGG classification due to its remarkable performance in tumor grading. As a result, for the classification of 3D data, the proposed model achieves a 99.64% accuracy by guiding the literature about the importance of 3t2FTS-v2 that can be utilized not only for tumor grading but also for whole brain tissue-based disease classification.

Gliomas are the most common intracranial primary tumors. Accurate grading of gliomas is crucial in determining treatment options and prognosis. Clinicians conventionally rely on multiple Magnetic Resonance Imaging (MRI) sequences for accurate glioma assessment. Traditional deep learning methods typically utilize the individual MRI sequence with the annotations of Region of Interest (ROIs), incurring substantial manual effort while losing the complementary information provided by other sequences. This task is inherently a standard multi-modal problem. However, existing methods often adopt complex multi-stream networks for feature extraction and fusion, leading to high resource demands and potential feature redundancy. To address the above challenge, a discrepancy-aware self-distillation method is proposed for multi-modal glioma grading, which requires only a single-stream network to concurrently analyze multiple MRI sequences without auxiliary ROIs. The first Modality Discrepancy-aware Fusion (MDF) module considers the MRI imaging differentiation and widens the inter-modal contrasts, allowing the modality-specific features to be highlighted and the modality-invariant features to be diminished. Furthermore, the proposed Class Activation Self-Distillation (CASD) strategy leverages the generated Class Activation Maps (CAMs) as dark knowledge for the distillation process. This guides shallow layers to focus on the category discriminative features specifically within the lesion region. Extensive experiments were conducted on the BraTS2018 and BraTS2019 datasets to evaluate the effectiveness of our method. The results show that our method outperforms other relevant glioma grading and multi-modal fusion methods on both datasets. • We propose an enhanced single-stream framework for multi-modal glioma grading. • Modality discrepancy-aware fusion module considers the MRI imaging differentiation. • Class activation self-distillation strategy transfers the CAMs as dark knowledge. • Our method achieves satisfactory results on the BraTS benchmarks. [ABSTRACT FROM AUTHOR]

Background: Noninvasive preoperative prediction of histological grading is essential for clinical management of cerebral glioma. Purpose: This study aimed to investigate the association between the image quality assessment of 1H magnetic resonance spectroscopy and accurate grading of glioma. Materials and Methods: 98 glioma patients confirmed by pathology were retrospectively recruited in this single-center study. All patients underwent 1H-MRS examination at 3.0T before surgery. According to WHO standards, all cases were divided into two groups: low-grade glioma (grade I and II, 48 cases) and high-grade glioma (grades III and IV, 50 cases). The metabolite ratios in both grades were calculated before and after image quality assessment. The area under the receiver operating characteristic (ROC) curve was used to evaluate the capacity of each ratio in glioma grading. Results: The Cho/Cr, Cho/NAA and NAA/Cr metabolite ratios had certain differences in each glioma group before and after MRS image quality assessment. In the low-grade glioma group, there was a dramatic difference in the Cho/Cr ratio before and after image quality assessment (p = 0.011). After MRS image quality assessment, the accuracy of glioma grading was significantly improved. The Cho/Cr ratio with 83.3% sensitivity and 93.7% specificity is the best index of glioma grading, with the optimal cutoff value of the Cho/Cr ratio being 3.72. Conclusion: The image quality of MRS does affect the metabolite ratios and the results of glioma grading. MRS image quality assessment can observably improve the accuracy rate of glioma grading. The Cho/Cr ratio has the best diagnostic performance in differentiating high-grade from low-grade glioma. [ABSTRACT FROM AUTHOR]

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterwards, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC:0.9939) on a public dataset, and good generalization performance (AUC:0.9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) models have provided advanced applications to many scientific areas, including the prediction of the pathologic grade of tumors, utilizing radiology techniques. Gliomas are among the malignant brain tumors in human adults, and their efficient diagnosis is of high clinical significance. Objectives: Given the contribution of AI to medical diagnoses, we investigated the role of deep learning in the differential diagnosis and grading of human brain gliomas. Methods: This study developed a new AI diagnostic model, i.e., EfficientNetB0, to grade and classify human brain gliomas, using sequences from magnetic resonance imaging (MRI). Results: We validated the newAI model, using a standard dataset (BraTS-2019) and demonstrated that the AI components, i.e., convo-lutional neural networks and transfer learning, provided excellent performance for classifying and grading glioma images at 98.8% accuracy. Conclusions: The proposed model, EfficientNetB0, is capable to classify and grade glioma from MRI sequences at high accuracy, validity, and specificity. It can provide better performance and diagnostic results for human glioma images than models developed by previous studies. [ABSTRACT FROM AUTHOR]

• The BraTS dataset is not divided into Low and High grade gliomas according to the WHO. • We propose a new radiological groundtruth for the BraTS dataset. • Prediction scores give insights about an automatic classifier's behaviour. • The prediction scores histogram can be used as a data exploration tool. • Crossed prediction scores allow comparison of two classifiers and individual tracking. Glioma grading using maching learning on magnetic resonance data is a growing topic. According to the World Health Organization (WHO), the classification of glioma discriminates between low grade gliomas (LGG), grades I, II; and high grade gliomas (HGG), grades III, IV, leading to major issues in oncology for therapeutic management of patients. A well-known dataset for machine-based grade prediction is the MICCAI Brain Tumor Segmentation (BraTS) dataset. However this dataset is not divided into WHO-defined LGG and HGG, since it combines grades I, II and III as "lower grades gliomas", while its HGG category only presents grade IV glioblastoma multiform. In this paper we want to train a binary grade classifier and investigate the consistency of the original BraTS labels with radiologic criteria using machine-aided predictions. Using WHO-based radiomic features, we trained a SVM classifier on the BraTS dataset, and used the prediction score histogram to investigate the behaviour of our classifier on the lower grade population. We also asked 5 expert radiologists to annotate BraTS images between low (as opposed to lower) grade and high grade glioma classes, resulting in a new groundtruth. Our first training reached 84.1% accuracy. The prediction score histogram allows us to identify the radiologically high grade patients among the original lower grade population of the BraTS dataset. Training another SVM on our new radiologically WHO-aligned groundtruth shows robust performances despite important class imbalance, reaching 82.4% accuracy. Our results highlight the coherence of radiologic criteria for low grade versus high grade classification under WHO terms. We also show how the histogram of prediction scores and crossed prediction scores can be used as tools for data exploration and performance evaluation. Therefore, we propose to use our radiological groundtruth for future development on binary glioma grading. [ABSTRACT FROM AUTHOR]

Glioma grading before surgery is very critical for the prognosis prediction and treatment plan making. We present a novel wavelet scattering-based radiomic method to predict noninvasively and accurately the glioma grades. The method consists of wavelet scattering feature extraction, dimensionality reduction, and glioma grade prediction. The dimensionality reduction was achieved using partial least squares (PLS) regression and the glioma grade prediction using support vector machine (SVM), logistic regression (LR) and random forest (RF). The prediction obtained on multimodal magnetic resonance images of 285 patients with well-labeled intratumoral and peritumoral regions showed that the area under the receiver operating characteristic curve (AUC) of glioma grade prediction was increased up to 0.99 when considering both intratumoral and peritumoral features in multimodal images, which represents an increase of about 13% compared to traditional radiomics. In addition, the features extracted from peritumoral regions further increase the accuracy of glioma grading.

Abstract Background Brain tumors are an important health problem. The preoperative classification of gliomas by non-invasive techniques is a significant problem. Relative cerebral blood volume and spectroscopy have the ability to sample the entire lesion non-invasively. The present study aims to evaluate the combined role of dynamic susceptibility perfusion and spectroscopy in the classification of primary brain tumors. The combination of both provides overall diagnostic accuracy (100%). Relative cerebral blood volume in peritumoral region plays an important additional role in this regard. Results On the basis of histopathology, among 50 patients with brain tumors, high-grade gliomas accounted for 58%, while low-grade gliomas accounted for 42%. The relative cerebral blood volume in the tumor had the best sensitivity, specificity, and accuracy of 96.8%, 95.3%, and 96, respectively. The use of relative cerebral blood volume and choline/N-acetyl Aspartate increased diagnostic accuracy by 100%. Conclusion The combination of magnetic resonance spectroscopy and perfusion can increase sensitivity and positive predictive value to define the degree of glioma.

[Display omitted] o Machine learning has been widely applied to MRI to detect and diagnose gliomas. o Non-invasive detection of genetics has the potential to supersede biopsy procedures. o Machine learning has demonstrated strong performance and clinical utility. o Performance metrics from 153 articles were synthesized to facilitate benchmarking. o Deep language models can facilitate systematic review article screening. Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine. [ABSTRACT FROM AUTHOR]

• A simple and sensitive DNA nanogear sensor has been proposed for grading analysis of gliomas by retrieval exosomes. • The designed DNA nanogear sensor can detect the target exosomes as low as 20 particles/μL. • The gear movement of the sensor on the surface of the exosomes showed a high-gain fluorescence signal. • Dual aptamers targeting exosomes improved the recognition specificity and capture efficiency of the sensor. Direct and accurate analysis of low concentrations of tumor-derived exosomes in complex biological samples is essential for non-invasive cancer diagnosis, but this remains challenging due to the lack of convenient and highly sensitive methods. Herein, we have proposed a novel strategy based on super spherical nucleic acids (SSNAs) combined with nicking enzyme triggering signal amplification for the direct detection of exosomes derived from gliomas. SSNAs utilize AuNPs as carriers, loaded with multifunctional DNA probes. And exosomes are simultaneously labeled by two aptamers. When SSNAs accurately recognize the labeled exosomes, the two make relative gear movement. During the gear movement, the probes act as an exosome-specific retrieval on the one hand, and serves as a fuel that is continuously consumed by the exosomes on the other hand, thus outputting a high-gain fluorescent signal. This strategy exhibits excellent specificity and ultra-high sensitivity for the detection of target exosomes as low as 20 particles/μL. The practicability of this method is further verified by the detection of clinical samples, which retains potential for early glioma diagnosis and grading analysis. [ABSTRACT FROM AUTHOR]

Lin-Feng Yan,1,* Ying-Zhi Sun,1,* Sha-Sha Zhao,1,* Yu-Chuan Hu,1,* Yu Han,1 Gang Li,2 Xin Zhang,1 Qiang Tian,1 Zhi-Cheng Liu,1 Yang Yang,1 Hai-Yan Nan,1 Ying Yu,1 Qian Sun,1 Jin Zhang,1 Ping Chen,1 Bo Hu,1 Fei Li,3 Teng-Hui Han,3 Wen Wang,1 Guang-Bin Cui1 1Department of Radiology & Functional and Molecular Imaging Key Laboratory of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University, Xi’an, Shaanxi 710038, People’s Republic of China; 2Department of Neurosurgery, Tangdu Hospital, Fourth Military Medical University, Xi’an, Shaanxi 710038, People’s Republic of China; 3Student Brigade, Fourth Military Medical University, Xi’an, Shaanxi 710032, People’s Republic of China*These authors contributed equally to this workCorrespondence: Wen Wang; Guang-Bin CuiDepartment of Radiology & Functional and Molecular Imaging Laboratory of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University, 569 Xinsi Road, Xi’an 710038, People’s Republic of ChinaTel +86-29-84778689; 86-29-84777863Email wangwen@fmmu.edu.cn; cuigbtd@fmmu.edu.cnPurpose: This study aims to incorporate informative histogram indicator analyses and advanced multimodal MRI parameters to differentiate low-grade gliomas (LGGs) from high-grade gliomas (HGGs) and to explore the features associated with patients’ survival.Patients and methods: A total of 120 patients with pathologically confirmed LGGs or HGGs receiving conventional and advanced MRI such as three-dimensional arterial spin labeling (3D-ASL), intravoxel incoherent motion-diffusion weighted imaging (IVIM-DWI), and dynamic contrast-enhanced MRI (DCE-MRI) were included. The mean and histogram indicators from advanced MRI were calculated from the entire tumor. The efficacies of a single indicator or multiple parameters were tested in distinguishing HGGs from LGGs and predicting patients’ survival. Receiver operating characteristic (ROC) curve and multivariable stepwise logistic regression were used to evaluate the diagnostic efficacies. Leave-one-out cross-validation was further used to validate the accuracy of the parameter sets in glioma grading. Log-rank test using the Kaplan–Meier curve was utilized to predict patients’ survival.Results: Overall, parameters from DCE-MRI performed better than those from 3D-ASL or IVIM-DWI in both glioma grading and survival prediction. The histogram metrics of Ve were demonstrated to have higher accuracies (the accuracies for Extended Tofts_Vemean and Extended Tofts_Vemedian were 68.33% and 71.67%, respectively, while those for the Incremental_Vemean and Incremental_Ve75th were 68.33% and 72.50%, respectively) in grading LGGs from HGGs. The combination of Tofts_Ve histogram metrics was the one with the highest accuracy (81.67%) and area under ROC curve (AUC = 0.840). On the other hand, Patlak_Ktrans95th (AUC = 0.9265) and Extended Tofts_Ve95th (AUC = 0.9154) performed better than their corresponding means (Patlak_Ktransmean: AUC = 0.9118 and Extended Tofts_Vemean: AUC = 0.9044) in predicting patients’ overall survival (OS) at 18-month follow-up.Conclusion: DCE-MRI-derived histogram features from the entire tumor were promising metrics for glioma grading and OS prediction. Combining single modal histogram features improved glioma grading.Trial registration: NCT 02622620.Keywords: multi-modal MRI, histogram features, receiver operating curve, glioma grading, survival analysis

Gliomas are the most common type of cerebral tumors; they occur with increasing incidence in the last decade and have a high rate of mortality. For efficient treatment, fast accurate diagnostic and grading of tumors are imperative. Presently, the grading of tumors is established by histopathological evaluation, which is a time-consuming procedure and relies on the pathologists' experience. Here we propose a supervised machine learning procedure for tumor grading which uses quantitative phase images of unstained tissue samples acquired by digital holographic microscopy. The algorithm is using an extensive set of statistical and texture parameters computed from these images. The procedure has been able to classify six classes of images (normal tissue and five glioma subtypes) and to distinguish between gliomas types from grades II to IV (with the highest sensitivity and specificity for grade II astrocytoma and grade III oligodendroglioma and very good scores in recognizing grade III anaplastic astrocytoma and grade IV glioblastoma). The procedure bolsters clinical diagnostic accuracy, offering a swift and reliable means of tumor characterization and grading, ultimately the enhancing treatment decision-making process., Competing Interests: The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Violeta L. Calin reports article publishing charges was provided by University of Medicine and Pharmacy Carol Davila. Violeta L. Calin, Mona Mihailescu reports equipment, drugs, or supplies was provided by Optoelectronica 2001 S.A. Violeta L. Calin, Mona Mihailescu, Tudor Savopol, Mihaela G. Moisescu have a patent licensed no. RO134410/2019 from Romanian State Office for Inventions and Trademarks., (© 2024 The Authors.)

The grading of glioma has clinical significance in determining a treatment strategy and evaluating prognosis to investigate a novel set of radiomic features extracted from the fractional anisotropy (FA) and mean diffusivity (MD) maps of brain diffusion tensor imaging (DTI) sequences for computer-aided grading of gliomas. This retrospective study included 108 patients who had pathologically confirmed brain gliomas and DTI scanned during 2012–2018. This cohort included 43 low-grade gliomas (LGGs; all grade II) and 65 high-grade gliomas (HGGs; grade III or IV). We extracted a set of radiomic features, including traditional texture, morphological, and novel deep features derived from pre-trained convolutional neural network models, in the manually-delineated tumor regions. We employed support vector machine and these radiomic features for two classification tasks: LGGs vs HGGs, and grade III vs IV. The area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity was reported as the performance metrics using the leave-one-out cross-validation method. When combining FA+MD, AUC = 0.93, accuracy = 0.94, sensitivity = 0.98, and specificity = 0.86 in classifying LGGs from HGGs, while AUC = 0.99, accuracy = 0.98, sensitivity = 0.98, and specificity = 1.00 in classifying grade III from IV. The AUC and accuracy remain close when features were extracted from only the solid tumor or additionally including necrosis, cyst, and peritumoral edema. Still, the effects in terms of sensitivity and specificity are mixed. Deep radiomic features derived from pre-trained convolutional neural networks showed higher prediction ability than the traditional texture and shape features in both classification experiments. Radiomic features extracted on the FA and MD maps of brain DTI images are useful for noninvasively classification/grading of LGGs vs HGGs, and grade III vs IV. [ABSTRACT FROM AUTHOR]

Purpose: Gliomas are the most common primary tumor of the brain and are classified into grades I‐IV of the World Health Organization (WHO), based on their invasively histological appearance. Gliomas grading plays an important role to determine the treatment plan and prognosis prediction. In this study we propose two novel methods for automatic, non‐invasively distinguishing low‐grade (Grades II and III) glioma (LGG) and high‐grade (grade IV) glioma (HGG) on conventional MRI images by using deep convolutional neural networks (CNNs). Methods: All MRI images have been preprocessed first by rigid image registration and intensity inhomogeneity correction. Both proposed methods consist of two steps: (a) three‐dimensional (3D) brain tumor segmentation based on a modification of the popular U‐Net model; (b) tumor classification on segmented brain tumor. In the first method, the slice with largest area of tumor is determined and the state‐of‐the‐art mask R‐CNN model is employed for tumor grading. To improve the performance of the grading model, a two‐dimensional (2D) data augmentation has been implemented to increase both the amount and the diversity of the training images. In the second method, denoted as 3DConvNet, a 3D volumetric CNNs is applied directly on bounding image regions of segmented tumor for classification, which can fully leverage the 3D spatial contextual information of volumetric image data. Results: The proposed schemes were evaluated on The Cancer Imaging Archive (TCIA) low grade glioma (LGG) data, and the Multimodal Brain Tumor Image Segmentation (BraTS) Benchmark 2018 training datasets with fivefold cross validation. All data are divided into training, validation, and test sets. Based on biopsy‐proven ground truth, the performance metrics of sensitivity, specificity, and accuracy are measured on the test sets. The results are 0.935 (sensitivity), 0.972 (specificity), and 0.963 (accuracy) for the 2D Mask R‐CNN based method, and 0.947 (sensitivity), 0.968 (specificity), and 0.971 (accuracy) for the 3DConvNet method, respectively. In regard to efficiency, for 3D brain tumor segmentation, the program takes around ten and a half hours for training with 300 epochs on BraTS 2018 dataset and takes only around 50 s for testing of a typical image with a size of 160 × 216 × 176. For 2D Mask R‐CNN based tumor grading, the program takes around 4 h for training with around 60 000 iterations, and around 1 s for testing of a 2D slice image with size of 128 × 128. For 3DConvNet based tumor grading, the program takes around 2 h for training with 10 000 iterations, and 0.25 s for testing of a 3D cropped image with size of 64 × 64 × 64, using a DELL PRECISION Tower T7910, with two NVIDIA Titan Xp GPUs. Conclusions: Two effective glioma grading methods on conventional MRI images using deep convolutional neural networks have been developed. Our methods are fully automated without manual specification of region‐of‐interests and selection of slices for model training, which are common in traditional machine learning based brain tumor grading methods. This methodology may play a crucial role in selecting effective treatment options and survival predictions without the need for surgical biopsy. [ABSTRACT FROM AUTHOR]

Objectives: The present study aimed to study whether combined inflow-based vascular-space-occupancy (iVASO) MR imaging (MRI) and diffusion-weighted imaging (DWI) improve the diagnostic accuracy in the preoperative grading of gliomas. Methods: Fifty-one patients with histopathologically confirmed diffuse gliomas underwent preoperative structural MRI, iVASO, and DWI. We performed 2 qualitative consensus reviews: (1) structural MR images alone and (2) structural MR images with iVASO and DWI. Relative arteriolar cerebral blood volume (rCBVa) and minimum apparent diffusion coefficient (mADC) were compared between low-grade and high-grade gliomas. Receiver operating characteristic (ROC) curve analysis was performed to compare the tumor grading efficiency of rCBVa, mADC, and the combination of the two parameters. Results: Two observers diagnosed accurate tumor grade in 40 of 51 (78.4%) patients in the first review and in 46 of 51 (90.2%) in the second review. Both rCBVa and mADC showed significant differences between low-grade and high-grade gliomas. ROC analysis gave a threshold value of 1.52 for rCBVa and 0.85 × 10−3 mm2/s for mADC to provide a sensitivity and specificity of 88.0 and 81.2% and 100.0 and 68.7%, respectively. The area under the ROC curve (AUC) was 0.87 and 0.85 for rCBVa and mADC, respectively. The combination of rCBVa and mADC values increased the AUC to 0.92. Conclusion: The combined application of iVASO and DWI may improve the diagnostic accuracy of glioma grading. [ABSTRACT FROM AUTHOR]

Background: Susceptibility weighted imaging (SWI) provides vascular information and plays an important role in improving the diagnostic accuracy of preoperative glioma grading. Intratumoral susceptibility signal intensities (ITSS) obtained from SWI has been used in glioma grading. However, the current method for estimation of ITSS is semiquantitative, manual count-dependent, and includes hemorrhage as well as vasculature.Purpose: To develop a quantitative approach that calculates the vasculature volume within tumors by filtering out the hemorrhage from ITSS using R2 * values and connected component analysis-based segmentation algorithm; to evaluate the accuracy of the proposed ITSS vasculature volume (IVV) for differentiating various grades of glioma; and compare it with reported semiquantitative ITSS approach.Study Type: Retrospective.Subjects: Histopathologically confirmed 41 grade IV, 19 grade III, and 15 grade II glioma patients.Field Strength/Sequence: SWI (four echoes: 5.6, 11.8, 18, 24.2 msec) along with conventional MRI sequences (T2 -weighted, T1 -weighted, 3D-fluid-attenuated inversion recovery [FLAIR], and diffusion-weighted imaging [DWI]) at 3.0T.Assessment: R2 * relaxation maps were calculated from multiecho SWI. The R2 * cutoff value for hemorrhage ITSS was determined. A segmentation algorithm was designed, based on this R2 * hemorrhage combined with connected component shape analysis, to quantify the IVV from all slices containing tumor by filtering out hemorrhages. Semiquantitative ITSS scoring as well as total ITSS volume (TIV) including hemorrhages were also calculated.Statistical Tests: One-way analysis of variance (ANOVA) and Tukey-Kramer post-hoc tests were performed to see the difference among the three grades of the tumor (II, III, and IV) in terms of semiquantitative ITSS scoring, TIV, and IVV. Receiver operating characteristic (ROC) curve analysis was used to evaluate the performance of the three methods individually in discriminating between grades of glioma.Results: One-way ANOVA showed that only the proposed IVV significantly differentiated different grades of gliomas having visible ITSS. ROC analysis showed that IVV provided the highest AUC for the discrimination of grade II vs. III (0.93), grade III vs. IV (0.98), and grade II vs. IV glioma (0.94). IVV also provided the highest sensitivity and specificity for differentiating grade II vs. III (87.44, 98.41), grade III vs. IV (97.15, 94.12), and grade II vs. IV (98.72, 92.31).Data Conclusion: The proposed quantitative method segregates hemorrhage from tumor vasculature. It scores above the existing semiquantitative method in terms of ITSS estimation and grading accuracy.Level Of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:225-233. [ABSTRACT FROM AUTHOR]

Abstract Background Dynamic-contrast-enhanced (DCE) MRI data acquired using gradient echo based sequences is affected by errors in flip angle (FA) due to transmit B1 inhomogeneity (B1inh). The purpose of the study was to evaluate the effect of B1inh on quantitative analysis of DCE-MRI data of human brain tumor patients and to evaluate the clinical significance of B1inh correction of perfusion parameters (PPs) on tumor grading. Methods An MRI study was conducted on 35 glioma patients at 3T. The patients had histologically confirmed glioma with 23 high-grade (HG) and 12 low-grade (LG). Data for B1-mapping, T1-mapping and DCE-MRI were acquired. Relative B1 maps (B1rel) were generated using the saturated-double-angle method. T1-maps were computed using the variable flip-angle method. Post-processing was performed for conversion of signal–intensity time (S(t)) curve to concentration–time (C(t)) curve followed by tracer kinetic analysis (Ktrans, Ve, Vp, Kep) and first pass analysis (CBV, CBF) using the general tracer-kinetic model. DCE-MRI data was analyzed without and with B1inh correction and errors in PPs were computed. Receiver-operating-characteristic (ROC) analysis was performed on HG and LG patients. Simulations were carried out to understand the effect of B1 inhomogeneity on DCE-MRI data analysis in a systematic way. S(t) curves mimicking those in tumor tissue, were generated and FA errors were introduced followed by error analysis of PPs. Dependence of FA-based errors on the concentration of contrast agent and on the duration of DCE-MRI data was also studied. Simulations were also done to obtain Ktrans of glioma patients at different B1rel values and see whether grading is affected or not. Results Current study shows that B1rel value higher than nominal results in an overestimation of C(t) curves as well as derived PPs and vice versa. Moreover, at same B1rel values, errors were large for larger values of C(t). Simulation results showed that grade of patients can change because of B1inh. Conclusions B1inh in the human brain at 3T-MRI can introduce substantial errors in PPs derived from DCE-MRI data that might affect the accuracy of tumor grading, particularly for border zone cases. These errors can be mitigated using B1inh correction during DCE-MRI data analysis.

Glioma is one of the most common malignant tumors in clinical practice, and its grading diagnosis provides an important clinical basis for the follow-up treatment and the formulation of a surgical plan. Different grades of glioma have varying degrees of invasion. In the context of medicine and engineering cooperation, to effectively achieve the clinical automatic grading of gliomas, this paper proposes a dual-path parallel hierarchical diagnostic model based on pathomorphological features. The model can extract the pathomorphological features of gliomas, and obtain the progressive enhancement result of the image to complete the enhancement of prior features of gliomas. The dual-path structure corresponds to the multi-modal input, and then the grading is completed with the help of multi-feature fusion. The model is verified on the clinical data samples provided by Liaoning Cancer Hospital, and its accuracy can reach 0.986. Experiments show that the proposed model has high accuracy and good generalization ability, which can complete the automatic grading diagnosis of glioma. [ABSTRACT FROM AUTHOR]

The fusion of multi-modal data, e.g., pathology slides and genomic profiles, can provide complementary information and benefit glioma grading. However, genomic profiles are difficult to obtain due to the high costs and technical challenges, thus limiting the clinical applications of multi-modal diagnosis. In this work, we investigate the realistic problem where paired pathology-genomic data are available during training, while only pathology slides are accessible for inference. To solve this problem, a comprehensive learning and adaptive teaching framework is proposed to improve the performance of pathological grading models by transferring the privileged knowledge from the multi-modal teacher to the pathology student. For comprehensive learning of the multi-modal teacher, we propose a novel Saliency-Aware Masking (SA-Mask) strategy to explore richer disease-related features from both modalities by masking the most salient features. For adaptive teaching of the pathology student, we first devise a Local T opology Preserving and D iscrepancy Eliminating C ontrastive Distillation (TDC-Distill) module to align the feature distributions of the teacher and student models. Furthermore, considering the multi-modal teacher may include incorrect information, we propose a Gradient-guided Knowledge Refinement (GK-Refine) module that builds a knowledge bank and adaptively absorbs the reliable knowledge according to their agreement in the gradient space. Experiments on the TCGA GBM-LGG dataset show that our proposed distillation framework improves the pathological glioma grading and outperforms other KD methods. Notably, with the sole pathology slides, our method achieves comparable performance with existing multi-modal methods. The code is available at https://github.com/CUHK-AIM-Group/MultiModal-learning. • Present a novel Comprehensive Learning and Adaptive Teaching framework to distill pathology-genomic knowledge and benefit the glioma grading with pathology slides. • Propose a Cross-modal Saliency Masking(CS-Mask) strategy to explore the neglected but useful features from both modalities, thus providing a better role model for the student. • Devise a novel Local Topology Preserving and Discrepancy Eliminating Contrastive Distillation(TDC-Distill) module to align feature distributions in an effective manner, and a Gradient-guided Knowledge Refinement(GK-Refine) scheme to enable adaptive knowledge absorption. [ABSTRACT FROM AUTHOR]

Objectives: To assess the diagnostic accuracy of DW-MRI, ADC value, and MRS in preoperative glioma grading because of its importance in treatment planning. Patients and methods: A prospective study included 30 patients with gliomas, based on CT and cMRI findings, referred from Neurosurgery Department for DWI and MRS. Results were correlated with histopathological diagnosis after surgical resection. Results: ADC values were significantly higher in low grade gliomas relative to high grade ones. The lowest value was for GBM, 100% sensitivity, specificity, PPV and NPP in glioma grading. MRS revealed higher Cho/NAA and Cho/Cr ratios in high grade neoplasms and characteristic elevated lipid peak with statistical significant difference between low grade and high grade gliomas. MRS was more accurate than ADC value in detecting peritumoral infiltration of high grade gliomas, but there were no statistically significant differences between anaplastic and GBM in tumoral and peritumoral regions. Conclusion: DW-MRI had higher sensitivity, specificity and accuracy than cMRI and MRS in glioma grading while MRS is more accurate than ADC value in assessing peri-tumoral infiltration based on high metabolite ratios in peri-tumoral tissue for anaplastic glioma and GBM, but there were no statistically significant differences between high grade groups.