Glioma is a primary brain tumor with high incidence rate. High-grade gliomas (HGG) are those with the highest degree of malignancy and the lowest degree of survival. Surgical resection and postoperative adjuvant chemoradiotherapy are often used in clinical treatment, so accurate segmentation of tumor-related areas is of great significance for the treatment of patients. In order to improve the segmentation accuracy of HGG, this paper proposes a multi-modal glioma semantic segmentation network with multi-scale feature extraction and multi-attention fusion mechanism. The main contributions are, (1) Multi-scale residual structures were used to extract features from multi-modal gliomas magnetic resonance imaging (MRI); (2) Two types of attention modules were used for features aggregating in channel and spatial; (3) In order to improve the segmentation performance of the whole network, the branch classifier was constructed using ensemble learning strategy to adjust and correct the classification results of the backbone classifier. The experimental results showed that the Dice coefficient values of the proposed segmentation method in this article were 0.909 7, 0.877 3 and 0.839 6 for whole tumor, tumor core and enhanced tumor respectively, and the segmentation results had good boundary continuity in the three-dimensional direction. Therefore, the proposed semantic segmentation network has good segmentation performance for high-grade gliomas lesions.
Attention ; Glioma/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging/methods* ; Semantics

BACKGROUND: It is crucial to differentiate accurately glioma recurrence and pseudoprogression which have entirely different prognosis and require different treatment strategies. This study aimed to assess the diagnostic accuracy of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) as a tool for distinguishing glioma recurrence and pseudoprogression. METHODS: According to particular criteria of inclusion and exclusion, related studies up to May 1, 2019, were thoroughly searched from several databases including PubMed, Embase, Cochrane Library, and Chinese biomedical databases. The quality assessment of diagnostic accuracy studies was applied to evaluate the quality of the included studies. By using the "mada" package in R, the heterogeneity, overall sensitivity, specificity, and diagnostic odds ratio were calculated. Moreover, funnel plots were used to visualize and estimate the publication bias in this study. The area under the summary receiver operating characteristic (SROC) curve was computed to display the diagnostic efficiency of DCE-MRI. RESULTS: In the present meta-analysis, a total of 11 studies covering 616 patients were included. The results showed that the pooled sensitivity, specificity, and diagnostic odds ratio were 0.792 (95% confidence interval [CI] 0.707-0.857), 0.779 (95% CI 0.715-0.832), and 16.219 (97.5% CI 9.123-28.833), respectively. The value of the area under the SROC curve was 0.846. In addition, the SROC curve showed high sensitivities (>0.6) and low false positive rates (<0.5) from most of the included studies, which suggest that the results of our study were reliable. Furthermore, the funnel plot suggested the existence of publication bias. CONCLUSIONS While the DCE-MRI is not the perfect diagnostic tool for distinguishing glioma recurrence and pseudoprogression, it was capable of improving diagnostic accuracy. Hence, further investigations combining DCE-MRI with other imaging modalities are required to establish an efficient diagnostic method for glioma patients.
Glioma/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging ; Neoplasm Recurrence, Local/diagnostic imaging* ; ROC Curve ; Sensitivity and Specificity

Glioma is the most common malignant brain tumor and classification of low grade glioma (LGG) and high grade glioma (HGG) is an important reference of making decisions on patient treatment options and prognosis. This work is largely done manually by pathologist based on an examination of whole slide image (WSI), which is arduous and heavily dependent on doctors' experience. In the World Health Organization (WHO) criteria, grade of glioma is closely related to hypercellularity, nuclear atypia and necrosis. Inspired by this, this paper designed and extracted cell density and atypia features to classify LGG and HGG. First, regions of interest (ROI) were located by analyzing cell density and global density features were extracted as well. Second, local density and atypia features were extracted in ROI. Third, balanced support vector machine (SVM) classifier was trained and tested using 10 selected features. The area under the curve (AUC) and accuracy (ACC) of 5-fold cross validation were 0.92 ± 0.01 and 0.82 ± 0.01 respectively. The results demonstrate that the proposed method of locating ROI is effective and the designed features of density and atypia can be used to predict glioma grade accurately, which can provide reliable basis for clinical diagnosis.
Brain Neoplasms/diagnostic imaging* ; Glioma/diagnostic imaging* ; Humans ; Magnetic Resonance Imaging ; Neoplasm Grading ; Support Vector Machine

OBJECTIVES: Glioma is the most common intracranial primary tumor in central nervous system. Glioma grading possesses important guiding significance for the selection of clinical treatment and follow-up plan, and the assessment of prognosis. This study aims to explore the feasibility of logistic regression model based on radiomics to predict glioma grading. METHODS: Retrospective analysis was performed on 146 glioma patients with confirmed pathological diagnosis from January, 2012 to December, 2018. A total of 41 radiomics features were extracted from contrast-enhanced T RESULTS: A total of 5 imaging features selected by LASSO were used to establish a logistic regression model for predicting glioma grading. The model showed good discrimination with AUC value of 0.919. Hosmer-Lemeshow test showed no significant difference between the calibration curve and the ideal curve ( CONCLUSIONS The logistic regression model using radiomics exhibits a relatively high accuracy for predicting glioma grading, which may serve as a complementary tool for preoperative prediction of giloma grading.
Brain Neoplasms/diagnostic imaging* ; Glioma/diagnostic imaging* ; Humans ; Logistic Models ; Magnetic Resonance Imaging ; ROC Curve ; Retrospective Studies

OBJECTIVE: To investigate the values of diffusion tensor imaging (DTI) and virtual reality (VR) techniques in design surgery program of gliomas near eloquent regions. METHODS: In this study, 35 cases were retrospectively analyzed with gliomas involved language areas or rolandic regions operated in Department of Neurosurgery, Peking University Third Hospital from January 2015 to January 2019. Surgery programs were performed by Dextroscope virtual reality system. The pre-operative data, such as the magnetic resonance imaging (MRI), magnetic resonance arteriography (MRA) and DTI was transferred into the VR computer for restitution,Tumors, neural fiber tracts and blood vessels were reconstructed to simulate operation and design individual surgical plan. Neurological function was evaluated 1 week, 1 month and 3 months after operation. RESULTS: Virtual reality three-dimensional images of the 35 cases were successfully achieved, including neural fiber tracts,blood vessels and the lesions. The displacement and destruction of fiber tracts, the anatomic relationship between tumor and important fiber bundle, artery and vein could be shown clearly. Surgical simulation and surgery program of VR of the 35 patients were successfully performed. The 3D images obtained from virtual reality near to the real surgery. Ten of the 35 cases were defined as rolandic regions tumors, 14 of the 35 cases were defined as language areas tumors and 11 of the 35 cases involved both language areas and rolandic regions. Complete resection of enhancing tumor (CRET) was achieved in 30 cases (85.7%), subtotal resection in 5 cases (14.3%), neurological function improved in 34 cases (97.1%) after operation,and 1 case had no improvement compared with that before(2.9%). Thirteen cases without neurological deficit pre-operation, showed transient neurological deficit ,which were recovered about 10 days post-operation, 12 of 22 cases with pre-operative neurologic deficit, improved one week postoperation, 9 of 22 cases with pre-operative neurologic deficit improved one month after operation, the rest 1 case was recurrent with glioblastoma with aggravated hemiplegia symptom after operation, who died of cerebral hernia 2 months later. CONCLUSION Dextroscope virtual reality system can clearly expose and quantify the 3D anatomic relationship of tumors, neural fiber tracts and blood vessels surrounding gliomas near eloquent regions, which is helpful to design the best individualized surgery program, to improve surgical effect.
Brain Neoplasms/diagnostic imaging* ; Diffusion Tensor Imaging ; Glioma/diagnostic imaging* ; Humans ; Imaging, Three-Dimensional ; Magnetic Resonance Imaging ; Retrospective Studies ; Virtual Reality

Focus on the inconsistency of the shape, location and size of brain glioma, a dual-channel 3-dimensional (3D) densely connected network is proposed to automatically segment brain glioma tumor on magnetic resonance images. Our method is based on a 3D convolutional neural network frame, and two convolution kernel sizes are adopted in each channel to extract multi-scale features in different scales of receptive fields. Then we construct two densely connected blocks in each pathway for feature learning and transmission. Finally, the concatenation of two pathway features was sent to classification layer to classify central region voxels to segment brain tumor automatically. We train and test our model on open brain tumor segmentation challenge dataset, and we also compared our results with other models. Experimental results show that our algorithm can segment different tumor lesions more accurately. It has important application value in the clinical diagnosis and treatment of brain tumor diseases.
Brain Neoplasms ; diagnostic imaging ; Glioma ; diagnostic imaging ; Humans ; Image Processing, Computer-Assisted ; Magnetic Resonance Imaging ; Neural Networks (Computer)

To explore the feasibility and efficacy of artificial neural network for differentiating high-grade glioma and low-grade glioma using image information.
 Methods: A total of 130 glioma patients with confirmed pathological diagnosis were selected retrospectively from 2012 to 2017. Forty one imaging features were extracted from each subjects based on 2-dimension magnetic resonance T1 weighted imaging with contrast-enhancement. An artificial neural network model was created and optimized according to the performance of feature selection. The training dataset was randomly selected half of the whole dataset, and the other half dataset was used to verify the performance of the neural network for glioma grading. The training-verification process was repeated for 100 times and the performance was averaged.
 Results: A total of 5 imaging features were selected as the ultimate input features for the neural network. The mean accuracy of the neural network for glioma grading was 90.32%, with a mean sensitivity at 87.86% and a mean specificity at 92.49%. The area under the curve of receiver operating characteristic curve was 0.9486.
 Conclusion: As a technique of artificial intelligence, neural network can reach a relatively high accuracy for the grading of glioma and provide a non-invasive and promising computer-aided diagnostic process for the pre-operative grading of glioma.
Brain Neoplasms ; diagnostic imaging ; pathology ; Glioma ; diagnostic imaging ; pathology ; Humans ; Magnetic Resonance Imaging ; Neoplasm Grading ; Neural Networks, Computer ; ROC Curve ; Retrospective Studies ; Sensitivity and Specificity

Objective:Gliomas are the most common neoplasm of the central nervous system (CNS); however, traditional imaging techniques do not show the boundaries of tumors well. Some researchers have found a new therapeutic mode to combine nanoparticles, which are nanosized particles with various properties for specific therapeutic purposes, and stem cells for tracing gliomas. This review provides an introduction of the basic understanding and clinical applications of the combination of stem cells and nanoparticles as a contrast agent for glioma imaging.

Data SourcesStudies published in English up to and including 2017 were extracted from the PubMed database with the selected key words of "stem cell," "glioma," "nanoparticles," "MRI," "nuclear imaging," and "Fluorescence imaging."

Study Selection:The selection of studies focused on both preclinical studies and basic studies of tracking glioma with nanoparticle-labeled stem cells.

Results:Studies have demonstrated successful labeling of stem cells with multiple types of nanoparticles. These labeled stem cells efficiently migrated to gliomas of varies models and produced signals sensitively captured by different imaging modalities.

ConclusionThe use of nanoparticle-labeled stem cells is a promising imaging platform for the tracking and treatment of gliomas.

Animals ; Contrast Media ; chemistry ; Glioma ; diagnostic imaging ; Humans ; Nanoparticles ; chemistry ; Stem Cells ; chemistry

PURPOSE: We aimed to investigate the effectiveness of ferritin as a contrast agent and a potential reporter gene for tracking tumor cells or macrophages in mouse cancer models. MATERIALS AND METHODS: Adenoviral human ferritin heavy chain (Ad-hFTH) was administrated to orthotopic glioma models and subcutaneous colon cancer mouse models using U87MG and HCT116 cells, respectively. Brain MR images were acquired before and daily for up to 6 days after the intracranial injection of Ad-hFTH. In the HCT116 tumor model, MR examinations were performed before and at 6, 24, and 48 h after intratumoral injection of Ad-hFTH, as well as before and every two days after intravenous injection of ferritin-labeled macrophages. The contrast effect of ferritin in vitro was measured by MR imaging of cell pellets. MRI examinations using a 7T MR scanner comprised a T1-weighted (T1w) spin-echo sequence, T2-weighted (T2w) relaxation enhancement sequence, and T2*-weighted (T2*w) fast low angle shot sequence. RESULTS: Cell pellet imaging of Ad-hFTH in vitro showed a strong negatively enhanced contrast in T2w and T2*w images, presenting with darker signal intensity in high concentrations of Fe. T2w images of glioma and subcutaneous HCT116 tumor models showed a dark signal intensity around or within the Ad-hFTH tumor, which was distinct with time and apparent in T2*w images. After injection of ferritin-labeled macrophages, negative contrast enhancement was identified within the tumor. CONCLUSION: Ferritin could be a good candidate as an endogenous MR contrast agent and a potential reporter gene that is capable of maintaining cell labeling stability and cellular safety.
Animals ; Brain Neoplasms/*diagnostic imaging/pathology ; Cell Line, Tumor ; Cell Tracking/*methods ; Colonic Neoplasms/*diagnostic imaging/pathology ; *Contrast Media/administration & dosage ; Disease Models, Animal ; Female ; *Ferritins/administration & dosage ; Genes, Reporter ; Glioma/*diagnostic imaging/pathology ; Humans ; Injections, Intravenous ; Macrophages ; Magnetic Resonance Imaging/*methods ; Male ; Mice ; Neoplasm Transplantation ; Skin Neoplasms/*diagnostic imaging/pathology ; Time Factors

Tuberous sclerosis complex (TSC) is an uncommon multiorgan disorder that may present many and different manifestations on imaging. Radiology plays an important role in diagnosis and management, and can substantially improve the clinical outcome of TSC. Therefore, a comprehensive understanding of this disease is essential for the radiologist. The manifestations of TSC on computer tomography (CT) and magnetic resonance (MR) images were analyzed. Eleven patients with a clinical diagnosis of TSC were retrospectively reviewed. Central nervous system lesions included subependymal nodules (SENs) (11/11), subependymal giant cell astrocytomas (SEGAs) (2/11), cortical and subcortical tuber lesions (5/11), and white matter lesions (4/11). Of the 6 patients with abdominal scans, there were 6 cases of renal angiomyolipomas (AMLs), and one case of hepatic AMLs. Of the 4 patients undergoing chest CT, lung lymhangioleiomyomatosis (LAM) (2/4), and multiple small sclerotic bone lesions (2/4) were observed. Different modalities show different sensitivity to the lesion. Analysis of images should be integrated with patients' history in order to diagnose TSC.
Adolescent ; Adult ; Brain ; diagnostic imaging ; pathology ; Child ; Child, Preschool ; Female ; Glioma, Subependymal ; diagnosis ; diagnostic imaging ; pathology ; Humans ; Lung ; diagnostic imaging ; pathology ; Magnetic Resonance Imaging ; methods ; Male ; Middle Aged ; Nervous System Diseases ; diagnosis ; diagnostic imaging ; pathology ; Tuberous Sclerosis ; classification ; diagnosis ; diagnostic imaging ; pathology