Intraaxial brain masses: MR imaging-based diagnostic strategy--initial experience

Multidimensional Proteomic Landscape Reveals Distinct Activated Pathways Between Human Brain Tumors

Brain metastases (BrMs) and gliomas are two typical human brain tumors with high incidence of mortalities and distinct clinical challenges, yet the understanding of these two types of tumors remains incomplete. Here, a multidimensional proteomic landscape of BrMs and gliomas to infer tumor-specific molecular pathophysiology at both tissue and plasma levels is presented. Tissue sample analysis reveals both shared and distinct characteristics of brain tumors, highlighting significant disparities between BrMs and gliomas with differentially activated upstream pathways of the PI3K-Akt signaling pathway that have been scarcely discussed previously. Novel proteins and phosphosites such as NSUN2, TM9SF3, and PRKCG_S330 are also detected, exhibiting a high correlation with reported clinical traits, which may serve as potential immunohistochemistry (IHC) biomarkers. Moreover, tumor-specific altered phosphosites and glycosites on FN1 are highlighted as potential therapeutic targets. Further validation of 110 potential noninvasive biomarkers yields three biomarker panels comprising a total of 19 biomarkers (including DES, VWF, and COL1A1) for accurate discrimination of two types of brain tumors and normal controls. In summary, this is a full-scale dataset of two typical human brain tumors, which serves as a valuable resource for advancing precision medicine in cancer patients through targeted therapy and immunotherapy.

Solitary Tumefactive Demyelinating Lesions in Children: Clinical and Magnetic Resonance Imaging Features, Pathologic Characteristics, and Outcomes

BACKGROUND

Isolated tumefactive demyelinating lesions (≥2 cm) may be difficult to distinguish from contrast-enhancing brain tumors, central nervous system infections, and (rarely) tissue dysgenesis, which may all occur with increased signal on T2-weighted images. Establishing an accurate diagnosis is essential for management, and we delineate our single-center experience.

METHODS

We performed a retrospective review of medical records, imaging, and biopsy specimens for patients under 18 years presenting with isolated tumefactive demyelination over a 10-year period.

RESULTS

Ten children (eight female) met inclusion criteria, with a median age of 14.1 years. Lesions were most likely to involve the thalamus (six of 10), brainstem (five of 10), basal ganglia (four of 10), or corpus callosum (four of 10). Eighty percent had perilesional edema at presentation, and 60% had midline shift. Biopsies demonstrated demyelination with perivascular lymphocytic infiltration and axonal damage ranging from mild to severe. All patients were initially treated with high-dose corticosteroids, and eight of 10 required additional medical therapies such as intravenous immunoglobulin, plasmapheresis, cyclophosphamide, or rituximab. Increased intracranial pressure was managed aggressively with two of 10 patients requiring decompressive craniectomies. Clinical outcomes varied.

CONCLUSIONS

Solitary tumefactive demyelinating lesions are rare, and aggressive management of inflammation and increased intracranial pressure is essential. Biopsy is helpful to evaluate for other diagnoses on the differential and maximize therapies. Treatment beyond initial therapy with corticosteroids is often required. Isolated tumefactive demyelinating lesions are uncommon; multicenter natural history studies are needed to better delineate differential diagnoses and optimal therapies.

DA, K. KK. Diagnostic Utility of Integration of Dynamic Contrast-Enhanced and Dynamic Susceptibility Contrast MR Perfusion Employing Split Bolus Technique in Differentiating High-Grade Glioma

Background : Despite documented correlation between glioma grades and dynamic contrast-enhanced (DCE) magnetic resonance (MR) perfusion-derived parameters, and its inherent advantages over dynamic susceptibility contrast (DSC) perfusion, the former remains underutilized in clinical practice. Given the inherent spatial heterogeneity in high-grade diffuse glioma (HGG) and assessment of different perfusion parameters by DCE (extravascular extracellular space volume [Ve] and volume transfer constant in unit time [k-trans]) and DSC (rCBV), integration of the two into a protocol could provide a holistic assessment. Considering therapeutic and prognostic implications of differentiating WHO grade 3 from 4, we analyzed the two grades based on a combined DCE and DSC perfusion. Methods : Perfusion sequences were performed on 3-T MR. Cumulative dose of 0.1 mmol/kg of gadodiamide, split into two equal boluses, was administered with an interval of 6 minutes between the DCE and DSC sequences. DCE data were analyzed utilizing commercially available GenIQ software. Results : Of the 41 cases of diffuse gliomas analyzed, 24 were WHO grade III and 17 grade IV gliomas (2016 WHO classification). To differentiate grade III and IV gliomas, Ve cut-off value of 0.178 provided the best combination of sensitivity (88.24%) and specificity (87.50%; AUC: 0.920; p  < 0.001). A relative cerebral blood volume (rCBV) of value 3.64 yielded a sensitivity of 70.59% and specificity of 62.50% ( p  = 0.018). The k-trans value, although higher in grade III than in grade IV gliomas, did not reach statistical significance ( p  = 0.108). Conclusion : Uniqueness of employed combined perfusion technique, treatment naïve patients at imaging, user-friendly postprocessing software utilization, and ability of Ve and rCBV to differentiate between grade III and IV gliomas ( p  < 0.05) are the strengths of the present study, contributing to the existing literature and moving a step closer to achieving accurate MR perfusion-based glioma grading.

Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation

RATIONALE AND OBJECTIVES

Imaging-based differentiation between glioblastoma (GB) and brain metastases (BM) remains challenging. Our aim was to evaluate the performance of 3D-convolutional neural networks (CNN) to address this binary classification problem.

MATERIALS AND METHODS

T1-CE, T2WI, and FLAIR 3D-segmented masks of 307 patients (157 GB and 150 BM) were generated post resampling, co-registration normalization and semi-automated 3D-segmentation and used for internal model development. Subsequent external validation was performed on 59 cases (27 GB and 32 BM) from another institution. Four different mask-sequence combinations were evaluated using area under the curve (AUC), precision, recall and F1-scores. Diagnostic performance of a neuroradiologist and a general radiologist, both without and with the model output available, was also assessed.

RESULTS

3D-model using the T1-CE tumor mask (TM) showed the highest performance [AUC 0.93 (95% CI 0.858-0.995)] on the external test set, followed closely by the model using T1-CE TM and FLAIR mask of peri-tumoral region (PTR) [AUC of 0.91 (95% CI 0.834-0.986)]. Models using T2WI masks showed robust performance on the internal dataset but lower performance on the external set. Both neuroradiologist and general radiologist showed improved performance with model output provided [AUC increased from 0.89 to 0.968 (p = 0.06) and from 0.78 to 0.965 (p = 0.007) respectively], the latter being statistically significant.

CONCLUSION

3D-CNNs showed robust performance for differentiating GB from BMs, with T1-CE TM, either alone or combined with FLAIR-PTR masks. Availability of model output significantly improved the accuracy of the general radiologist.

Balanced transformer: efficient classification of glioblastoma and primary central nervous system lymphoma

Objective.Primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) are malignant primary brain tumors with different biological characteristics. Great differences exist between the treatment strategies of PCNSL and GBM. Thus, accurately distinguishing between PCNSL and GBM before surgery is very important for guiding neurosurgery. At present, the spinal fluid of patients is commonly extracted to find tumor markers for diagnosis. However, this method not only causes secondary injury to patients, but also easily delays treatment. Although diagnosis using radiology images is non-invasive, the morphological features and texture features of the two in magnetic resonance imaging (MRI) are quite similar, making distinction with human eyes and image diagnosis very difficult. In order to solve the problem of insufficient number of samples and sample imbalance, we used data augmentation and balanced sample sampling methods. Conventional Transformer networks use patch segmentation operations to divide images into small patches, but the lack of communication between patches leads to unbalanced data layers.Approach.To address this problem, we propose a balanced patch embedding approach that extracts high-level semantic information by reducing the feature dimensionality and maintaining the geometric variation invariance of the features. This approach balances the interactions between the information and improves the representativeness of the data. To further address the imbalance problem, the balanced patch partition method is proposed to increase the receptive field by sampling the four corners of the sliding window and introducing a linear encoding component without increasing the computational effort, and designed a new balanced loss function.Main results.Benefiting from the overall balance design, we conducted an experiment using Balanced Transformer and obtained an accuracy of 99.89%, sensitivity of 99.74%, specificity of 99.73% and AUC of 99.19%, which is far higher than the previous results (accuracy of 89.6% ∼ 96.8%, sensitivity of 74.3% ∼ 91.3%, specificity of 88.9% ∼ 96.02% and AUC of 87.8% ∼ 94.9%).Significance.This study can accurately distinguish PCNSL and GBM before surgery. Because GBM is a common type of malignant tumor, the 1% improvement in accuracy has saved many patients and reduced treatment times considerably. Thus, it can provide doctors with a good basis for auxiliary diagnosis.

Modern preoperative imaging and functional mapping in patients with intracranial glioma

Magnetic resonance imaging (MRI) in therapy-naïve intracranial glioma is paramount for neuro-oncological diagnostics, and it provides images that are helpful for surgery planning and intraoperative guidance during tumor resection, including assessment of the involvement of functionally eloquent brain structures. This study reviews emerging MRI techniques to depict structural information, diffusion characteristics, perfusion alterations, and metabolism changes for advanced neuro-oncological imaging. In addition, it reflects current methods to map brain function close to a tumor, including functional MRI and navigated transcranial magnetic stimulation with derived function-based tractography of subcortical white matter pathways. We conclude that modern preoperative MRI in neuro-oncology offers a multitude of possibilities tailored to clinical needs, and advancements in scanner technology (e. g., parallel imaging for acceleration of acquisitions) make multi-sequence protocols increasingly feasible. Specifically, advanced MRI using a multi-sequence protocol enables noninvasive, image-based tumor grading and phenotyping in patients with glioma. Furthermore, the add-on use of preoperatively acquired MRI data in combination with functional mapping and tractography facilitates risk stratification and helps to avoid perioperative functional decline by providing individual information about the spatial location of functionally eloquent tissue in relation to the tumor mass. KEY POINTS::   · Advanced preoperative MRI allows for image-based tumor grading and phenotyping in glioma.. · Multi-sequence MRI protocols nowadays make it possible to assess various tumor characteristics (incl. perfusion, diffusion, and metabolism).. · Presurgical MRI in glioma is increasingly combined with functional mapping to identify and enclose individual functional areas.. · Advancements in scanner technology (e. g., parallel imaging) facilitate increasing application of dedicated multi-sequence imaging protocols.. CITATION FORMAT: · Sollmann N, Zhang H, Kloth C et al. Modern preoperative imaging and functional mapping in patients with intracranial glioma. Fortschr Röntgenstr 2023; 195: 989 - 1000.

Imaging Recommendations for the Diagnosis, Staging, and Management of Adult Brain Tumors

Neuroimaging plays a pivotal role in the clinical practice of brain tumors aiding in the diagnosis, genotype prediction, preoperative planning, and prognostication. The brain tumors most commonly seen in adults are extra-axial lesions like meningioma, intra-axial lesions like gliomas and lesions of the pituitary gland. Clinical features may be localizing like partial seizures, weakness, and sensory disturbances or nonspecific like a headache. On clinical suspicion of a brain tumor, the primary investigative workup should focus on imaging. Other investigations like fundoscopy and electroencephalography may be performed depending on the clinical presentation. Obtaining a tissue sample after identifying a brain tumor on imaging is crucial for confirming the diagnosis and planning further treatment. Tissue sample may be obtained by techniques such as stereotactic biopsy or upfront surgery. The magnetic resonance (MR) imaging protocol needs to be standardized and includes conventional sequences like T1-weighted (T1W) imaging with and without contrast, T2w imaging, fluid-attenuated axial inversion recovery, diffusion-weighted imaging (DWI), susceptibility-weighted imaging, and advanced imaging sequences like MR perfusion and MR spectroscopy. Various tumor characteristics in each of these sequences can help us narrow down the differential diagnosis and also predict the grade of the tumor. Multidisciplinary co-ordination is needed for proper management and care of brain tumor patients. Treatment protocols need to be adapted and individualized for each patient depending on the age, general condition of the patient, histopathological characteristics, and genotype of the tumor. Treatment options include surgery, radiotherapy, and chemotherapy. Imaging also plays a vital role in post-treatment follow-up. Sequences like DWI, MR perfusion, and MR spectroscopy are useful to distinguish post-treatment effects like radiation necrosis and pseudoprogression from true recurrence. Radiological reporting of brain tumor images should follow a structured format to include all the elements that could have an impact on the treatment decisions in patients.

Smart Visualization of Medical Images as a Tool in the Function of Education in Neuroradiology

The smart visualization of medical images (SVMI) model is based on multi-detector computed tomography (MDCT) data sets and can provide a clearer view of changes in the brain, such as tumors (expansive changes), bleeding, and ischemia on native imaging (i.e., a non-contrast MDCT scan). The new SVMI method provides a more precise representation of the brain image by hiding pixels that are not carrying information and rescaling and coloring the range of pixels essential for detecting and visualizing the disease. In addition, SVMI can be used to avoid the additional exposure of patients to ionizing radiation, which can lead to the occurrence of allergic reactions due to the contrast media administration. Results of the SVMI model were compared with the final diagnosis of the disease after additional diagnostics and confirmation by neuroradiologists, who are highly trained physicians with many years of experience. The application of the realized and presented SVMI model can optimize the engagement of material, medical, and human resources and has the potential for general application in medical training, education, and clinical research.

Contribution of advanced neuro-imaging (MR diffusion, perfusion and proton spectroscopy) in differentiation between low grade gliomas GII and MR morphologically similar non neoplastic lesions

Background

Non-neoplastic brain lesions can be misdiagnosed as low-grade gliomas. Conventional magnetic resonance (MR) imaging may be non-specific. Additional imaging modalities such as spectroscopy (MRS), perfusion and diffusion imaging aid in diagnosis of such lesions. However, contradictory and overlapping results are still present. Hence, our purpose was to evaluate the role of advanced neuro-imaging in differentiation between low-grade gliomas (WHO grade II) and MR morphologically similar non-neoplastic lesions and to prove which modality has the most accurate results in differentiation.

Results

All patients were classified into two main groups: patients with low-grade glioma (n = 12; mean age, 38.8 ± 16; 8 males) and patients with non-neoplastic lesions (n = 27; mean age, 36.6 ± 15; 19 males) based on the histopathological and clinical–radiological diagnosis. Using ROC curve analysis, a threshold value of 0.93 for rCBV (AUC = 0.875, PPV = 92%, NPV = 71.4%) and a threshold value of 2.5 for Cho/NAA (AUC = 0.829, PPV = 92%, NPV = 71.4%) had 85.2% sensitivity and 83.3% specificity for predicting neoplastic lesions. The area under the curve (AUC) of ROC analysis was good for relative cerebral blood volume (rCBV) and Cho/NAA ratios (> 0.80) and fair for Cho/Cr and NAA/Cr ratios (0.70–0.80). When the rCBV measurements were combined with MRS ratios, significant improvement was observed in the area under the curve (AUC) (0.969) with improved diagnostic accuracy (89.7%) and sensitivity (88.9%).

Conclusions

Evaluation of rCBV and metabolite ratios at MRS, particularly Cho/NAA ratio, may be helpful in differentiating low-grade gliomas from non-neoplastic lesions. The combination of dynamic susceptibility contrast (DSC) perfusion and MRS can significantly improve the diagnostic accuracy and can help avoiding the need for an invasive biopsy.

Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis

BACKGROUND AND PURPOSE

To investigate the diagnostic performance of fully automated radiomics-based models for multiclass classification of a single enhancing brain tumor among glioblastoma, central nervous system lymphoma, and metastasis.

MATERIALS AND METHODS

The training and test sets were comprised of 538 cases (300 glioblastomas, 73 lymphomas, and 165 metastases) and 169 cases (101 glioblastomas, 29 lymphomas, and 39 metastases), respectively. After fully automated segmentation, radiomic features were extracted. Three conventional machine learning classifiers, including least absolute shrinkage and selection operator (LASSO), adaptive boosting (Adaboost), and support vector machine with the linear kernel (SVC), combined with one of four feature selection methods, including forward sequential feature selection, F score, mutual information, and LASSO, were trained. Additionally, one ensemble classifier based on the three classifiers was used. The diagnostic performance of the optimized models was tested in the test set using the accuracy, F1-macro score, and the area under the receiver operating characteristic curve (AUCROC).

RESULTS

The best performance was achieved when the LASSO was used as a feature selection method. In the test set, the best performance was achieved by the ensemble classifier, showing an accuracy of 76.3% (95% CI, 70.0-82.7), a F1-macro score of 0.704, and an AUCROC of 0.878.

CONCLUSION

Our fully automated radiomics-based models for multiclass classification might be useful for differential diagnosis of a single enhancing brain tumor with a good diagnostic performance and generalizability.

Differentiation of Intracerebral Tumor Entities with Quantitative Contrast Attenuation and Iodine Mapping in Dual-Layer Computed Tomography

Purpose: To investigate if quantitative contrast enhancement and iodine mapping of common brain tumor (BT) entities may correctly differentiate between tumor etiologies in standardized stereotactic CT protocols. Material and Methods: A retrospective monocentric study of 139 consecutive standardized dual-layer dual-energy CT (dlDECT) scans conducted prior to the stereotactic needle biopsy of untreated primary brain tumor lesions. Attenuation of contrast-enhancing BT was derived from polyenergetic images as well as spectral iodine density maps (IDM) and their contrast-to-noise-ratios (CNR) were determined using ROI measures in contrast-enhancing BT and healthy contralateral white matter. The measures were correlated to histopathology regarding tumor entity, isocitrate dehydrogenase (IDH) and MGMT mutation status. Results: The cohort included 52 female and 76 male patients, mean age of 59.4 (±17.1) years. Brain lymphomas showed the highest attenuation (IDM CNR 3.28 ± 1,23), significantly higher than glioblastoma (2.37 ± 1.55, p < 0.005) and metastases (1.95 ± 1.14, p < 0.02), while the differences between glioblastomas and metastases were not significant. These strongly enhancing lesions differed from oligodendroglioma and astrocytoma (Grade II and III) that showed IDM CNR in the range of 1.22−1.27 (±0.45−0.82). Conventional attenuation measurements in DLCT data performed equally or slightly superior to iodine density measurements. Conclusion: Quantitative attenuation and iodine density measurements of contrast-enhancing brain tumors are feasible imaging biomarkers for the discrimination of cerebral tumor lesions but not specifically for single tumor entities. CNR based on simple HU measurements performed equally or slightly superior to iodine quantification.

Classifying primary central nervous system lymphoma from glioblastoma using deep learning and radiomics based machine learning approach - a systematic review and meta-analysis

Background

Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common in elderly yet difficult to differentiate on MRI. Their management and prognosis are quite different. Recent surge of interest in predictive analytics, using machine learning (ML) from radiomic features and deep learning (DL) for diagnosing, predicting response and prognosticating disease has evinced interest among radiologists and clinicians. The objective of this systematic review and meta-analysis was to evaluate the deep learning &amp; ML algorithms in classifying PCNSL from GBM.

Methods

The authors performed a systematic review of the literature from MEDLINE, EMBASE and the Cochrane central trials register for the search strategy in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML, DL, AI, GBM, PCNSL. All studies reporting on ML algorithms or DL that for differentiating PCNSL from GBM on MR imaging were included. These studies were further narrowed down to focus on works published between 2018 and 2021. Two researchers independently conducted the literature screening, database extraction and risk bias assessment. The extracted data was synthesised and analysed by forest plots. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity and balanced accuracy.

Results

Ten articles meeting the eligibility criteria were identified addressing use of ML and DL in training and validation classifiers to distinguish PCNSL from GBM on MR imaging. The total sample size was 1311 in the included studies. ML approach was used in 6 studies while DL in 4 studies. The lowest reported sensitivity was 80%, while the highest reported sensitivity was 99% in studies in which ML and DL was directly compared with the gold standard histopathology. The lowest reported specificity was 87% while the highest reported specificity was 100%. The highest reported balanced accuracy was 100% and the lowest was 84%.

Conclusions

Extensive search of the database revealed a limited number of studies that have applied ML or DL to differentiate PCNSL from GBM. Of the currently published studies, Both DL &amp; ML algorithms have demonstrated encouraging results and certainly have the potential to aid neurooncologists in taking preoperative decisions in the future leading to not only reduction in morbidities but also be cost effective.

High-grade glioma and solitary metastasis: differentiation by spectroscopy and advanced magnetic resonance techniques

Background

The differentiation by means of magnetic resonance between high-grade gliomas and intracranial solitary single metastasis is of the utmost importance since they condition both surgical and complementary treatment.

Results

Retrospective study that analyzes the parameters of advanced magnetic resonance imaging: spectroscopy, diffusion and perfusion, specifically focused on the differences in the coefficients of the metabolites Cho/Cr, Cho/NAA and NAA/Cr in peritumoral edema between high-grade gliomas and metastases. The data have been statistically analyzed using ROC (receiver operating characteristic) curves, and cutoff values were obtained.

A total of 79 patients with histologically analyzed tumors were analyzed: 49 high-grade gliomas (40 multiform glioblastomas and 9 anaplastic astrocytomas) and 30 metastases. A statistically significant mean difference was obtained in the three metabolite ratios. The area under the curve for the Cho/NAA ratio was 0.958 (CI: 0.903–1), for Cho/Cr 0.922 (CI: 0.859–0.985) and for NAA/Cr 0.163 (CI: 0.068–0.258; p < 0.001). The cutoff values were 1.115 for Cho/NAA (sensitivity 93.87%, specificity 93.33%, global precision 93.67%); 1.18 for the Cho/Cr ratio (sensitivity 89.79%, specificity 93.33% and precision 91.13%) and 1.155 for the NAA/Cr ratio (sensitivity 67.34%, specificity 93.33%, global precision 44.30%).

Conclusion

The results of the study support the premise that spectroscopy at the level of peritumoral edema is able to differentiate between high-grade gliomas and metastases by showing tumor infiltration in peritumoral edema.

Machine Learning and Deep Learning CT-Based Models for Predicting the Primary Central Nervous System Lymphoma and Glioma Types: A Multicenter Retrospective Study

Purpose and Background

Distinguishing primary central nervous system lymphoma (PCNSL) and glioma on computed tomography (CT) is an important task since treatment options differ vastly from the two diseases. This study aims to explore various machine learning and deep learning methods based on radiomic features extracted from CT scans and end-to-end convolutional neural network (CNN) model to predict PCNSL and glioma types and compare the performance of different models.

Methods

A total of 101 patients from five Chinese medical centers with pathologically confirmed PCNSL and glioma were analyzed retrospectively, including 50 PCNSL and 51 glioma. After manual segmentation of the region of interest (ROI) on CT scans, 293 radiomic features of each patient were extracted. The radiomic features were used as input, and then, we established six machine learning models and one deep learning model and three readers to identify the two types of tumors. We also established a 2D CNN model using raw CT scans as input. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were used to evaluate different models.

Results

The cohort was split into a training (70, 70% patients) and validation cohort (31,30% patients) according to the stratified sampling strategy. Among all models, the MLP performed best, with an accuracy of 0.886 and 0.903, sensitivity of 0.914 and 0.867, specificity of 0.857 and 0.937, and AUC of 0.957 and 0.908 in the training and validation cohorts, respectively, which was significantly higher than the three primary physician's diagnoses (ACCs ranged from 0.710 to 0.742, p &lt; 0.001 for all) and comparable with the senior radiologist (ACC 0.839, p = 0.988). Among all the machine learning models, the AUC ranged from 0.605 to 0.821 in the validation cohort. The end-to-end CNN model achieved an AUC of 0.839 and an ACC of 0.840 in the validation cohort, which had no significant difference in accuracy compared to the MLP model (p = 0.472) and the senior radiologist (p = 0.470).

Conclusion

The established PCNSL and glioma prediction model based on deep neural network methods from CT scans or radiomic features are feasible and provided high performance, which shows the potential to assist clinical decision-making.

Convolutional neural networks to predict brain tumor grades and Alzheimer’s disease with MR spectroscopic imaging data

Purpose

To evaluate the value of convolutional neural network (CNN) in the diagnosis of human brain tumor or Alzheimer’s disease by MR spectroscopic imaging (MRSI) and to compare its Matthews correlation coefficient (MCC) score against that of other machine learning methods and previous evaluation of the same data. We address two challenges: 1) limited number of cases in MRSI datasets and 2) interpretability of results in the form of relevant spectral regions.

Methods

A shallow CNN with only one hidden layer and an ad-hoc loss function was constructed involving two branches for processing spectral and image features of a brain voxel respectively. Each branch consists of a single convolutional hidden layer. The output of the two convolutional layers is merged and fed to a classification layer that outputs class predictions for the given brain voxel.

Results

Our CNN method separated glioma grades 3 and 4 and identified Alzheimer’s disease patients using MRSI and complementary MRI data with high MCC score (Area Under the Curve were 0.87 and 0.91 respectively). The results demonstrated superior effectiveness over other popular methods as Partial Least Squares or Support Vector Machines. Also, our method automatically identified the spectral regions most important in the diagnosis process and we show that these are in good agreement with existing biomarkers from the literature.

Conclusion

Shallow CNNs models integrating image and spectral features improved quantitative and exploration and diagnosis of brain diseases for research and clinical purposes. Software is available at https://bitbucket.org/TeslaH2O/cnn_mrsi.

Study and analysis of different segmentation methods for brain tumor MRI application

Medical Resonance Imaging (MRI) is one of the preferred imaging methods for brain tumor diagnosis and getting detailed information on tumor type, location, size, identification, and detection. Segmentation divides an image into multiple segments and describes the separation of the suspicious region from pre-processed MRI images to make the simpler image that is more meaningful and easier to examine. There are many segmentation methods, embedded with detection devices, and the response of each method is different. The study article focuses on comparing the performance of several image segmentation algorithms for brain tumor diagnosis, such as Otsu's, watershed, level set, K-means, HAAR Discrete Wavelet Transform (DWT), and Convolutional Neural Network (CNN). All of the techniques are simulated in MATLAB using online images from the Brain Tumor Image Segmentation Benchmark (BRATS) dataset-2018. The performance of these methods is analyzed based on response time and measures such as recall, precision, F-measures, and accuracy. The measured accuracy of Otsu's, watershed, level set, K-means, DWT, and CNN methods is 71.42%, 78.26%, 80.45%, 84.34%, 86.95%, and 91.39 respectively. The response time of CNN is 2.519 s in the MATLAB simulation environment for the designed algorithm. The novelty of the work is that CNN has been proven the best algorithm in comparison to all other methods for brain tumor image segmentation. The simulated and estimated parameters provide the direction to researchers to choose the specific algorithm for embedded hardware solutions and develop the optimal machine-learning models, as the industries are looking for the optimal solutions of CNN and deep learning-based hardware models for the brain tumor.

A Deep Learning Model for Preoperative Differentiation of Glioblastoma, Brain Metastasis and Primary Central Nervous System Lymphoma: A Pilot Study

Background

Neuroimaging differentiation of glioblastoma, primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (BM) remains challenging in specific cases showing similar appearances or atypical features. Overall, advanced MRI protocols have high diagnostic reliability, but their limited worldwide availability, coupled with the overlapping of specific neuroimaging features among tumor subgroups, represent significant drawbacks and entail disparities in the planning and management of these oncological patients.

Objective

To evaluate the classification performance metrics of a deep learning algorithm trained on T1-weighted gadolinium-enhanced (T1Gd) MRI scans of glioblastomas, atypical PCNSLs and BMs.

Materials and Methods

We enrolled 121 patients (glioblastoma: n=47; PCNSL: n=37; BM: n=37) who had undergone preoperative T1Gd-MRI and histopathological confirmation. Each lesion was segmented, and all ROIs were exported in a DICOM dataset. The patient cohort was then split in a training and hold-out test sets following a 70/30 ratio. A Resnet101 model, a deep neural network (DNN), was trained on the training set and validated on the hold-out test set to differentiate glioblastomas, PCNSLs and BMs on T1Gd-MRI scans.

Results

The DNN achieved optimal classification performance in distinguishing PCNSLs (AUC: 0.98; 95%CI: 0.95 - 1.00) and glioblastomas (AUC: 0.90; 95%CI: 0.81 - 0.97) and moderate ability in differentiating BMs (AUC: 0.81; 95%CI: 0.70 - 0.95). This performance may allow clinicians to correctly identify patients eligible for lesion biopsy or surgical resection.

Conclusion

We trained and internally validated a deep learning model able to reliably differentiate ambiguous cases of PCNSLs, glioblastoma and BMs by means of T1Gd-MRI. The proposed predictive model may provide a low-cost, easily-accessible and high-speed decision-making support for eligibility to diagnostic brain biopsy or maximal tumor resection in atypical cases.

Radiographic markers of breast cancer brain metastases: relation to clinical characteristics and postoperative outcome

Objective

Occurrence of brain metastases BM is associated with poor prognosis in patients with breast cancer (BC). Magnetic resonance imaging (MRI) is the standard of care in the diagnosis of BM and determines further treatment strategy. The aim of the present study was to evaluate the association between the radiographic markers of BCBM on MRI with other patients’ characteristics and overall survival (OS).

Methods

We included 88 female patients who underwent BCBM surgery in our institution from 2008 to 2019. Data on demographic, clinical, and histopathological characteristics of the patients and postoperative survival were collected from the electronic health records. Radiographic features of BM were assessed upon the preoperative MRI. Univariable and multivariable analyses were performed.

Results

The median OS was 17 months. Of all evaluated radiographic markers of BCBM, only the presence of necrosis was independently associated with OS (14.5 vs 22.5 months, p = 0.027). In turn, intra-tumoral necrosis was more often in individuals with shorter time interval between BC and BM diagnosis (< 3 years, p = 0.035) and preoperative leukocytosis (p = 0.022). Moreover, dural affection of BM was more common in individuals with positive human epidermal growth factor receptor 2 status (p = 0.015) and supratentorial BM location (p = 0.024).

Conclusion

Intra-tumoral necrosis demonstrated significant association with OS after BM surgery in patients with BC. The radiographic pattern of BM on the preoperative MRI depends on certain tumor and clinical characteristics of patients.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00701-021-05026-4.

Evolving Role and Translation of Radiomics and Radiogenomics in Adult and Pediatric Neuro-Oncology

Exponential technologic advancements in imaging, high-performance computing, and artificial intelligence, in addition to increasing access to vast amounts of diverse data, have revolutionized the role of imaging in medicine. Radiomics is defined as a high-throughput feature-extraction method that unlocks microscale quantitative data hidden within standard-of-care medical imaging. Radiogenomics is defined as the linkage between imaging and genomics information. Multiple radiomics and radiogenomics studies performed on conventional and advanced neuro-oncology image modalities show that they have the potential to differentiate pseudoprogression from true progression, classify tumor subgroups, and predict recurrence, survival, and mutation status with high accuracy. In this article, we outline the technical steps involved in radiomics and radiogenomics analyses with the use of artificial intelligence methods and review current applications in adult and pediatric neuro-oncology.

Filtration-Histogram Based Magnetic Resonance Texture Analysis (MRTA) for the Distinction of Primary Central Nervous System Lymphoma and Glioblastoma

Primary central nervous system lymphoma (PCNSL) has variable imaging appearances, which overlap with those of glioblastoma (GBM), thereby necessitating invasive tissue diagnosis. We aimed to investigate whether a rapid filtration histogram analysis of clinical MRI data supports the distinction of PCNSL from GBM. Ninety tumours (PCNSL n = 48, GBM n = 42) were analysed using pre-treatment MRI sequences (T₁-weighted contrast-enhanced (T₁CE), T₂-weighted (T₂), and apparent diffusion coefficient maps (ADC)). The segmentations were completed with proprietary texture analysis software (TexRAD version 3.3). Filtered (five filter sizes SSF = 2-6 mm) and unfiltered (SSF = 0) histogram parameters were compared using Mann-Whitney U non-parametric testing, with receiver operating characteristic (ROC) derived area under the curve (AUC) analysis for significant results. Across all (n = 90) tumours, the optimal algorithm performance was achieved using an unfiltered ADC mean and the mean of positive pixels (MPP), with a sensitivity of 83.8%, specificity of 8.9%, and AUC of 0.88. For subgroup analysis with >1/3 necrosis masses, ADC permitted the identification of PCNSL with a sensitivity of 96.9% and specificity of 100%. For T₁CE-derived regions, the distinction was less accurate, with a sensitivity of 71.4%, specificity of 77.1%, and AUC of 0.779. A role may exist for cross-sectional texture analysis without complex machine learning models to differentiate PCNSL from GBM. ADC appears the most suitable sequence, especially for necrotic lesion distinction.

Brain Tumor Detection and Classification on MR Images by a Deep Wavelet Auto-Encoder Model

The process of diagnosing brain tumors is very complicated for many reasons, including the brain's synaptic structure, size, and shape. Machine learning techniques are employed to help doctors to detect brain tumor and support their decisions. In recent years, deep learning techniques have made a great achievement in medical image analysis. This paper proposed a deep wavelet autoencoder model named "DWAE model", employed to divide input data slice as a tumor (abnormal) or no tumor (normal). This article used a high pass filter to show the heterogeneity of the MRI images and their integration with the input images. A high median filter was utilized to merge slices. We improved the output slices' quality through highlight edges and smoothened input MR brain images. Then, we applied the seed growing method based on 4-connected since the thresholding cluster equal pixels with input MR data. The segmented MR image slices provide two two-layer using the proposed deep wavelet auto-encoder model. We then used 200 hidden units in the first layer and 400 hidden units in the second layer. The softmax layer testing and training are performed for the identification of the MR image normal and abnormal. The contribution of the deep wavelet auto-encoder model is in the analysis of pixel pattern of MR brain image and the ability to detect and classify the tumor with high accuracy, short time, and low loss validation. To train and test the overall performance of the proposed model, we utilized 2500 MR brain images from BRATS2012, BRATS2013, BRATS2014, BRATS2015, 2015 challenge, and ISLES, which consists of normal and abnormal images. The experiments results show that the proposed model achieved an accuracy of 99.3%, loss validation of 0.1, low FPR and FNR values. This result demonstrates that the proposed DWAE model can facilitate the automatic detection of brain tumors.

Accuracy of apparent diffusion coefficient in differentiation of glioblastoma from metastasis

BACKGROUND

Brain metastasis and glioblastoma multiforme are two of the most common malignant brain neoplasms. There are many difficulties in distinguishing these diseases from each other.

PURPOSE

The purpose of this study was to determine whether the mean apparent diffusion coefficient and absolute standard deviation derived from apparent diffusion coefficient measurements can be used to differentiate glioblastoma multiforme from brain metastasis based on cellularity levels.

MATERIAL AND METHODS

Magnetic resonance images of 34 patients with histologically verified brain tumors were evaluated retrospectively. Apparent diffusion coefficient and standard deviation values were measured in the enhancing tumor, peritumoral region, and contralateral healthy white matter. Then, to determine whether there was a statistical difference between brain metastasis and glioblastoma multiforme, we analyzed different variables between the two groups.

RESULTS

Neither mean apparent diffusion coefficient values and ratios nor standard deviation values and ratios were significantly different between glioblastoma multiforme and brain metastasis. Receiver operating characteristic curve analysis of the logistic model with backward stepwise feature selection yielded an area under the curve of 0.77, a specificity of 84%, a sensitivity of 67%, a positive predictive value of 83.33%, and a negative predictive value of 78.26% for distinguishing between glioblastoma multiforme and brain metastasis. The absolute standard deviation and standard deviation ratios were significantly higher in the peritumoral edema compared to the tumor region in each case.

CONCLUSION

Apparent diffusion coefficient values and ratios, as well as standard deviation values and ratios in peritumoral edema, cannot be used to differentiate edema with infiltration of tumor cells from vasogenic edema. However, standard deviation values could successfully characterize areas of peritumoral edema from the tumoral region in each case.

Differentiation between glioblastoma and primary CNS lymphoma: application of DCE-MRI parameters based on arterial input function obtained from DSC-MRI

OBJECTIVE

This study aimed to evaluate whether arterial input functions (AIFs) obtained from dynamic susceptibility contrast (DSC)-MRI (AIF_DSC) improve the reliability and diagnostic accuracy of dynamic contrast-enhanced (DCE)-derived pharmacokinetic (PK) parameters for differentiating glioblastoma from primary CNS lymphoma (PCNSL) compared with AIFs derived from DCE-MRI (AIF_DCE).

METHODS

This retrospective study included 172 patients with glioblastoma (n = 147) and PCNSL (n = 25). All patients had undergone preoperative DSC- and DCE-MRI. The volume transfer constant (K^trans), volume of the vascular plasma space (v_p), and volume of the extravascular extracellular space (v_e) were acquired using AIF_DSC and AIF_DCE. The relative cerebral blood volume (rCBV) was obtained from DSC-MRI. Intraclass correlation coefficients (ICC) and ROC curves were used to assess the reliability and diagnostic accuracy of individual parameters.

RESULTS

The mean K^trans, v_p, and v_e values revealed better ICCs with AIF_DSC than with AIF_DCE (K^trans, 0.911 vs 0.355; v_p, 0.766 vs 0.503; v_e, 0.758 vs 0.657, respectively). For differentiating all glioblastomas from PCNSL, the mean rCBV (AUC = 0.856) was more accurate than the AIF_DSC-driven mean K^trans, which had the largest AUC (0.711) among the DCE-derived parameters (p = 0.02). However, for glioblastomas with low rCBV (≤ 75th percentile of PCNSL; n = 30), the AIF_DSC-driven mean K^trans and v_p were more accurate than rCBV (AUC: K^trans, 0.807 vs rCBV, 0.515, p = 0.004; v_p, 0.715 vs rCBV, p = 0.045).

CONCLUSION

DCE-derived PK parameters using the AIF_DSC showed improved reliability and diagnostic accuracy for differentiating glioblastoma with low rCBV from PCNSL.

KEY POINTS

• An accurate differential diagnosis of glioblastoma and PCNSL is crucial because of different therapeutic strategies. • In contrast to the rCBV from DSC-MRI, another perfusion imaging technique, the DCE parameters for the differential diagnosis have been limited because of the low reliability of AIFs from DCE-MRI. • When we analyzed DCE-MRI data using AIFs from DSC-MRI (AIF_DSC), AIF_DSC-driven DCE parameters showed improved reliability and better diagnostic accuracy than rCBV for differentiating glioblastoma with low rCBV from PCNSL.

Feasibility and Therapeutic Potential of Peptide Receptor Radionuclide Therapy for High-Grade Gliomas

PURPOSE

This pilot study tested the principle that 177Lu-DOTATATE may be applied to patients with high-grade gliomas (HGGs) that are either inoperable or refractory to the standard conventional treatments and also assessed whether this approach could be a viable therapeutic plan in this dilemma.

METHODS

In this prospective study, 16 subjects experiencing HGGs that were either inoperable or refractory to the standard conventional treatments were included. All the patients checked for somatostatin receptor expression on the tumors. The patients were treated with 1 to 4 cycles of IV 177Lu-DOTATATE. The primary end point was radiological response after peptide receptor radionuclide therapy, and the secondary end point was improved quality of life using Karnofsky Performance Score and Eastern Cooperative Oncology Group score.

RESULTS

In total, 16 subjects (10 males and 6 females) with a mean age of 55.68 ± 13.17 years (26-73 years) participated in the study. Of them, 8 patients were new HGG cases, and 8 patients had recurrent tumors. The participants' responses to treatments were complete remission in 12.5% of (n = 2), partial remission in 31.25% (n = 5), disease stability in 18.7% (n = 3), and disease progression in 37.5% (n = 6). In total, pretreatment and posttreatment Karnofsky Performance Score and Eastern Cooperative Oncology Group scores did not improved (P > 0.05). The patients were followed up from 1 month to 26 months (median, 3 months).

CONCLUSIONS

This preliminary result suggests that peptide receptor radionuclide therapy using 177Lu-DOTATATE may be associated with positive effects in patients with HGGs (grade III-IV). However, this approach should be evaluated in a more homogeneous group of patients with more favorable performance status.

The Diagnostic Value of Apparent Diffusion Coefficient and Proton Magnetic Resonance Spectroscopy in the Grading of Pediatric Gliomas

The aims of this retrospective study were to assess the value of the quantitative analysis of apparent diffusion coefficient (ADC) and proton magnetic resonance spectroscopy (¹H-MRS) metabolites in differentiating grades of pediatric gliomas.

Clinical Review of Computed Tomography and MR Perfusion Imaging in Neuro-Oncology

Neuroimaging plays an essential role in the initial diagnosis and continued surveillance of intracranial neoplasms. The advent of perfusion techniques with computed tomography and MR imaging have proven useful in neuro-oncology, offering enhanced approaches for tumor grading, guiding stereotactic biopsies, and monitoring treatment efficacy. Perfusion imaging can help to identify treatment-related processes, such as radiation necrosis, pseudoprogression, and pseudoregression, and can help to inform treatment-related decision making. Perfusion imaging is useful to differentiate between tumor types and between tumor and nonneoplastic conditions. This article reviews the clinical relevance and implications of perfusion imaging in neuro-oncology and highlights promising perfusion biomarkers.

Deep Learning for Automatic Differential Diagnosis of Primary Central Nervous System Lymphoma and Glioblastoma: Multi-Parametric Magnetic Resonance Imaging Based Convolutional Neural Network Model

BACKGROUND

Differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) is useful to guide treatment strategies.

PURPOSE

To investigate the use of a convolutional neural network (CNN) model for differentiation of PCNSL and GBM without tumor delineation.

STUDY TYPE

Retrospective.

POPULATION

A total of 289 patients with PCNSL (136) or GBM (153) were included, the average age of the cohort was 54 years, and there were 173 men and 116 women.

FIELD STRENGTH/SEQUENCE

3.0 T Axial contrast-enhanced T₁ -weighted spin-echo inversion recovery sequence (CE-T₁ WI), T₂ -weighted fluid-attenuation inversion recovery sequence (FLAIR), and diffusion weighted imaging (DWI, b = 0 second/mm² , 1000 seconds/mm² ).

ASSESSMENT

A single-parametric CNN model was built using CE-T₁ WI, FLAIR, and the apparent diffusion coefficient (ADC) map derived from DWI, respectively. A decision-level fusion based multi-parametric CNN model (DF-CNN) was built by combining the predictions of single-parametric CNN models through logistic regression. An image-level fusion based multi-parametric CNN model (IF-CNN) was built using the integrated multi-parametric MR images. The radiomics models were developed. The diagnoses by three radiologists with 6 years (junior radiologist Y.Y.), 11 years (intermediate-level radiologist Y.T.), and 21 years (senior radiologist Y.L.) of experience were obtained.

STATISTICAL ANALYSIS

The 5-fold cross validation was used for model evaluation. The Pearson's chi-squared test was used to compare the accuracies. U-test and Fisher's exact test were used to compare clinical characteristics.

RESULTS

The CE-T₁ WI, FLAIR, and ADC based single-parametric CNN model had accuracy of 0.884, 0.782, and 0.700, respectively. The DF-CNN model had an accuracy of 0.899 which was higher than the IF-CNN model (0.830, P = 0.021), but had no significant difference in accuracy compared to the radiomics model (0.865, P = 0.255), and the senior radiologist (0.906, P = 0.886).

DATA CONCLUSION

A CNN model can differentiate PCNSL from GBM without tumor delineation, and comparable to the radiomics models and radiologists.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Inflow-based vascular-space-occupancy (iVASO) might potentially predict IDH mutation status and tumor grade in diffuse cerebral gliomas

PURPOSE

The aim of the study is to assess the diagnostic performance of inflow-based vascular-space-occupancy (iVASO) MR imaging for differentiating glioblastomas (grade IV, GBM) and lower-grade diffuse gliomas (grade II and III, LGG) and its potential to predict IDH mutation status.

METHODS

One hundred and two patients with diffuse cerebral glioma (56 males; median age, 43.5 years) underwent iVASO and dynamic susceptibility contrast (DSC) MR imaging. The iVASO-derived arteriolar cerebral blood volume (CBVa), relative CBVa (rCBVa), and the DSC-derived relative cerebral blood volume (rCBV) were obtained, and these measurements were compared between the GBM group (n = 43) and the LGG group (n = 59) and between the IDH-mutation group (n = 54) and the IDH-wild group (n = 48).

RESULTS

Significant correlation was observed between rCBV and CBVa (P < 0.001) or rCBVa (P < 0.001). Both CBVa (P < 0.001) and rCBVa (P < 0.001) were higher in the GBM group. Both CBVa (P < 0.001) and rCBVa (P < 0.001) were lower in the IDH-mutation group compared to the IDH-wild group. Receiver operating characteristic analyses showed the area under curve (AUC) of 0.95 with CBVa and 0.97 with rCBVa in differentiating GBM from LGG. The AUCs were 0.82 and 0.85 for CBVa and rCBVa in predicting IDH gene status, respectively, which were lower than that of rCBV (AUC = 0.90). Combined rCBV and rCBVa significantly improved the diagnostic performance (AUC = 0.95).

CONCLUSIONS

iVASO MR imaging has the potential to predict IDH mutation and grade in glioma.

High 18F-FDOPA PET Uptake in Primary Central Nervous System Lymphoma

We present a 42-year-old woman with primary central nervous system lymphoma (PCNSL) and strong F-FDOPA PET uptake. F-FDOPA PET has high diagnostic accuracy in gliomas and brain metastases. The L-type amino acid transporter 1, targeted by F-FDOPA and C-MET PET, is a cell-type transporter usually upregulated in malignant tumors, including PCNSL. In this line, strong uptake was already shown with C-MET in PCNSL. We report the same findings with F-FDOPA. Consequently, PCNSL is a possible differential neoplastic diagnosis of F-FDOPA uptake among neoplastic lesions.

Combined application of MRS and DWI can effectively predict cell proliferation and assess the grade of glioma: A prospective study

In order to assess combined application of MRS and DWI for prediction cell proliferation and grade diagnosis of glioma, We prospectively collected the Cho/Cr, Cho/NAA, Cr/NAA of MRS and tumor parenchyma ADC (ADC_T), contralateral mirror brain tissue ADC (ADC_H), rADC (rADC = ADC_T/ADC_H). According to postoperative pathology, the patients were divided into two groups: LGG group and HGG group, compared differences of age, gender, Ki67, MRS, DWI between two groups. Next, we analyzed the correlation between MRS, DWI and Ki67. On this basis, the sensitivity and specificity of MRS, DWI and MRS combined with DWI (MRS + DWI) in diagnosis of glioma grade were evaluated. The differences of Ki67, Cho/Cr, Cho/NAA, Cr/NAA, ADC_T, rADC between LGG group and HGG group were statistically significant (p = 0.000, 0.000, 0.000, 0.008, 0.000, and 0.000 respectively). From ROC curve, area under the curve (AUC), sensitivity and specificity of Cho/Cr, Cho/NAA, Cr/NAA, ADC_T, rADC, PRE (MRS + DWI) were (0.901, 86.7%, 85.7%), (0.876, 80.0%, 82.1%), (0.704, 63.3%, 71.4%), (0.862, 82.1%, 83.3%), (0.820, 75.0%, 76.7%), (0.920, 86.7%, 89.3%), respectively. Fisher's linear discriminant functions results suggest: Y₁ = -20.447 + 3.46•X₁ + 17.141•X₂ (LGG), Y₂ = -19.415 + 4.828•X₁ + 14.543•X₂ (HGG). Our study suggested that MRS and DWI can effectively predict cell proliferation preoperative. MRS combined with DWI can further improve sensitivity and specificity in assessing the grade of glioma.

Magnetic resonance spectroscopy in pediatric brain tumors: how to make a more confident diagnosis

Background

Non-invasive diagnosis of pediatric brain tumors can be challenging due to diverse tumor pathologies and similar imaging appearances. Magnetic resonance spectroscopy (MRS), when combined with high spatial resolution anatomic imaging obtained with conventional magnetic resonance imaging (MRI), provides metabolic information within the lesion as well as the surrounding tissue. The differentiation of neoplastic from non-neoplastic lesions and low-grade from high-grade neoplasms is essential for determining the choice of treatment and the best treatment plan. We aimed to measure specific metabolic ratios and evaluate metabolic profiles of various lesions by MRS to assist in making a more confident diagnosis.

Results

The choline/creatine (Cho/Cr), choline/N-acetylaspartate (Cho/NAA), and Cho/NAA+Cr ratios all had statistically significant values for the differentiation between neoplastic and non-neoplastic lesions at cutoffs 1.8, 2, and 0.8 respectively. The Cho/NAA, Cho/Cr, Cho/NAA+Cr, and myo-inositol/creatine (mI/Cr) ratios all had statistically significant values for the differentiation of high-grade from low-grade neoplasms at cutoffs 3.3, 3.5, 1.3, and 1.5 respectively. The presence of a lipid lactate peak was only significant for differentiating high-grade from low-grade neoplasms. Medulloblastomas, diffuse pontine gliomas, and choroid plexus carcinoma all showed characteristic metabolic profiles on MRS. Metastasis showed lower Cho/NAA and Cho/Cr ratios outside the tumor margin than high-grade neoplasms.

Conclusion

The use of certain metabolite ratios with high sensitivity and specificity to distinguish neoplastic from non-neoplastic lesions and low-grade from high-grade neoplasms while assessing the metabolic profile of the lesion aids in the non-invasive diagnosis of pediatric brain tumors. MRS facilitates earlier treatment planning by determining tumor spatial extent and predicting tumor behavior with potential to solve sampling problems of inaccessible and heterogenous lesions as well as unnecessary sampling of benign lesions.

Comparison of Radiomics-Based Machine-Learning Classifiers in Diagnosis of Glioblastoma From Primary Central Nervous System Lymphoma

Purpose: The purpose of the current study was to evaluate the ability of magnetic resonance (MR) radiomics-based machine-learning algorithms in differentiating glioblastoma (GBM) from primary central nervous system lymphoma (PCNSL).

Method: One-hundred and thirty-eight patients were enrolled in this study. Radiomics features were extracted from contrast-enhanced MR images, and the machine-learning models were established using five selection methods (distance correlation, random forest, least absolute shrinkage and selection operator (LASSO), eXtreme gradient boosting (Xgboost), and Gradient Boosting Decision Tree) and three radiomics-based machine-learning classifiers [linear discriminant analysis (LDA), support vector machine (SVM), and logistic regression (LR)]. Sensitivity, specificity, accuracy, and areas under curves (AUC) of models were calculated, with which the performances of classifiers were evaluated and compared with each other.

Result: Brilliant discriminative performance would be observed among all classifiers when combined with the suitable selection method. For LDA-based models, the optimal one was Distance Correlation + LDA with AUC of 0.978. For SVM-based models, Distance Correlation + SVM was the one with highest AUC of 0.959, while for LR-based models, the highest AUC was 0.966 established with LASSO + LR.

Conclusion: Radiomics-based machine-learning algorithms potentially have promising performances in differentiating GBM from PCNSL.

Differentiating glioblastoma multiforme from cerebral lymphoma: application of advanced texture analysis of quantitative apparent diffusion coefficients

PURPOSE

The purpose of this study was to differentiate glioblastoma multiforme from primary central nervous system lymphoma using the customised first and second-order histogram features derived from apparent diffusion coefficients.Methods and materials: A total of 82 patients (57 with glioblastoma multiforme and 25 with primary central nervous system lymphoma) were included in this study. The axial T1 post-contrast and fluid-attenuated inversion recovery magnetic resonance images were used to delineate regions of interest for the tumour and peritumoral oedema. The regions of interest were then co-registered with the apparent diffusion coefficient maps, and the first and second-order histogram features were extracted and compared between glioblastoma multiforme and primary central nervous system lymphoma groups. Receiver operating characteristic curve analysis was performed to calculate a cut-off value and its sensitivity and specificity to differentiate glioblastoma multiforme from primary central nervous system lymphoma.

RESULTS

Based on the tumour regions of interest, apparent diffusion coefficient mean, maximum, median, uniformity and entropy were higher in the glioblastoma multiforme group than the primary central nervous system lymphoma group (P ≤ 0.001). The most sensitive first and second-order histogram feature to differentiate glioblastoma multiforme from primary central nervous system lymphoma was the maximum of 2.026 or less (95% confidence interval (CI) 75.1-99.9%), and the most specific first and second-order histogram feature was smoothness of 1.28 or greater (84.0% CI 70.9-92.8%). Based on the oedema regions of interest, most of the first and second-order histogram features were higher in the glioblastoma multiforme group compared to the primary central nervous system lymphoma group (P ≤ 0.015). The most sensitive first and second-order histogram feature to differentiate glioblastoma multiforme from primary central nervous system lymphoma was the 25th percentile of 0.675 or less (100% CI 83.2-100%) and the most specific first and second-order histogram feature was the median of 1.28 or less (85.9% CI 66.3-95.8%).

CONCLUSIONS

Texture analysis using first and second-order histogram features derived from apparent diffusion coefficient maps may be helpful in differentiating glioblastoma multiforme from primary central nervous system lymphoma.

The Fluctuations of Blood Oxygen Level-Dependent Signals as a Method of Brain Tumor Characterization: A Preliminary Report

OBJECTIVE

In this study we present the nature and characteristic of the fluctuation of blood oxygen level-dependent (BOLD) signals measured from brain tumors.

METHODS

Supratentorial astrocytomas, which were neither operated nor previously managed with chemotherapy or radiotherapy, were segmented, and the time series of the BOLD signal fluctuations were extracted. The mean (across patients) power spectra were plotted for the different World Health Organization tumor grades. One-way analysis of variance (ANOVA) was performed to identify significant differences between the power spectra of different tumor grades. Results were considered significant at P < 0.05.

RESULTS

A total of 58 patients were included in the study. This group of patients included 1 patient with grade I glioma; 15 with grade II; 12 with grade III; and 30 with grade IV. The power spectra of the tumor time series were individually inspected, and all tumors exhibited high peaks at the lower frequency signals, but these were more pronounced in high-grade tumors. ANOVA showed a significant difference in power spectra between groups (P = 0.000). Post hoc analysis with Bonferroni correction showed a significant difference between grade II and grade III (P = 0.012) and grade IV (P = 0.000). There was no significant power spectra difference between grade III and IV tumors (P = 1).

CONCLUSIONS

The power spectra of BOLD signals from tumor tissue showed fluctuations in the low-frequency signals and were significantly correlated with tumor grade. These signals could have a misleading effect when analyzing resting state functional magnetic resonance imaging and could be also viewed as a potential method of tumor characterization.

Anatomical relationships between medullary veins and three types of deep-seated malignant brain tumors as detected by susceptibility-weighted imaging

BACKGROUND

Deep-seated brain tumors can be difficult to differentiate. Three tumor types (primary central nervous system lymphoma [PCNSL], high-grade glioma, and metastatic brain tumors), identified by susceptibility-weighted imaging, have different relationships with small medullary veins, and these relationships can be used to enhance diagnostic accuracy.

METHODS

Records of patients with pathology confirmed malignant brain tumors who received susceptibility-weighted imaging between 2009 and 2015 were reviewed. A total of 29 patients with deep-seated malignant brain tumors in the territory of small medullary veins were enrolled in this study. The sensitivity, specificity, and diagnostic accuracy of medullary vein blockage (MVB), defined as a small medullary vein terminating at the margin of the tumor, for indicating malignant brain tumors were analyzed.

RESULTS

Of 11 patients with PCNSLs, 5 with high-grade gliomas, and 13 with metastases, only the latter presented MVBs. The sensitivity, specificity, and accuracy of using MVBs for diagnosing metastatic tumors were 76.9%, 100%, and 89.7%, respectively.

CONCLUSION

An MVB is an accurate sign for differentiating metastatic brain tumors from two other common malignancies and thus provides a useful tool for preoperative planning.

Endogenous Chemical Exchange Saturation Transfer MRI for the Diagnosis and Therapy Response Assessment of Brain Tumors: A Systematic Review

Purpose

To generate a narrative synthesis of published data on the use of endogenous chemical exchange saturation transfer (CEST) MRI in brain tumors.

Materials and Methods

A systematic database search (PubMed, Ovid Embase, Cochrane Library) was used to collate eligible studies. Two researchers independently screened publications according to predefined exclusion and inclusion criteria, followed by comprehensive data extraction. All included studies were subjected to a bias risk assessment using the Quality Assessment of Diagnostic Accuracy Studies tool.

Results

The electronic database search identified 430 studies, of which 36 fulfilled the inclusion criteria. The final selection of included studies was categorized into five groups as follows: grading gliomas, 19 studies (area under the receiver operating characteristic curve [AUC], 0.500-1.000); predicting molecular subtypes of gliomas, five studies (AUC, 0.610-0.920); distinction of different brain tumor types, seven studies (AUC, 0.707-0.905); therapy response assessment, three studies (AUC not given); and differentiating recurrence from treatment-related changes, five studies (AUC, 0.880-0.980). A high bias risk was observed in a substantial proportion of studies.

Conclusion

Endogenous CEST MRI offers valuable, potentially unique information in brain tumors, but its diagnostic accuracy remains incompletely known. Further research is required to assess the method's role in support of molecular genetic diagnosis, to investigate its use in the posttreatment phase, and to compare techniques with a view to standardization.Keywords: Brain/Brain Stem, MR-Imaging, Neuro-OncologySupplemental material is available for this article.© RSNA, 2020.

Brain Tumor Detection by Using Stacked Autoencoders in Deep Learning

Brain tumor detection depicts a tough job because of its shape, size and appearance variations. In this manuscript, a deep learning model is deployed to predict input slices as a tumor (unhealthy)/non-tumor (healthy). This manuscript employs a high pass filter image to prominent the inhomogeneities field effect of the MR slices and fused with the input slices. Moreover, the median filter is applied to the fused slices. The resultant slices quality is improved with smoothen and highlighted edges of the input slices. After that, based on these slices' intensity, a 4-connected seed growing algorithm is applied, where optimal threshold clusters the similar pixels from the input slices. The segmented slices are then supplied to the fine-tuned two layers proposed stacked sparse autoencoder (SSAE) model. The hyperparameters of the model are selected after extensive experiments. At the first layer, 200 hidden units and at the second layer 400 hidden units are utilized. The testing is performed on the softmax layer for the prediction of the images having tumors and no tumors. The suggested model is trained and checked on BRATS datasets i.e., 2012(challenge and synthetic), 2013, and 2013 Leaderboard, 2014, and 2015 datasets. The presented model is evaluated with a number of performance metrics which demonstrates the improved performance.

A Mistaken Diagnosis of Secondary Glioblastoma as Parasitosis

Background: Glioblastoma is a malignant brain tumor with poor prognosis requiring early diagnosis. Secondary glioblastoma refers to cases that progressed from low-grade glioma. Evidence shows that timely resection correlates with increased survival.

Case presentation: We describe a case of a patient with secondary glioblastoma who was mistakenly diagnosed with Angiostrongylus cantonensis infection until 7 years after disease onset. The patient presented with non-specific clinical manifestations at disease onset. A conventional magnetic resonance imaging (MRI) in the primary survey provided insufficient information, and thus failed to identify the malignancy. During follow-up, unfortunately, clinicians were misled by the patient's raw food diet, a positive serum parasite antibody and a result of low glucose metabolism on Fluorodeoxyglucose-positron emission tomography-computed tomography (FDG-PET-CT). The patient was diagnosed with parasitosis. However, his condition kept getting worse under antiparasitic treatment. Preoperative magnetic resonance spectroscopy (MRS) and diffusion tensor imaging (DTI) failed to reverse the mistaken impression. Final diagnosis was confirmed until intraoperative and postoperative pathological findings indicated glioblastoma.

Conclusion: We ascribe the incorrect diagnosis to insufficient understanding on imaging manifestations of brain neoplasm as well as clinical features of parasitosis. Thus, we review the MRI, FDG-PET-CT, MRS, and DTI data of this case according to the timeline, refer to relevant studies, and point out the pitfalls. With a long course of slowly progressing, this was a rare case of secondary glioblastoma with the absence of isocitrate dehydrogenase 1 (IDH1) gene mutation.

Proton 3D MR spectroscopy in the diagnosis of glial brain tumors

The purpose of this study was an assessment of the proton 3D MR spectroscopy efficacy in diagnosis of primary glial brain tumors.Material and methods. Sixty three patients aged from 20 to 60 years with primary glial brain tumors of varying degrees of malignancy were examined. The ratios of main metabolites indices were evaluated with following comparison with the metabolites obtained in gray and white matter of the opposite hemisphere.The ratios of main metabolites: Cho/Cr, NAA/Cr, Cho/NAA showed significant (p <0.005) differences in the groups of patients with low and high grade gliomas.Results. The obtained data proved the efficacy of the proton 3D MR-spectroscopy in predicting of the glial brain tumors malignancy.

An update on PET-based molecular imaging in neuro-oncology: challenges and implementation for a precision medicine approach in cancer care

PET imaging using novel radiotracers show promises for tumor grading and molecular characterization through visualizing molecular and functional properties of the tumors. Application of PET tracers in brain neoplasm depends on both type of the neoplasm and the research or clinical significance required to be addressed. In clinical neuro-oncology, 18F-FDG is used mainly to differentiate tumor recurrence from radiation-induced necrosis, and novel PET agents show attractive imaging properties. Novel PET tracers can offer biologic information not visible via contrast-enhanced MRI or 18F-FDG PET. This review aims to provide an update on the complementary role of PET imaging in neuro-oncology both in research and clinical settings along with presenting interesting cases in this context.

Diagnostic accuracy of dynamic contrast-enhanced perfusion MRI in stratifying gliomas: A systematic review and meta-analysis

Background

T1‐weighted dynamic contrast‐enhanced (DCE) perfusion magnetic resonance imaging (MRI) has been broadly utilized in the evaluation of brain tumors. We aimed at assessing the diagnostic accuracy of DCE‐MRI in discriminating between low‐grade gliomas (LGGs) and high‐grade gliomas (HGGs), between tumor recurrence and treatment‐related changes, and between primary central nervous system lymphomas (PCNSLs) and HGGs.

Methods

We performed this study based on the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis of Diagnostic Test Accuracy Studies criteria. We systematically surveyed studies evaluating the diagnostic accuracy of DCE‐MRI for the aforementioned entities. Meta‐analysis was conducted with the use of a random effects model.

Results

Twenty‐seven studies were included after screening of 2945 possible entries. We categorized the eligible studies into three groups: those utilizing DCE‐MRI to differentiate between HGGs and LGGs (14 studies, 546 patients), between recurrence and treatment‐related changes (9 studies, 298 patients) and between PCNSLs and HGGs (5 studies, 224 patients). The pooled sensitivity, specificity, and area under the curve for differentiating HGGs from LGGs were 0.93, 0.90, and 0.96, for differentiating tumor relapse from treatment‐related changes were 0.88, 0.86, and 0.89, and for differentiating PCNSLs from HGGs were 0.78, 0.81, and 0.86, respectively.

Conclusions

Dynamic contrast‐enhanced‐Magnetic resonance imaging is a promising noninvasive imaging method that has moderate or high accuracy in stratifying gliomas. DCE‐MRI shows high diagnostic accuracy in discriminating between HGGs and their low‐grade counterparts, and moderate diagnostic accuracy in discriminating recurrent lesions and treatment‐related changes as well as PCNSLs and HGGs.

Brain SPECT and perfusion MRI: do they provide complementary information about the tumour lesion and its grading?

AIM

To evaluate the relative and combined utility of ^99mTc-tetrofosmin (^99mTc-TF) brain single-photon-emission computed tomography (SPECT) and dynamic susceptibility contrast (DSC) perfusion magnetic resonance imaging (MRI) in grading brain gliomas.

MATERIALS AND METHODS

Thirty-six patients with clinically suspected brain tumours were assessed by ^99mTc-TF SPECT and DSC-MRI. Brain tumour malignancy was confirmed in all patients at histopathology. On both techniques brain lesions were evaluated via visual and semi-quantitative analysis methods (deriving tetrofosmin index [T-index] and relative cerebral blood volume [rCBV] ratios, respectively).

RESULTS

^99mTc-TF SPECT showed abnormally elevated tracer uptake in 31/36 patients whereas MRI detected the brain tumour in all patients. Optimal cut-off values of each index for discriminating between low- and high-grade gliomas were obtained through receiver operating characteristic (ROC) analyses. A T-index cut-off of 6.35 ensured 82% sensitivity and 71% specificity for discriminating between high- and low-grade gliomas, whereas a relative rCBV ratio cut-off of 1.80 achieved 91% sensitivity and 100% specificity. Requiring a positive result on either technique to characterise a high-grade glioma was associated with similar specificity and slightly increased sensitivity.

CONCLUSION

Both imaging techniques, ^99mTF SPECT and DSC MRI, may provide complementary indices of tumour grade and have an independent diagnostic value for high-risk tumours.

Lack of choline elevation on proton magnetic resonance spectroscopy in grade I-III gliomas

Elevated levels of choline are generally emphasized as marker of increased cellularity and cell membrane turnover in gliomas. In this study, we investigated the incidence rate of lack of choline/creatine and choline/water elevation in a population of grade I-III gliomas. A cohort of 41 patients with histopathologically confirmed gliomas underwent multi-voxel proton magnetic resonance spectroscopy on a 3 T magnetic resonance system prior to treatment. Peak areas for choline and myoinositol were measured from all voxels that exhibited hyperintensity on fluid-attenuated inversion recovery images and were normalized to creatine and unsuppressed water from each voxel. The average metabolite/creatine and metabolite/water ratios from these voxels were then computed. Similarly, average metabolite ratios were computed from normal brain parenchyma. Gliomas were considered for lack of choline elevation when choline/creatine and choline/water ratios from neoplastic regions were less than those from normal brain parenchyma regions. Six of 41 (14.6%) grade I-III gliomas showed lack of elevation for choline/creatine and choline/water ratios compared to normal brain parenchyma. Four of these six gliomas also demonstrated elevated levels of myoinositol/creatine ratio. All other gliomas (n = 35) had elevated choline levels from neoplastic regions relative to normal parenchyma. The sensitivity of choline/creatine or choline/water in determining a grade I-III glioma was 85.4%. These findings suggest that a lack of choline/creatine or choline/water elevation may be seen in some gliomas and low choline levels should not prevent us from considering the possibility of a grade I-III glioma.