Morphometric model for discrimination between glioblastoma multiforme and solitary metastasis using three-dimensional shape analysis

Diffusion Tensor Imaging (DTI) Biomarker Alterations in Brain Metastases and Comparable Tumors: A Systematic Review of DTI and Tractography Findings

BACKGROUND

Brain metastases (BMs) are the most frequent tumors of the central nervous system. Diffusion tensor imaging (DTI) is a magnetic resonance imaging technique that provides insights into brain microstructural alterations and tensor metrics and generates tractography to visualize white matter fiber tracts based on diffusion directionality. This systematic review assessed evidence from DTI biomarker alterations in BMs and comparable tumors such as glioblastoma.

METHODS

PubMed, Scopus, and Web of Science were searched, and published between January 2000 and August 2023. The key inclusion criteria were studies reporting DTI metrics in BMs and comparisons with other tumors. Data on study characteristics, tumor types, sample details, and main DTI findings were extracted.

RESULTS

Fifty-seven studies with 1592 BM patients and 1578 comparable brain tumors were included. Peritumoral fractional anisotropy (FA) consistently differentiates BMs from primary brain tumors, whereas intratumoral FA shows limited discriminatory power. Mean diffusivity increased in BMs versus comparators. Intratumoral metrics were less consistent but revealed differences in BM origin. Axial and radial diffusivity have provided insights into the effects of radiation, tumor origin, and infiltration. Axial diffusivity/radial diffusivity differentiated tumor infiltration from vasogenic edema. Tractography revealed anatomical relationships between white matter tracts and BMs. In addition, tractography-guided BM surgery and radiotherapy planning are required. Machine learning models incorporating DTI biomarkers/metrics accurately classified BMs versus comparators and improved diagnostic classification.

CONCLUSIONS

DTI metrics provide noninvasive biomarkers for distinguishing BMs from other tumors and predicting outcomes. Key metrics included peritumoral FA and mean diffusivity.

The value of texture analysis in peritumoral edema of differentiating diagnosis between glioblastoma and primary brain lymphoma

OBJECTIVE

To evaluate the value of texture analysis of routine MRI image in peritumoral edema of differentiating diagnosis between glioblastoma (GBM) and primary brain lymphoma (PBL).

METHODS

The MRI imaging data of 22 patients with glioblastoma and 21 patients with PBL who were hospitalized in our hospital from January 2010 to October 2018 were selected. All the patients were pathologically diagnosed as glioblastoma or PBL, and MRI plain scan and enhanced examination were performed before operation. FireVoxel software was used to delineate the region of interest (ROI) on the most obvious level of peritumoral edema based on T1WI enhancement. Texture parameters were extracted and compared between glioblastoma and PBL.

RESULTS

In the glioblastoma group, the inhomogeneity, kurtosis and entropy texture parameters were statistically different from those in the PBL group. The entropy parameter area under the curve (AUC) (0.903) was significantly better than the kurtosis parameter AUC (0.859) and the inhomogeneity parameter AUC (0.729). When the entropy parameter Cut-off point = 3.883, the sensitivity, specificity and accuracy of glioblastoma and PBL were 85.7, 86.4 and 86.0%, respectively, by differential diagnosis.

CONCLUSION

Texture analysis of tumor peritumoral edema provided quantifiable information, which might be a new method for differentiating glioblastoma from PBL.

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

OBJECTIVE

Preoperative diagnosis of diffuse midline glioma, H3 K27-altered (DMG-A) and midline high-grade glioma without H3 K27 alteration (DMG-W), as well as midline primary CNS lymphoma (PCNSL) in adults, is challenging but crucial. The aim of this study was to develop a model for predicting these three entities using machine learning (ML) algorithms.

METHODS

Thirty-three patients with DMG-A, 35 with DMG-W, and 35 with midline PCNSL were retrospectively enrolled in the study. Radiomics features were extracted from contrast-enhanced T1-weighted MR images. Two radiologists evaluated the conventional MRI features of the tumors, such as shape. Patient age, tumor volume, and conventional MRI features were considered clinical features. The data set was randomly stratified into 70% training and 30% testing cohorts. Predictive models based on the clinical features, radiomics features, and integration of clinical and radiomics features were established through ML. The performances of the models were evaluated by calculating the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. Subsequently, 10 patients with DMG-A, 10 with DMG-W, and 12 with PCNSL were enrolled from another institution to validate the established models.

RESULTS

The predictive models based on clinical features, radiomics features, and the integration of clinical and radiomics features through the support vector machine algorithm had the optimal accuracies in the training, testing, and validation cohorts, and the accuracies in the testing cohort were 0.871, 0.892, and 0.903, respectively. Age, 2 radiomics features, and 3 conventional MRI features were the 6 most significant features in the established integrated model.

CONCLUSIONS

The integrated prediction model established by ML provides high discriminatory accuracy for predicting DMG-A, DMG-W, and midline PCNSL in adults.

Shape and texture analyses based on conventional MRI for the preoperative prediction of the aggressiveness of pituitary adenomas

OBJECTIVES

Pituitary adenomas can exhibit aggressive behavior, characterized by rapid growth, resistance to conventional treatment, and early recurrence. This study aims to evaluate the clinical value of shape-related features combined with textural features based on conventional MRI in evaluating the aggressiveness of pituitary adenomas and develop the best diagnostic model.

METHODS

Two hundred forty-six pituitary adenoma patients (84 aggressive, 162 non-aggressive) who underwent preoperative MRI were retrospectively reviewed. The patients were divided into training (n = 193) and testing (n = 53) sets. Clinical information, shape-related, and textural features extracted from the tumor volume on contrast-enhanced T1-weighted images (CE-T1WI), were compared between aggressive and non-aggressive groups. Variables with significant differences were enrolled into Pearson's correlation analysis to weaken multicollinearity. Logistic regression models based on the selected features were constructed to predict tumor aggressiveness under fivefold cross-validation.

RESULTS

Sixty-five imaging features, including five shape-related and sixty textural features, were extracted from volumetric CE-T1WI. Forty-seven features were significantly different between aggressive and non-aggressive groups (all p values < 0.05). After feature selection, four features (SHAPE_Sphericity, SHAPE_Compacity, DISCRETIZED_Q3, and DISCRETIZED_Kurtosis) were put into logistic regression analysis. Based on the combination of these features and Knosp grade, the model yielded an area under the curve value of 0.935, with a sensitivity of 94.4% and a specificity of 82.9%, to discriminate between aggressive and non-aggressive pituitary adenomas in the testing set.

CONCLUSION

The radiomic model based on tumor shape and textural features study from CE-T1WI might potentially assist in the preoperative aggressiveness diagnosis of pituitary adenomas.

KEY POINTS

• Pituitary adenomas with aggressive behavior exhibit rapid growth, resistance to conventional treatment, and early recurrence despite gross resection and may require multiline treatments. • Shape-related features and texture features based on CE-T1WI were significantly correlated with the Ki-67 labeling index, mitotic count, and p53 expression, and the proposed model achieved a favorable prediction of the aggressiveness of PAs with an AUC value of 0.935. • The prediction model might provide valuable guidance for individualized treatment in patients with PAs.

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.

Radiomics can differentiate high-grade glioma from brain metastasis: a systematic review and meta-analysis

OBJECTIVE

(1) To evaluate the diagnostic performance of radiomics in differentiating high-grade glioma from brain metastasis and how to improve the model. (2) To assess the methodological quality of radiomics studies and explore ways of embracing the clinical application of radiomics.

METHODS

Studies using radiomics to differentiate high-grade glioma from brain metastasis published by 26 July 2021 were systematically reviewed. Methodological quality and risk of bias were assessed using the Radiomics Quality Score (RQS) system and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool, respectively. Pooled sensitivity and specificity of the radiomics model were also calculated.

RESULTS

Seventeen studies combining 1,717 patients were included in the systematic review, of which 10 studies without data leakage suspicion were employed for the quantitative statistical analysis. The average RQS was 5.13 (14.25% of total), with substantial or almost perfect inter-rater agreements. The inclusion of clinical features in the radiomics model was only reported in one study, as was the case for publicly available algorithm code. The pooled sensitivity and specificity were 84% (95% CI, 80-88%) and 84% (95% CI, 81-87%), respectively. The performances of feature extraction from the volume of interest (VOI) or (semi) automatic segmentation in the radiomics models were superior to those of protocols employing region of interest (ROI) or manual segmentation.

CONCLUSION

Radiomics can accurately differentiate high-grade glioma from brain metastasis. The adoption of standardized workflow to avoid potential data leakage as well as the integration of clinical features and radiomics are advised to consider in future studies.

KEY POINTS

• The pooled sensitivity and specificity of radiomics for differentiating high-grade gliomas from brain metastasis were 84% and 84%, respectively. • Avoiding potential data leakage by adopting an intensive and standardized workflow is essential to improve the quality and generalizability of the radiomics model. • The application of radiomics in combination with clinical features in differentiating high-grade gliomas from brain metastasis needs further validation.

Histogram Analysis Based on Neurite Orientation Dispersion and Density MR Imaging for Differentiation Between Glioblastoma Multiforme and Solitary Brain Metastasis and Comparison of the Diagnostic Performance of Two ROI Placements

BACKGROUND

Preoperative differentiation of glioblastoma multiforme (GBM) and solitary brain metastasis (SBM) contributes to guide neurosurgical decision-making.

PURPOSE

To explore the value of histogram analysis based on neurite orientation dispersion and density imaging (NODDI) in differentiating between GBM and SBM and comparison of the diagnostic performance of two region of interest (ROI) placements.

STUDY TYPE

Retrospective.

POPULATION

In all, 109 patients with GBM (n = 57) or SBM (n = 52) were enrolled.

FIELD STRENGTH/SEQUENCE

A 3.0 T scanners. T₂ -dark-fluid sequence, contrast-enhanced T₁ magnetization-prepared rapid gradient echo sequence, and NODDI.

ASSESSMENT

ROIs were placed on the peritumoral edema area (ROI1) and whole tumor area (ROI2, included the cystic, necrotic, and hemorrhagic areas). Histogram parameters of each isotropic volume fraction (ISOVF), intracellular volume fraction (ICVF), and orientation dispersion index (ODI) from NODDI images for two ROIs were calculated, respectively.

STATISTICAL TESTS

Mann-Whitney U test, independent t-test, chi-square test, multivariate logistic regression analysis, DeLong's test.

RESULTS

For the ROI1 and ROI2, the ICVF_min and ODI_mean obtained the highest area under curve (AUC, AUC = 0.741 and 0.750, respectively) compared to other single parameters, and the AUC of the multivariate logistic regression model was 0.851 and 0.942, respectively. DeLong's test revealed significant difference in diagnostic performance between optimal single parameter and multivariate logistic regression model within the same ROI, and the multivariate logistic regression models between two different ROIs.

DATA CONCLUSION

The performance of multivariate logistic regression model is superior to optimal single parameter in both ROIs based on NODDI histogram analysis to distinguish SBM from GBM, and the ROI placed on the whole tumor area exhibited better diagnostic performance.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Differentiating solitary brain metastases from high-grade gliomas with MR: comparing qualitative versus quantitative diagnostic strategies

PURPOSE

To investigate the diagnostic efficacy of MRI diagnostic algorithms with an ascending automatization, in distinguishing between high-grade glioma (HGG) and solitary brain metastases (SBM).

METHODS

36 patients with histologically proven HGG (n = 18) or SBM (n = 18), matched by size and location were enrolled from a database containing 655 patients. Four different diagnostic algorithms were performed serially to mimic the clinical setting where a radiologist would typically seek out further findings to reach a decision: pure qualitative, analytic qualitative (based on standardized evaluation of tumor features), semi-quantitative (based on perfusion and diffusion cutoffs included in the literature) and a quantitative data-driven algorithm of the perfusion and diffusion parameters. The diagnostic yields of the four algorithms were tested with ROC analysis and Kendall coefficient of concordance.

RESULTS

Qualitative algorithm yielded sensitivity of 72.2%, specificity of 78.8%, and AUC of 0.75. Analytic qualitative algorithm distinguished HGG from SBM with a sensitivity of 100%, specificity of 77.7%, and an AUC of 0.889. The semi-quantitative algorithm yielded sensitivity of 94.4%, specificity of 83.3%, and AUC = 0.889. The data-driven algorithm yielded sensitivity = 94.4%, specificity = 100%, and AUC = 0.948. The concordance analysis between the four algorithms and the histologic findings showed moderate concordance for the first algorithm, (k = 0.501, P < 0.01), good concordance for the second (k = 0.798, P < 0.01), and third (k = 0.783, P < 0.01), and excellent concordance for fourth (k = 0.901, p < 0.0001).

CONCLUSION

When differentiating HGG from SBM, an analytical qualitative algorithm outperformed qualitative algorithm, and obtained similar results compared to the semi-quantitative approach. However, the use of data-driven quantitative algorithm yielded an excellent differentiation.

Machine Learning Applications for Differentiation of Glioma from Brain Metastasis-A Systematic Review

Simple Summary

We present a systematic review of published reports on machine learning (ML) applications for the differentiation of gliomas from brain metastases by summarizing study characteristics, strengths, and pitfalls. Based on these findings, we present recommendations for future research in this field.

Abstract

Glioma and brain metastasis can be difficult to distinguish on conventional magnetic resonance imaging (MRI) due to the similarity of imaging features in specific clinical circumstances. Multiple studies have investigated the use of machine learning (ML) models for non-invasive differentiation of glioma from brain metastasis. Many of the studies report promising classification results, however, to date, none have been implemented into clinical practice. After a screening of 12,470 studies, we included 29 eligible studies in our systematic review. From each study, we aggregated data on model design, development, and best classifiers, as well as quality of reporting according to the TRIPOD statement. In a subset of eligible studies, we conducted a meta-analysis of the reported AUC. It was found that data predominantly originated from single-center institutions (n = 25/29) and only two studies performed external validation. The median TRIPOD adherence was 0.48, indicating insufficient quality of reporting among surveyed studies. Our findings illustrate that despite promising classification results, reliable model assessment is limited by poor reporting of study design and lack of algorithm validation and generalizability. Therefore, adherence to quality guidelines and validation on outside datasets is critical for the clinical translation of ML for the differentiation of glioma and brain metastasis.

An Integrated Radiomics Model Incorporating Diffusion-Weighted Imaging and 18F-FDG PET Imaging Improves the Performance of Differentiating Glioblastoma From Solitary Brain Metastases

BACKGROUND

The effectiveness of conventional MRI (cMRI)-based radiomics in differentiating glioblastoma (GBM) from solitary brain metastases (SBM) is not satisfactory enough. Therefore, we aimed to develop an integrated radiomics model to improve the performance of differentiating GBM from SBM.

METHODS

One hundred patients with solitary brain tumors (50 with GBM, 50 with SBM) were retrospectively enrolled and randomly assigned to the training set (n = 80) or validation set (n = 20). A total of 4,424 radiomic features were obtained from contrast-enhanced T1-weighted imaging (CE-T1WI) with the contrast-enhancing and peri-enhancing edema region, T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC), and 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images. The partial least squares (PLS) regression with fivefold cross-validation is used to analyze the correlation between different radiomic features and different modalities. The cross-validity analysis was performed to judge whether a new principal component or a new feature dimension can significantly improve the final prediction effect. The principal components with effective interpretation in all radiomic features were projected to a low-dimensional space (2D in this study). The effective features of the new projection mapping were then sent to the random forest classifier to predict the results. The performance of differentiating GBM from SBM was compared between the integrated radiomics model and other radiomics models or nonradiomics methods using the area under the receiver operating characteristics curve (AUC).

RESULTS

Through the cross-validity analysis of partial least squares, hundreds of radiomic features were projected into a new two-dimensional space to complete the construction of radiomics model. Compared with the combined radiomics model using DWI + 18F-FDG PET (AUC = 0.93, p = 0.014), cMRI + DWI (AUC = 0.89, p = 0.011), cMRI + 8F-FDG PET (AUC = 0.91, p = 0.015), and single radiomics model using cMRI (AUC = 0.85, p = 0.018), DWI (AUC = 0.84, p = 0.017), and 18F-FDG PET (AUC = 0.85, p = 0.421), the integrated radiomics model (AUC = 0.98) showed more efficient diagnostic performance. The integrated radiomics model (AUC = 0.98) also showed significantly better performance than any single ADC, SUV, or TBR parameter (AUC = 0.57-0.71, p < 0.05). The integrated radiomics model showed better performance in the training (AUC = 0.98) and validation (AUC = 0.93) sets than any other models and methods, demonstrating robustness.

CONCLUSIONS

We developed an integrated radiomics model incorporating DWI and 18F-FDG PET, which improved the performance of differentiating GBM from SBM greatly.

Differentiating Glioblastomas from Solitary Brain Metastases: An Update on the Current Literature of Advanced Imaging Modalities

Differentiating between glioblastomas and solitary brain metastases proves to be a challenging diagnosis for neuroradiologists, as both present with imaging patterns consisting of peritumoral hyperintensities with similar intratumoral texture on traditional magnetic resonance imaging sequences. Early diagnosis is paramount, as each pathology has completely different methods of clinical assessment. In the past decade, recent developments in advanced imaging modalities enabled providers to acquire a more accurate diagnosis earlier in the patient's clinical assessment, thus optimizing clinical outcome. Dynamic susceptibility contrast has been optimized for detecting relative cerebral blood flow and relative cerebral blood volume. Diffusion tensor imaging can be used to detect changes in mean diffusivity. Neurite orientation dispersion and density imaging is an innovative modality detecting changes in intracellular volume fraction, isotropic volume fraction, and extracellular volume fraction. Magnetic resonance spectroscopy is able to assist by providing a metabolic descriptor while detecting variable ratios of choline/N-acetylaspartate, choline/creatine, and N-acetylaspartate/creatine. Finally, radiomics and machine learning algorithms have been devised to assist in improving diagnostic accuracy while often utilizing more than one advanced imaging protocol per patient. In this review, we provide an update on all the current evidence regarding the identification and differentiation of glioblastomas from solitary brain metastases.

A radiomics-based model to differentiate glioblastoma from solitary brain metastases

AIM

To differentiate glioblastoma (GBM) from solitary brain metastases (MET) using radiomic analysis.

MATERIALS AND METHODS

Two hundred and fifty-three patients with solitary brain tumours (157 GBM and 98 solitary brain MET) were split into a training cohort (n=178) and a validation cohort (n=77) by stratified sampling using computer-generated random numbers at a ratio of 7:3. After feature extraction, minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) were used to build the radiomics signature on the training cohort and validation cohort. Performance was assessed by radiomics score (Rad-score), receiver operating characteristic (ROC) curve, calibration, and clinical usefulness.

RESULTS

Eleven radiomic features were selected as significant features in the training cohort. The Rad-score was significantly associated with the differentiation between GBM and solitary brain MET (p<0.001) both in the training and validation cohorts. The radiomics signature yielded area under the curve (AUC) values of 0.82 and 0.81 in the training and validation cohorts to distinguish between GBM and solitary brain MET.

CONCLUSIONS

The radiomics model might be a useful supporting tool for the preoperative differentiation of GBM from solitary brain MET, which could aid pretreatment decision-making.

Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Few studies have addressed radiomics based differentiation of Glioblastoma (GBM) and intracranial metastatic disease (IMD). However, the effect of different tumor masks, comparison of single versus multiparametric MRI (mp-MRI) or select combination of sequences remains undefined. We cross-compared multiple radiomics based machine learning (ML) models using mp-MRI to determine optimized configurations. Our retrospective study included 60 GBM and 60 IMD patients. Forty-five combinations of ML models and feature reduction strategies were assessed for features extracted from whole tumor and edema masks using mp-MRI [T1W, T2W, T1-contrast enhanced (T1-CE), ADC, FLAIR], individual MRI sequences and combined T1-CE and FLAIR sequences. Model performance was assessed using receiver operating characteristic curve. For mp-MRI, the best model was LASSO model fit using full feature set (AUC 0.953). FLAIR was the best individual sequence (LASSO-full feature set, AUC 0.951). For combined T1-CE/FLAIR sequence, adaBoost-full feature set was the best performer (AUC 0.951). No significant difference was seen between top models across all scenarios, including models using FLAIR only, mp-MRI and combined T1-CE/FLAIR sequence. Top features were extracted from both the whole tumor and edema masks. Shape sphericity is an important discriminating feature.

Differential Diagnosis of Solitary Fibrous Tumor/Hemangiopericytoma and Angiomatous Meningioma Using Three-Dimensional Magnetic Resonance Imaging Texture Feature Model

Background

Intracranial solitary fibrous tumor(SFT)/hemangiopericytoma (HPC) is an aggressive malignant tumor originating from the intracranial vasculature. Angiomatous meningioma (AM) is a benign tumor with a good prognosis. The imaging manifestations of the two are very similar. Thus, novel noninvasive diagnostic method is urgently needed in clinical practice. Texture analysis and model building through machine learning may have good prospects.

Aim

To evaluate whether a 3D-MRI texture feature model could be used to differentiate malignant intracranial SFT/HPC from AM.

Method

A total of 97 patients with SFT/HPC and 95 with AM were included in this study. Patients from each group were randomly divided into the train (70%) and test (30%) sets. ROIs were drawn along the edge of the tumor on each section of T1WI, T2WI, and contrasted T1WI using ITK-SNAP software. The segmented image was imported into the AK software for texture feature extraction, and the 3D ROI signal intensity histograms of T1WI, T2WI, and contrasted T1WI were automatically obtained along with all the parameters. Modeling was performed using the language R. Confusion matrix was used to analyze the accuracy of the model. ROC curve was constructed to assess the grading ability of the logistic regression model.

Results

After Lasso dimension reduction, 5, 9, and 7 texture features were extracted from T1WI, T2WI, and contrasted T1WI, respectively; additional 8 texture features were extracted from the combined sequence for modeling. The ROC analyses on four models resulted in an area under the curve (AUC) of 0.885 (sensitivity 76.1%, specificity 87.9%) for T1WI model, 0.918 (73.1%, 95.5%) for T2WI model, 0.815 (55.2%, 93.9%) for contrasted T1WI model, and 0.959 (92.5%, 84.8%) for the combined sequence model and were enough to correctly distinguish the two groups in 71.2%, 81.4%, 69.5%, and 83.1% of cases in test set, respectively.

Conclusions

The radiological model based on texture features could be used to differentiate SFT/HPC from AM.

Automatic lesion detection, segmentation and characterization via 3D multiscale morphological sifting in breast MRI

Previous studies on computer aided detection/diagnosis (CAD) in 4D breast magnetic resonance imaging (MRI) usually regard lesion detection, segmentation and characterization as separate tasks, and typically require users to manually select 2D MRI slices or regions of interest as the input. In this work, we present a breast MRI CAD system that can handle 4D multimodal breast MRI data, and integrate lesion detection, segmentation and characterization with no user intervention. The proposed CAD system consists of three major stages: region candidate generation, feature extraction and region candidate classification. Breast lesions are firstly extracted as region candidates using the novel 3D multiscale morphological sifting (MMS). The 3D MMS, which uses linear structuring elements to extract lesion-like patterns, can segment lesions from breast images accurately and efficiently. Analytical features are then extracted from all available 4D multimodal breast MRI sequences, including T1-, T2-weighted and DCE sequences, to represent the signal intensity, texture, morphological and enhancement kinetic characteristics of the region candidates. The region candidates are lastly classified as lesion or normal tissue by the random under-sampling boost (RUSboost), and as malignant or benign lesion by the random forest. Evaluated on a breast MRI dataset which contains a total of 117 cases with 141 biopsy-proven lesions (95 malignant and 46 benign lesions), the proposed system achieves a true positive rate (TPR) of 0.90 at 3.19 false positives per patient (FPP) for lesion detection and a TPR of 0.91 at a FPP of 2.95 for identifying malignant lesions without any user intervention. The average dice similarity index (DSI) is0.72±0.15for lesion segmentation. Compared with previously proposed lesion detection, detection-segmentation and detection-characterization systems evaluated on the same breast MRI dataset, the proposed CAD system achieves a favourable performance in breast lesion detection and characterization.

Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation

We evaluated the diagnostic performance and generalizability of traditional machine learning and deep learning models for distinguishing glioblastoma from single brain metastasis using radiomics. The training and external validation cohorts comprised 166 (109 glioblastomas and 57 metastases) and 82 (50 glioblastomas and 32 metastases) patients, respectively. Two-hundred-and-sixty-five radiomic features were extracted from semiautomatically segmented regions on contrast-enhancing and peritumoral T2 hyperintense masks and used as input data. For each of a deep neural network (DNN) and seven traditional machine learning classifiers combined with one of five feature selection methods, hyperparameters were optimized through tenfold cross-validation in the training cohort. The diagnostic performance of the optimized models and two neuroradiologists was tested in the validation cohort for distinguishing glioblastoma from metastasis. In the external validation, DNN showed the highest diagnostic performance, with an area under receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.956 (95% confidence interval [CI], 0.918–0.990), 90.6% (95% CI, 80.5–100), 88.0% (95% CI, 79.0–97.0), and 89.0% (95% CI, 82.3–95.8), respectively, compared to the best-performing traditional machine learning model (adaptive boosting combined with tree-based feature selection; AUC, 0.890 (95% CI, 0.823–0.947)) and human readers (AUC, 0.774 [95% CI, 0.685–0.852] and 0.904 [95% CI, 0.852–0.951]). The results demonstrated deep learning using radiomic features can be useful for distinguishing glioblastoma from metastasis with good generalizability.

Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification

BACKGROUND AND OBJECTIVE

Computer automated diagnosis of various skin lesions through medical dermoscopy images remains a challenging task.

METHODS

In this work, we propose an integrated diagnostic framework that combines a skin lesion boundary segmentation stage and a multiple skin lesions classification stage. Firstly, we segment the skin lesion boundaries from the entire dermoscopy images using deep learning full resolution convolutional network (FrCN). Then, a convolutional neural network classifier (i.e., Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201) is applied on the segmented skin lesions for classification. The former stage is a critical prerequisite step for skin lesion diagnosis since it extracts prominent features of various types of skin lesions. A promising classifier is selected by testing well-established classification convolutional neural networks. The proposed integrated deep learning model has been evaluated using three independent datasets (i.e., International Skin Imaging Collaboration (ISIC) 2016, 2017, and 2018, which contain two, three, and seven types of skin lesions, respectively) with proper balancing, segmentation, and augmentation.

RESULTS

In the integrated diagnostic system, segmented lesions improve the classification performance of Inception-ResNet-v2 by 2.72% and 4.71% in terms of the F1-score for benign and malignant cases of the ISIC 2016 test dataset, respectively. The classifiers of Inception-v3, ResNet-50, Inception-ResNet-v2, and DenseNet-201 exhibit their capability with overall weighted prediction accuracies of 77.04%, 79.95%, 81.79%, and 81.27% for two classes of ISIC 2016, 81.29%, 81.57%, 81.34%, and 73.44% for three classes of ISIC 2017, and 88.05%, 89.28%, 87.74%, and 88.70% for seven classes of ISIC 2018, respectively, demonstrating the superior performance of ResNet-50.

CONCLUSIONS

The proposed integrated diagnostic networks could be used to support and aid dermatologists for further improvement in skin cancer diagnosis.

3D dense connectivity network with atrous convolutional feature pyramid for brain tumor segmentation in magnetic resonance imaging of human heads

The existing deep convolutional neural networks (DCNNs) based methods have achieved significant progress regarding automatic glioma segmentation in magnetic resonance imaging (MRI) data. However, there are two main problems affecting the performance of traditional DCNNs constructed by simply stacking convolutional layers, namely, exploding/vanishing gradients and limitations to the feature computations. To address these challenges, we propose a novel framework to automatically segment brain tumors. First, a three-dimensional (3D) dense connectivity architecture is used to build the backbone for feature reuse. Second, we design a new feature pyramid module using 3D atrous convolutional layers and add this module to the end of the backbone to fuse multiscale contexts. Finally, a 3D deep supervision mechanism is equipped with the network to promote training. On the multimodal brain tumor image segmentation benchmark (BRATS) datasets, our method achieves Dice similarity coefficient values of 0.87, 0.72, and 0.70 on the BRATS 2013 Challenge, 0.84, 0.70, and 0.61 on the BRATS 2013 LeaderBoard, 0.83, 0.70, and 0.62 on the BRATS 2015 Testing, 0.8642, 0.7738, and 0.7525 on the BRATS 2018 Validation in terms of whole tumors, tumor cores, and enhancing cores, respectively. Compared to the published state-of-the-art methods, the proposed method achieves promising accuracy and fast processing, demonstrating good potential for clinical medicine.

Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers

OBJECTIVE

To differentiate supratentorial single brain metastasis (MET) from glioblastoma (GBM) by using radiomic features derived from the peri-enhancing oedema region and multiple classifiers.

METHODS

One hundred and twenty single brain METs and GBMs were retrospectively reviewed and then randomly divided into a training data set (70%) and validation data set (30%). Quantitative radiomic features of each case were extracted from the peri-enhancing oedema region of conventional MR images. After feature selection, five classifiers were built. Additionally, the combined use of the classifiers was studied. Accuracy, sensitivity, and specificity were used to evaluate the classification performance.

RESULTS

A total of 321 features were extracted, and 3 features were selected for each case. The 5 classifiers showed an accuracy of 0.70 to 0.76, sensitivity of 0.57 to 0.98, and specificity of 0.43 to 0.93 for the training data set, with an accuracy of 0.56 to 0.64, sensitivity of 0.39 to 0.78, and specificity of 0.50 to 0.89 for the validation data set. When combining the classifiers, the classification performance differed according to the combined mode and the agreement pattern of classifiers, and the greatest benefit was obtained when all the classifiers reached agreement using the same weight and simple majority vote method.

CONCLUSIONS

Three features derived from the peri-enhancing oedema region had moderate value in differentiating supratentorial single brain MET from GBM with five single classifiers. Combined use of classifiers, like multi-disciplinary team (MDT) consultation, could confer extra benefits, especially for those cases when all classifiers reach agreement.

KEY POINTS

• Radiomics provides a way to differentiate single brain MET between GBM by using conventional MR images. • The results of classifiers or algorithms themselves are also data, the transformation of the primary data. • Like MDT consultation, the combined use of multiple classifiers may confer extra benefits.

Improving brain tumor segmentation on MRI based on the deep U-net and residual units

BACKGROUNDAccurate segmentation of brain tumor depicting on magnetic resonance imaging (MRI) is an important step for doctors to determine optimal treatment plan of Gliomas, which are the common malignant brain tumors that seriously damage patients' health and life.OBJECTThis study aims to improve accuracy and efficiency of brain tumor segmentation on MRI using the advanced deep learning model.METHODIn this study, an improved model based on the U-net for accurate segmentation of brain tumor MRI images, called Deeper ResU-net, is proposed. First, a deep Deeper U-net is built, which has deeper network depth compared with U-net, uses Squeeze Operator to control network parameters and attempts to enhance the feature extraction ability. Then, Deeper ResU-net is formed to eliminate degradation phenomenon of the deep network, in which residual unit is designed and integrated into the Deeper U-net to keep the number of parameters unchanged.RESULTDeeper ResU-net makes the deep network conduct stable training without degrading. Evaluation result shows that the Deeper ResU-net has achieved competitive result with average DSC metrics of 0.9, 0.82, 0.88 for Complete tumor region, Core tumor region and Enhanced tumor region, respectively.CONCLUSIONBy extending the U-net model to a deeper layer and adding the residual structure to ensure effective and stable training of the model, the experiment results demonstrate that applying the improved Deeper ResU-net can effectively eliminate the degradation phenomenon of deep network and improve segmentation performance.

Clinical-radiomics nomograms for pre-operative differentiation of sacral chordoma and sacral giant cell tumor based on 3D computed tomography and multiparametric magnetic resonance imaging

OBJECTIVE

To develop and validate clinical-radiomics nomograms based on three-dimensional CT and multiparametric MRI (mpMRI) for pre-operative differentiation of sacral chordoma (SC) and sacral giant cell tumor (SGCT).

METHODS

A total of 83 SC and 54 SGCT patients diagnosed through surgical pathology were retrospectively analyzed. We built six models based on CT, CT enhancement (CTE), T₁ weighted, T₂ weighted, diffusion-weighted imaging (DWI), and contrast-enhanced T₁ weighted features, two radiomics nomograms and two clinical-radiomics nomograms combined radiomics mixed features with clinical data. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) analysis were used to assess the performance of the models.

RESULTS

SC and SGCT presented significant differences in terms of age, sex, and tumor location (t_age = 9.00, χ²_sex = 10.86, χ²_location = 26.20; p < 0.01). For individual scan, the radiomics model based on diffusion-weighted imaging features yielded the highest AUC of 0.889 and ACC of 0.885, followed by CT (AUC = 0.857; ACC = 0.846) and CT enhancement (AUC = 0.833; ACC = 0.769). For the combined features, the radiomics model based on mixed CT features exhibited a better AUC of 0.942 and ACC of 0.880, whereas mixed MRI features achieved a lower performance than the individual scan. The clinical-radiomics nomogram based on combined CT features achieved the highest AUC of 0.948 and ACC of 0.920.

CONCLUSIONS

The radiomics model based on CT and multiparametricMRI present a certain predictive value in distinguishing SC and SGCT, which can be used for auxiliary diagnosis before operation. The clinical-radiomics nomograms performed better than radiomics nomograms.

ADVANCES IN KNOWLEDGE

Clinical-radiomics nomograms based on CT and mpMRI features can be used for preoperative differentiation of SC and SGCT.

Reliability of tumor segmentation in glioblastoma: Impact on the robustness of MRI-radiomic features

PURPOSE

The use of radiomic features as biomarkers of treatment response and outcome or as correlates to genomic variations requires that the computed features are robust and reproducible. Segmentation, a crucial step in radiomic analysis, is a major source of variability in the computed radiomic features. Therefore, we studied the impact of tumor segmentation variability on the robustness of MRI radiomic features.

METHOD

Fluid-attenuated inversion recovery (FLAIR) and contrast-enhanced T1-weighted (T1WI_CE ) MRI of 90 patients diagnosed with glioblastoma were segmented using a semiautomatic algorithm and an interactive segmentation with two different raters. We analyzed the robustness of 108 radiomic features from five categories (intensity histogram, gray-level co-occurrence matrix, gray-level size-zone matrix (GLSZM), edge maps, and shape) using intra-class correlation coefficient (ICC) and Bland and Altman analysis.

RESULTS

Our results show that both segmentation methods are reliable with ICC ≥ 0.96 and standard deviation (SD) of mean differences between the two raters (SD_diffs ) ≤ 30%. Features computed from the histogram and co-occurrence matrices were found to be the most robust (ICC ≥ 0.8 and SD_diffs  ≤ 30% for most features in these groups). Features from GLSZM were shown to have mixed robustness. Edge, shape, and GLSZM features were the most impacted by the choice of segmentation method with the interactive method resulting in more robust features than the semiautomatic method. Finally, features computed from T1WI_CE and FLAIR images were found to have similar robustness when computed with the interactive segmentation method.

CONCLUSION

Semiautomatic and interactive segmentation methods using two raters are both reliable. The interactive method produced more robust features than the semiautomatic method. We also found that the robustness of radiomic features varied by categories. Therefore, this study could help motivate segmentation methods and feature selection in MRI radiomic studies.

Segmentation and classification of consumer-grade and dermoscopic skin cancer images using hybrid textural analysis

We present a skin lesion diagnosis system that segments the lesion and classifies it as melanoma or nonmelanoma. The proposed system is capable to deal with skin lesion images acquired by standard consumer-grade cameras and dermascopes. In order to suppress the image artifacts and enhance the lesion area, we propose an illumination correction strategy which consists of filtering in frequency and spatial domains. We introduce a hybrid model for lesion segmentation, which forms texture segments of the illumination corrected image using a factorization technique. Then based on the texture distinctiveness of the corrected and the texture segmented images, the saliency maps are computed, which are combined to decide lesion texture segments. In order to classify the segmented lesion, we propose a multimodal feature set composed of texture-, shape-, and color-based features. Classification performance of the multimodal features is evaluated using support vector machine, decision trees, and Mahalanobis distance classifiers. We evaluate the performance of the proposed system qualitatively and quantitatively. For the consumer-grade camera skin images dataset and ISIC 2017 dermascopic images dataset, the average segmentation accuracies are 98.4% and 95.4%, respectively; the classification accuracies are 98.06% and 93.95%, respectively.

Deep Learning for Diagnosis of Chronic Myocardial Infarction on Nonenhanced Cardiac Cine MRI

Background Renal impairment is common in patients with coronary artery disease and, if severe, late gadolinium enhancement (LGE) imaging for myocardial infarction (MI) evaluation cannot be performed. Purpose To develop a fully automatic framework for chronic MI delineation via deep learning on non-contrast material-enhanced cardiac cine MRI. Materials and Methods In this retrospective single-center study, a deep learning model was developed to extract motion features from the left ventricle and delineate MI regions on nonenhanced cardiac cine MRI collected between October 2015 and March 2017. Patients with chronic MI, as well as healthy control patients, had both nonenhanced cardiac cine (25 phases per cardiac cycle) and LGE MRI examinations. Eighty percent of MRI examinations were used for the training data set and 20% for the independent testing data set. Chronic MI regions on LGE MRI were defined as ground truth. Diagnostic performance was assessed by analysis of the area under the receiver operating characteristic curve (AUC). MI area and MI area percentage from nonenhanced cardiac cine and LGE MRI were compared by using the Pearson correlation, paired t test, and Bland-Altman analysis. Results Study participants included 212 patients with chronic MI (men, 171; age, 57.2 years ± 12.5) and 87 healthy control patients (men, 42; age, 43.3 years ± 15.5). Using the full cardiac cine MRI, the per-segment sensitivity and specificity for detecting chronic MI in the independent test set was 89.8% and 99.1%, respectively, with an AUC of 0.94. There were no differences between nonenhanced cardiac cine and LGE MRI analyses in number of MI segments (114 vs 127, respectively; P = .38), per-patient MI area (6.2 cm² ± 2.8 vs 5.5 cm² ± 2.3, respectively; P = .27; correlation coefficient, r = 0.88), and MI area percentage (21.5% ± 17.3 vs 18.5% ± 15.4; P = .17; correlation coefficient, r = 0.89). Conclusion The proposed deep learning framework on nonenhanced cardiac cine MRI enables the confirmation (presence), detection (position), and delineation (transmurality and size) of chronic myocardial infarction. However, future larger-scale multicenter studies are required for a full validation. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Leiner in this issue.

Texture analysis on diffusion tensor imaging: discriminating glioblastoma from single brain metastasis

BACKGROUND

Texture analysis has been done on several radiological modalities to stage, differentiate, and predict prognosis in many oncologic tumors.

PURPOSE

To determine the diagnostic accuracy of discriminating glioblastoma (GBM) from single brain metastasis (MET) by assessing the heterogeneity of both the solid tumor and the peritumoral edema with magnetic resonance imaging (MRI) texture analysis (MRTA).

MATERIAL AND METHODS

Preoperative MRI examinations done on a 3-T scanner of 43 patients were included: 22 GBM and 21 MET. MRTA was performed on diffusion tensor imaging (DTI) in a representative region of interest (ROI). The MRTA was assessed using a commercially available research software program (TexRAD) which applies a filtration histogram technique for characterizing tumor and peritumoral heterogeneity. The filtration step selectively filters and extracts texture features at different anatomical scales varying from 2 mm (fine) to 6 mm (coarse). Heterogeneity quantification was obtained by the statistical parameter entropy. A threshold value to differentiate GBM from MET with sensitivity and specificity was calculated by receiver operating characteristic (ROC) analysis.

RESULTS

Quantifying the heterogeneity of the solid part of the tumor showed no significant difference between GBM and MET. However, the heterogeneity of the GBMs peritumoral edema was significantly higher than the edema surrounding MET, differentiating them with a sensitivity of 80% and specificity of 90%.

CONCLUSION

Assessing the peritumoral heterogeneity can increase the radiological diagnostic accuracy when discriminating GBM and MET. This will facilitate the medical staging and optimize the planning for surgical resection of the tumor and postoperative management.

Diffusion-Weighted Imaging and Diffusion Tensor Imaging for Differentiating High-Grade Glioma from Solitary Brain Metastasis: A Systematic Review and Meta-Analysis

BACKGROUND

Accurate diagnosis of high-grade glioma and solitary brain metastasis is clinically important because it affects the patient's outcome and alters patient management.

PURPOSE

To evaluate the diagnostic performance of DWI and DTI for differentiating high-grade glioma from solitary brain metastasis.

DATA SOURCES

A literature search of Ovid MEDLINE and EMBASE was conducted up to November 10, 2017.

STUDY SELECTION

Studies evaluating the diagnostic performance of DWI and DTI for differentiating high-grade glioma from solitary brain metastasis were selected.

DATA ANALYSIS

Summary sensitivity and specificity were established by hierarchic logistic regression modeling. Multiple subgroup analyses were also performed.

DATA SYNTHESIS

Fourteen studies with 1143 patients were included. The individual sensitivities and specificities of the 14 included studies showed a wide variation, ranging from 46.2% to 96.0% for sensitivity and 40.0% to 100.0% for specificity. The pooled sensitivity of both DWI and DTI was 79.8% (95% CI, 70.9%-86.4%), and the pooled specificity was 80.9% (95% CI, 75.1%-85.5%). The area under the hierarchical summary receiver operating characteristic curve was 0.87 (95% CI, 0.84-0.89). The multiple subgroup analyses also demonstrated similar diagnostic performances (sensitivities of 76.8%-84.7% and specificities of 79.7%-84.0%). There was some level of heterogeneity across the included studies (I² = 36%); however, it did not reach a level of concern.

LIMITATIONS

The included studies used various DWI and DTI parameters.

CONCLUSIONS

DWI and DTI demonstrated a moderate diagnostic performance for differentiation of high-grade glioma from solitary brain metastasis.

Fully automatic segmentation and objective assessment of atrial scars for long-standing persistent atrial fibrillation patients using late gadolinium-enhanced MRI

PURPOSE

Atrial fibrillation (AF) is the most common heart rhythm disorder and causes considerable morbidity and mortality, resulting in a large public health burden that is increasing as the population ages. It is associated with atrial fibrosis, the amount and distribution of which can be used to stratify patients and to guide subsequent electrophysiology ablation treatment. Atrial fibrosis may be assessed noninvasively using late gadolinium-enhanced (LGE) magnetic resonance imaging (MRI) where scar tissue is visualized as a region of signal enhancement. However, manual segmentation of the heart chambers and of the atrial scar tissue is time consuming and subject to interoperator variability, particularly as image quality in AF is often poor. In this study, we propose a novel fully automatic pipeline to achieve accurate and objective segmentation of the heart (from MRI Roadmap data) and of scar tissue within the heart (from LGE MRI data) acquired in patients with AF.

METHODS

Our fully automatic pipeline uniquely combines: (a) a multiatlas-based whole heart segmentation (MA-WHS) to determine the cardiac anatomy from an MRI Roadmap acquisition which is then mapped to LGE MRI, and (b) a super-pixel and supervised learning based approach to delineate the distribution and extent of atrial scarring in LGE MRI. We compared the accuracy of the automatic analysis to manual ground truth segmentations in 37 patients with persistent long-standing AF.

RESULTS

Both our MA-WHS and atrial scarring segmentations showed accurate delineations of cardiac anatomy (mean Dice = 89%) and atrial scarring (mean Dice = 79%), respectively, compared to the established ground truth from manual segmentation. In addition, compared to the ground truth, we obtained 88% segmentation accuracy, with 90% sensitivity and 79% specificity. Receiver operating characteristic analysis achieved an average area under the curve of 0.91.

CONCLUSION

Compared with previously studied methods with manual interventions, our innovative pipeline demonstrated comparable results, but was computed fully automatically. The proposed segmentation methods allow LGE MRI to be used as an objective assessment tool for localization, visualization, and quantitation of atrial scarring and to guide ablation treatment.

Brain metastases: neuroimaging

Magnetic resonance imaging (MRI) is the cornerstone for evaluating patients with brain masses such as primary and metastatic tumors. Important challenges in effectively detecting and diagnosing brain metastases and in accurately characterizing their subsequent response to treatment remain. These difficulties include discriminating metastases from potential mimics such as primary brain tumors and infection, detecting small metastases, and differentiating treatment response from tumor recurrence and progression. Optimal patient management could be benefited by improved and well-validated prognostic and predictive imaging markers, as well as early response markers to identify successful treatment prior to changes in tumor size. To address these fundamental needs, newer MRI techniques including diffusion and perfusion imaging, MR spectroscopy, and positron emission tomography (PET) tracers beyond traditionally used 18-fluorodeoxyglucose are the subject of extensive ongoing investigations, with several promising avenues of added value already identified. These newer techniques provide a wealth of physiologic and metabolic information that may supplement standard MR evaluation, by providing the ability to monitor and characterize cellularity, angiogenesis, perfusion, pH, hypoxia, metabolite concentrations, and other critical features of malignancy. This chapter reviews standard and advanced imaging of brain metastases provided by computed tomography, MRI, and amino acid PET, focusing on potential biomarkers that can serve as problem-solving tools in the clinical management of patients with brain metastases.

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

OBJECTIVE

Predicting the survival outcome of patients with glioblastoma multiforme (GBM) is of key importance to clinicians for selecting the optimal course of treatment. The goal of this study was to evaluate the usefulness of geometric shape features, extracted from MR images, as a potential non-invasive way to characterize GBM tumours and predict the overall survival times of patients with GBM.

METHODS

The data of 40 patients with GBM were obtained from the Cancer Genome Atlas and Cancer Imaging Archive. The T₁ weighted post-contrast and fluid-attenuated inversion-recovery volumes of patients were co-registered and segmented into delineate regions corresponding to three GBM phenotypes: necrosis, active tumour and oedema/invasion. A set of two-dimensional shape features were then extracted slicewise from each phenotype region and combined over slices to describe the three-dimensional shape of these phenotypes. Thereafter, a Kruskal-Wallis test was employed to identify shape features with significantly different distributions across phenotypes. Moreover, a Kaplan-Meier analysis was performed to find features strongly associated with GBM survival. Finally, a multivariate analysis based on the random forest model was used for predicting the survival group of patients with GBM.

RESULTS

Our analysis using the Kruskal-Wallis test showed that all but one shape feature had statistically significant differences across phenotypes, with p-value < 0.05, following Holm-Bonferroni correction, justifying the analysis of GBM tumour shapes on a per-phenotype basis. Furthermore, the survival analysis based on the Kaplan-Meier estimator identified three features derived from necrotic regions (i.e. Eccentricity, Extent and Solidity) that were significantly correlated with overall survival (corrected p-value < 0.05; hazard ratios between 1.68 and 1.87). In the multivariate analysis, features from necrotic regions gave the highest accuracy in predicting the survival group of patients, with a mean area under the receiver-operating characteristic curve (AUC) of 63.85%. Combining the features of all three phenotypes increased the mean AUC to 66.99%, suggesting that shape features from different phenotypes can be used in a synergic manner to predict GBM survival.

CONCLUSION

Results show that shape features, in particular those extracted from necrotic regions, can be used effectively to characterize GBM tumours and predict the overall survival of patients with GBM. Advances in knowledge: Simple volumetric features have been largely used to characterize the different phenotypes of a GBM tumour (i.e. active tumour, oedema and necrosis). This study extends previous work by considering a wide range of shape features, extracted in different phenotypes, for the prediction of survival in patients with GBM.