Differentiation Between Glioblastoma Multiforme and Metastasis From the Lungs and Other Sites Using Combined Clinical/Routine MRI Radiomics

Role of artificial intelligence in brain tumour imaging

Artificial intelligence (AI) is a rapidly evolving field with many neuro-oncology applications. In this review, we discuss how AI can assist in brain tumour imaging, focusing on machine learning (ML) and deep learning (DL) techniques. We describe how AI can help in lesion detection, differential diagnosis, anatomic segmentation, molecular marker identification, prognostication, and pseudo-progression evaluation. We also cover AI applications in non-glioma brain tumours, such as brain metastasis, posterior fossa, and pituitary tumours. We highlight the challenges and limitations of AI implementation in radiology, such as data quality, standardization, and integration. Based on the findings in the aforementioned areas, we conclude that AI can potentially improve the diagnosis and treatment of brain tumours and provide a path towards personalized medicine and better patient outcomes.

A systematic review of brain metastases from lung cancer using magnetic resonance neuroimaging: Clinical and technical aspects

INTRODUCTION

Brain metastases (BMs) are common in lung cancer (LC) and are associated with poor prognosis. Magnetic resonance imaging (MRI) plays a vital role in the detection, diagnosis and management of BMs. This review summarises recent advances in MRI techniques for BMs from LC.

METHODS

This systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive literature search was conducted in three electronic databases: PubMed, Scopus and the Web of Science. The search was limited to studies published between January 2000 and March 2023. The quality of the included studies was evaluated using appropriate tools for different study designs. A narrative synthesis was carried out to describe the key findings of the included studies.

RESULTS

Sixty-five studies were included. Standard MRI sequences such as T1-weighted (T1w), T2-weighted (T2w) and fluid-attenuated inversion recovery (FLAIR) were commonly used. Advanced techniques included perfusion-weighted imaging (PWI), diffusion-weighted imaging (DWI) and radiomics analysis. DWI and PWI parameters could distinguish tumour recurrence from radiation necrosis. Radiomics models predicted genetic mutations and the risk of BMs. Diagnostic accuracy was improved with deep learning (DL) approaches. Prognostic factors such as performance status and concurrent chemotherapy impacted survival.

CONCLUSION

Advanced MRI techniques and specialised MRI methods have emerging roles in managing BMs from LC. PWI and DWI improve diagnostic accuracy in treated BMs. Radiomics and DL facilitate personalised prognosis and treatment. Magnetic resonance imaging plays a key role in the continuum of care for BMs of patients with LC, from screening to treatment monitoring.

Radiomics Analysis of Diffusion Kurtosis Imaging: Distinguishing Between Glioblastoma and Single Brain Metastasis

RATIONALE AND OBJECTIVES

This study aimed to assess the value of diffusion kurtosis imaging (DKI)-based radiomics models in differentiating glioblastoma (GB) from single brain metastasis (SBM) and compare their diagnostic performance with that of routine magnetic resonance imaging (MRI) models.

MATERIALS AND METHODS

A total of 110 patients who underwent DKI and were pathologically diagnosed with GB (n = 58) or SBM (n = 52) were enrolled in this study. Radiomics features were extracted from the manually delineated region of interest of the lesion. A training set for model development was constructed from the images of 88 random patients, and 22 patients were reserved for independent validation. Seven single-DKI-parametric models and a multi-DKI-parametric model were constructed using six classifiers, whereas four single-routine-sequence models (based on T2 weighted imaging, apparent diffusion coefficient, T2-dark-fluid, and contrast-enhanced T1 magnetization prepared rapid gradient echo) and a multisequence routine MRI model were constructed for comparison. Receiver operating characteristic curve analysis was conducted to assess the diagnostic performance. The areas under the curve (AUCs) of different models were compared using the DeLong test.

RESULTS

The AUCs of the single-DKI-parametric models ranged from 0.800 to 0.933 (mean kurtosis [MK] model). The multi-DKI-parametric model had a slightly higher AUC (0.958) than the MK model; however, the difference was not statistically significant (P = 0.688). In comparison, the AUCs of the routine MRI models ranged from 0.633 to 0.733 (multisequence routine MRI model). The AUC of the multi-DKI-parametric model was significantly higher than that of the multisequence routine MRI model (P = 0.042).

CONCLUSION

The multi-DKI-parametric radiomics model exhibited better performance than that of the single-DKI-parametric models and routine MRI models in distinguishing GB from SBM.

Radiomic texture analysis based on neurite orientation dispersion and density imaging to differentiate glioblastoma from solitary brain metastasis

BACKGROUND

We created discriminative models of different regions of interest (ROIs) using radiomic texture features of neurite orientation dispersion and density imaging (NODDI) and evaluated the feasibility of each model in differentiating glioblastoma multiforme (GBM) from solitary brain metastasis (SBM).

METHODS

We conducted a retrospective study of 204 patients with GBM (n = 146) or SBM (n = 58). Radiomic texture features were extracted from five ROIs based on three metric maps (intracellular volume fraction, orientation dispersion index, and isotropic volume fraction of NODDI), including necrosis, solid tumors, peritumoral edema, tumor bulk volume (TBV), and abnormal bulk volume. Four feature selection methods and eight classifiers were used for the radiomic texture feature selection and model construction. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of the models. Routine magnetic resonance imaging (MRI) radiomic texture feature models generated in the same manner were used for the horizontal comparison.

RESULTS

NODDI-radiomic texture analysis based on TBV subregions exhibited the highest accuracy (although nonsignificant) in differentiating GBM from SBM, with area under the ROC curve (AUC) values of 0.918 and 0.882 in the training and test datasets, respectively, compared to necrosis (AUCtraining:0.845, AUCtest:0.714), solid tumor (AUCtraining:0.852, AUCtest:0.821), peritumoral edema (AUCtraining:0.817, AUCtest:0.762), and ABV (AUCtraining:0.834, AUCtest:0.779). The performance of the five ROI radiomic texture models in routine MRI was inferior to that of the NODDI-radiomic texture model.

CONCLUSION

Preoperative NODDI-radiomic texture analysis based on TBV subregions shows great potential for distinguishing GBM from SBM.

The role of 3-Tesla magnetic resonance perfusion and spectroscopy in distinguishing glioblastoma from solitary brain metastasis

OBJECTIVES

This study aimed to assess the value of magnetic resonance perfusion (MR perfusion) and magnetic resonance spectroscopy (MR spectroscopy) in 3.0-Tesla magnetic resonanceimaging (MRI) for differential diagnosis of glioblastoma (GBM) and solitary brain metastasis (SBM).

MATERIAL AND METHODS

This retrospective study involved 36 patients, including 24 cases of GBM and 12 of SBM diagnosed using histopathology. All patients underwent a 3.0-Tesla MRI examination with pre-operative MR perfusion and MR spectroscopy. We assessed the differences in age, sex, cerebral blood volume (CBV), relative CBV (rCBV), and the metabolite ratios of choline/N-acetylaspartate (Cho/NAA) and Cho/creatine between the GBM and SBM groups using the Mann-Whitney U-test and Chi-square test. The cutoff value, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value of the significantly different parameters between these two groups were determined using the receiver operating characteristic curve.

RESULTS

In MR perfusion, the CBV of the peritumoral region (pCBV) had the highest preoperative predictive value in discriminating GBM from SBM (cutoff: 1.41; sensitivity: 70.83%; and specificity: 83.33%), followed by the ratio of CBV of the solid tumor component to CBV of normal white matter (rCBVt/n) and the ratio of CBV of the pCBV to CBV of normal white matter (rCBVp/n). In MR spectroscopy, the Cho/NAA ratio of the pCBV (pCho/NAA; cutoff: 1.02; sensitivity: 87.50%; and specificity: 75%) and the Cho/NAA ratio of the solid tumor component (tCho/NAA; cutoff: 2.11; sensitivity: 87.50%; and specificity: 66.67%) were significantly different between groups. Moreover, combining these remarkably different parameters increased their diagnostic utility for distinguishing between GBM and SBM.

CONCLUSION

pCBV, rCBVt/n, rCBVp/n, pCho/NAA, and tCho/NAA are useful indices for differentiating between GBM and SBM. Combining these indices can improve diagnostic performance in distinguishing between these two tumors.

Prediction of Glioma Grade by Tumor Heterogeneity Radiomic Analysis Based on Multiparametric MRI

Predicting glioma grade plays a pivotal role in treatment and prognosis. However, several current methods for grading depend on the characteristics of the whole tumor. Predicting grade by analyzing tumor subregions has not been thoroughly investigated, which aims to improve the prediction performance. To predict glioma grade via analysis of tumor heterogeneity with features extracted from tumor subregions, it is mainly divided into four magnetic resonance imaging (MRI) sequences, including T2-weighted (T2), fluid-attenuated inversion recovery (FLAIR), pre-gadolinium T1-weighted (T1), and post-gadolinium T1-weighted methods. This study included the data of 97 patients with glioblastomas and 42 patients with low-grade gliomas before surgery. Three subregions, including enhanced tumor (ET), non-enhanced tumor, and peritumoral edema, were obtained based on segmentation labels generated by the GLISTRBoost algorithm. One hundred radiomic features were extracted from each subregion. Feature selection was performed using the cross-validated recursive feature elimination with a support vector machine (SVM) algorithm. SVM classifiers with grid search were established to predict glioma grade based on unparametric and multiparametric MRI. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the classifiers, and the performance of the subregions was compared with the results of the whole tumor. In uniparametric analysis, the features from the ET subregion yielded a higher AUC value of 0.8697, 0.8474, and 0.8474 than those of the whole tumor of FLAIR, T1, and T2. In multiparametric analysis, the ET subregion achieved the best performance (AUC = 0.8755), which was higher than the uniparametric results. Radiomic features from the tumor subregion can potentially be used as clinical markers to improve the predictive accuracy of glioma grades.

The Application of DTCWT on MRI-Derived Radiomics for Differentiation of Glioblastoma and Solitary Brain Metastases

Background: While magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of patients with brain tumors, it may still be challenging to differentiate glioblastoma multiforme (GBM) from solitary brain metastasis (SBM) due to their similar imaging features. This study aimed to evaluate the features extracted of dual-tree complex wavelet transform (DTCWT) from routine MRI protocol for preoperative differentiation of glioblastoma (GBM) and solitary brain metastasis (SBM). Methods: A total of 51 patients were recruited, including 27 GBM and 24 SBM patients. Their contrast-enhanced T1-weighted images (CET1WIs), T2 fluid-attenuated inversion recovery (T2FLAIR) images, diffusion-weighted images (DWIs), and apparent diffusion coefficient (ADC) images were employed in this study. The statistical features of the pre-transformed images and the decomposed images of the wavelet transform and DTCWT were utilized to distinguish between GBM and SBM. Results: The support vector machine (SVM) showed that DTCWT images have a better accuracy (82.35%), sensitivity (77.78%), specificity (87.50%), and the area under the curve of the receiver operating characteristic curve (AUC) (89.20%) than the pre-transformed and conventional wavelet transform images. By incorporating DTCWT and pre-transformed images, the accuracy (86.27%), sensitivity (81.48%), specificity (91.67%), and AUC (93.06%) were further improved. Conclusions: Our studies suggest that the features extracted from the DTCWT images can potentially improve the differentiation between GBM and SBM.

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

Simple Summary

Gliomas can be difficult to discern clinically and radiologically from other brain lesions (either neoplastic or non-neoplastic) since their clinical manifestations as well as preoperative imaging features often overlap and appear misleading. Radiomics could be extremely helpful for non-invasive glioma differential diagnosis (DDx). However, implementation in clinical practice is still distant and concerns have been raised regarding the methodological quality of radiomic studies. In this context, we aimed to summarize the current status and quality of radiomic studies concerning glioma DDx in a systematic review. In total, 42 studies were selected and examined in our work. Our study revealed that, despite promising and encouraging results, current studies on radiomics for glioma DDx still lack the quality required to allow its introduction into clinical practice. This work could provide new insights and help to reach a consensus on the use of the radiomic approach for glioma DDx.

Abstract

Radiomics is a promising tool that may increase the value of imaging in differential diagnosis (DDx) of glioma. However, implementation in clinical practice is still distant and concerns have been raised regarding the methodological quality of radiomic studies. Therefore, we aimed to systematically review the current status of radiomic studies concerning glioma DDx, also using the radiomics quality score (RQS) to assess the quality of the methodology used in each study. A systematic literature search was performed to identify original articles focused on the use of radiomics for glioma DDx from 2015. Methodological quality was assessed using the RQS tool. Spearman’s correlation (ρ) analysis was performed to explore whether RQS was correlated with journal metrics and the characteristics of the studies. Finally, 42 articles were selected for the systematic qualitative analysis. Selected articles were grouped and summarized in terms of those on DDx between glioma and primary central nervous system lymphoma, those aiming at differentiating glioma from brain metastases, and those based on DDx of glioma and other brain diseases. Median RQS was 8.71 out 36, with a mean RQS of all studies of 24.21%. Our study revealed that, despite promising and encouraging results, current studies on radiomics for glioma DDx still lack the quality required to allow its introduction into clinical practice. This work could provide new insights and help to reach a consensus on the use of the radiomic approach for glioma DDx.