A Multiparametric MR-Based RadioFusionOmics Model with Robust Capabilities of Differentiating Glioblastoma Multiforme from Solitary Brain Metastasis

Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis

BACKGROUND

Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types.

METHODS

A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity.

RESULTS

Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00).

CONCLUSIONS

ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

Multiparametric MR-based feature fusion radiomics combined with ADC maps-based tumor proliferative burden in distinguishing TNBC versus non-TNBC

Objective.To investigate the incremental value of quantitative stratified apparent diffusion coefficient (ADC) defined tumor habitats for differentiating triple negative breast cancer (TNBC) from non-TNBC on multiparametric MRI (mpMRI) based feature-fusion radiomics (RFF) model.Approach.466 breast cancer patients (54 TNBC, 412 non-TNBC) who underwent routine breast MRIs in our hospital were retrospectively analyzed. Radiomics features were extracted from whole tumor on T2WI, diffusion-weighted imaging, ADC maps and the 2nd phase of dynamic contrast-enhanced MRI. Four models including the RFFmodel (fused features from all MRI sequences), RADCmodel (ADC radiomics feature), StratifiedADCmodel (tumor habitas defined on stratified ADC parameters) and combinational RFF-StratifiedADCmodel were constructed to distinguish TNBC versus non-TNBC. All cases were randomly divided into a training (n= 337) and test set (n= 129). The four competing models were validated using the area under the curve (AUC), sensitivity, specificity and accuracy.Main results.Both the RFFand StratifiedADCmodels demonstrated good performance in distinguishing TNBC from non-TNBC, with best AUCs of 0.818 and 0.773 in the training and test sets. StratifiedADCmodel revealed significant different tumor habitats (necrosis/cysts habitat, chaotic habitat or proliferative tumor core) between TNBC and non-TNBC with its top three discriminative parameters (p <0.05). The integrated RFF-StratifiedADCmodel demonstrated superior accuracy over the other three models, with higher AUCs of 0.832 and 0.784 in the training and test set, respectively (p <0.05).Significance.The RFF-StratifiedADCmodel through integrating various tumor habitats' information from whole-tumor ADC maps-based StratifiedADCmodel and radiomics information from mpMRI-based RFFmodel, exhibits tremendous promise for identifying TNBC.

Discriminative fusion of moments-aligned latent representation of multimodality medical data

Fusion of multimodal medical data provides multifaceted, disease-relevant information for diagnosis or prognosis prediction modeling. Traditional fusion strategies such as feature concatenation often fail to learn hidden complementary and discriminative manifestations from high-dimensional multimodal data. To this end, we proposed a methodology for the integration of multimodality medical data by matching their moments in a latent space, where the hidden, shared information of multimodal data is gradually learned by optimization with multiple feature collinearity and correlation constrains. We first obtained the multimodal hidden representations by learning mappings between the original domain and shared latent space. Within this shared space, we utilized several relational regularizations, including data attribute preservation, feature collinearity and feature-task correlation, to encourage learning of the underlying associations inherent in multimodal data. The fused multimodal latent features were finally fed to a logistic regression classifier for diagnostic prediction. Extensive evaluations on three independent clinical datasets have demonstrated the effectiveness of the proposed method in fusing multimodal data for medical prediction modeling.

Atypical primary central nervous system lymphoma and glioblastoma: multiparametric differentiation based on non-enhancing volume, apparent diffusion coefficient, and arterial spin labeling

OBJECTIVES

To evaluate the multiparametric diagnostic performance with non-enhancing tumor volume, apparent diffusion coefficient (ADC), and arterial spin labeling (ASL) to differentiate between atypical primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM).

METHODS

One hundred and fifty-eight patients with pathologically confirmed typical PCNSL (n = 59), atypical PCNSL (hemorrhage, necrosis, or heterogeneous contrast enhancement, n = 29), and GBM (n = 70) were selected. Relative minimum ADC (rADCmin), mean (rADCmean), maximum (rADCmax), and rADCmax-min (rADCdif) were obtained by standardization of the contralateral white matter. Maximum cerebral blood flow (CBFmax) was obtained according to the ASL-CBF map. The regions of interests (ROIs) were manually delineated on the inner side of the tumor to further generate a 3D-ROI and obtain the non-enhancing tumor (nET) volume. The area under the curve (AUC) was used to evaluate the diagnostic performance.

RESULTS

Atypical PCNSLs showed significantly lower rADCmax, rADCmean, and rADCdif than that of GBMs. GBMs showed significantly higher CBFmax and nET volume ratios than that of atypical PCNSLs. Combined three-variable models with rADCmean, CBFmax, and nET volume ratio were superior to one- and two-variable models. The AUC of the three-variable model was 0.96, and the sensitivity and specificity were 90% and 96.55%, respectively.

CONCLUSION

The combined evaluation of rADCmean, CBFmax, and nET volume allowed for reliable differentiation between atypical PCNSL and GBM.

KEY POINTS

• Atypical PCNSL is easily misdiagnosed as glioblastoma, which leads to unnecessary surgical resection. • The nET volume, ADC, and ASL-derived parameter (CBF) were lower for atypical PCNSL than that for glioblastoma. • The combination of multiple parameters performed well (AUC = 0.96) in the discrimination between atypical PCNSL and glioblastoma.

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.

Differentiating Glioblastoma Multiforme from Brain Metastases Using Multidimensional Radiomics Features Derived from MRI and Multiple Machine Learning Models

Due to different treatment strategies, it is extremely important to differentiate between glioblastoma multiforme (GBM) and brain metastases (MET). It often proves difficult to distinguish between GBM and MET using MRI due to their similar appearance on the imaging modalities. Surgical methods are still necessary for definitive diagnosis, despite the importance of magnetic resonance imaging in detecting, characterizing, and monitoring brain tumors. We introduced an accurate, convenient, and user-friendly method to differentiate between GBM and MET through routine MRI sequence and radiomics analyses. We collected 91 patients from one institution, including 50 with GBM and 41 with MET, which were proven pathologically. The tumors separately were segmented on all MRI images (T1-weighted imaging (T1WI), contrast-enhanced T1-weighted imaging (T1C), T2-weighted imaging (T2WI), and fluid-attenuated inversion recovery (FLAIR)) to form the volume of interest (VOI). Eight ML models and feature reduction strategies were evaluated using routine MRI sequences (T1W, T2W, T1-CE, and FLAIR) in two methods with (second model) and without wavelet transform (first model) radiomics. The optimal model was selected based on each model’s accuracy, AUC-roc, and F1-score values. In this study, we have achieved the result of 0.98, 0.99, and 0.98 percent for accuracy, AUC-roc, and F1-score, respectively, which have yielded a better result than the first model. In most investigated models, there were significant improvements in the multidimensional wavelets model compared to the non-multidimensional wavelets model. Multidimensional discrete wavelet transform can analyze hidden features of the MRI from a different perspective and generate accurate features which are highly correlated with the model accuracy.

ADC for Differentiation between Posttreatment Changes and Recurrence in Head and Neck Cancer: A Systematic Review and Meta-analysis

BACKGROUND

Previous studies reported that the ADC values of recurrent head and neck cancer lesions are lower than those of posttreatment changes, however, the utility of ADC to differentiate them has not been definitively summarized and established.

PURPOSE

Our aim was to evaluate the diagnostic benefit of ADC calculated from diffusion-weighted imaging in differentiating recurrent lesions from posttreatment changes in head and neck cancer.

DATA SOURCES

MEDLINE, Scopus, and EMBASE data bases were searched for studies.

STUDY SELECTION

The review identified 6 prospective studies with a total of 365 patients (402 lesions) who were eligible for the meta-analysis.

DATA ANALYSIS

Forest plots were used to assess the mean difference in ADC values. Heterogeneity among the studies was evaluated using the Cochrane Q test and the I² statistic.

DATA SYNTHESIS

Among included studies, the overall mean of ADC values of recurrent lesions was 1.03 × 10^-3mm²/s and that of the posttreatment changes was 1.51 × 10^-3mm²/s. The ADC value of recurrence was significantly less than that of posttreatment changes in head and neck cancer (pooled mean difference: -0.45; 95% CI, -0.59-0.32, P < .0001) with heterogeneity among studies. The threshold of ADC values between recurrent lesions and posttreatment changes was suggested to be 1.10 × 10^-3mm²/s.

LIMITATIONS

Given the heterogeneity of the data of the study, the conclusions should be interpreted with caution.

CONCLUSIONS

The ADC values in recurrent head and neck cancers are lower than those of posttreatment changes, and the threshold of ADC values between them was suggested.

CT in the Differentiation of Gliomas from Brain Metastases: The Radiomics Analysis of the Peritumoral Zone

Due to their similar imaging features, high-grade gliomas (HGGs) and solitary brain metastases (BMs) can be easily misclassified. The peritumoral zone (PZ) of HGGs develops neoplastic cell infiltration, while in BMs the PZ contains pure vasogenic edema. As the two PZs cannot be differentiated macroscopically, this study investigated whether computed tomography (CT)-based texture analysis (TA) of the PZ can reflect the histological difference between the two entities. Thirty-six patients with solitary brain tumors (HGGs, n = 17; BMs, n = 19) that underwent CT examinations were retrospectively included in this pilot study. TA of the PZ was analyzed using dedicated software (MaZda version 5). Univariate, multivariate, and receiver operating characteristics analyses were used to identify the best-suited parameters for distinguishing between the two groups. Seven texture parameters were able to differentiate between HGGs and BMs with variable sensitivity (56.67–96.67%) and specificity (69.23–100%) rates. Their combined ability successfully identified HGGs with 77.9–99.2% sensitivity and 75.3–100% specificity. In conclusion, the CT-based TA can be a useful tool for differentiating between primary and secondary malignancies. The TA features indicate a more heterogenous content of the HGGs’ PZ, possibly due to the local infiltration of neoplastic cells.