Diffusion kurtosis imaging in evaluating gliomas: different region of interest selection methods on time efficiency, measurement repeatability, and diagnostic ability

Super-resolution reconstruction improves multishell diffusion: using radiomics to predict adult-type diffuse glioma IDH and grade

Objectives

Multishell diffusion scanning is limited by low spatial resolution. We sought to improve the resolution of multishell diffusion images through deep learning-based super-resolution reconstruction (SR) and subsequently develop and validate a prediction model for adult-type diffuse glioma, isocitrate dehydrogenase status and grade 2/3 tumors.

Materials and methods

A simple diffusion model (DTI) and three advanced diffusion models (DKI, MAP, and NODDI) were constructed based on multishell diffusion scanning. Migration was performed with a generative adversarial network based on deep residual channel attention networks, after which images with 2x and 4x resolution improvements were generated. Radiomic features were used as inputs, and diagnostic models were subsequently constructed via multiple pipelines.

Results

This prospective study included 90 instances (median age, 54.5 years; 39 men) diagnosed with adult-type diffuse glioma. Images with both 2x- and 4x-improved resolution were visually superior to the original images, and the 2x-improved images allowed better predictions than did the 4x-improved images (P<.001). A comparison of the areas under the curve among the multiple pipeline-constructed models revealed that the advanced diffusion models did not have greater diagnostic performance than the simple diffusion model (P>.05). The NODDI model constructed with 2x-improved images had the best performance in predicting isocitrate dehydrogenase status (AUC_validation=0.877; Brier score=0.132). The MAP model constructed with the original images performed best in classifying grade 2 and grade 3 tumors (AUC_validation=0.806; Brier score=0.168).

Conclusion

SR improves the resolution of multishell diffusion images and has different advantages in achieving different goals and creating different target diffusion models.

Identification of T2W hypointense ring as a novel noninvasive indicator for glioma grade and IDH genotype

BACKGROUND

This study aimed to evaluate the T2W hypointense ring and T2-FLAIR mismatch signs in gliomas and use these signs to construct prediction models for glioma grading and isocitrate dehydrogenase (IDH) mutation status.

METHODS

Two independent radiologists retrospectively evaluated 207 glioma patients to assess the presence of T2W hypointense ring and T2-FLAIR mismatch signs. The inter-rater reliability was calculated using the Cohen's kappa statistic. Two logistic regression models were constructed to differentiate glioma grade and predict IDH genotype noninvasively, respectively. Receiver operating characteristic (ROC) analysis was used to evaluate the developed models.

RESULTS

Of the 207 patients enrolled (119 males and 88 females, mean age 51.6 ± 14.8 years), 45 cases were low-grade gliomas (LGGs), 162 were high-grade gliomas (HGGs), 55 patients had IDH mutations, and 116 were IDH wild-type. The number of T2W hypointense ring signs was higher in HGGs compared to LGGs (p < 0.001) and higher in the IDH wild-type group than in the IDH mutant group (p < 0.001). There were also significant differences in T2-FLAIR mismatch signs between HGGs and LGGs, as well as between IDH mutant and wild-type groups (p < 0.001). Two predictive models incorporating T2W hypointense ring, absence of T2-FLAIR mismatch, and age were constructed. The area under the ROC curve (AUROC) was 0.940 for predicting HGGs (95% CI = 0.907-0.972) and 0.830 for differentiating IDH wild-type (95% CI = 0.757-0.904).

CONCLUSIONS

The combination of T2W hypointense ring, absence of T2-FLAIR mismatch, and age demonstrate good predictive capability for HGGs and IDH wild-type. These findings suggest that MRI can be used noninvasively to predict glioma grading and IDH mutation status, which may have important implications for patient management and treatment planning.

Hematologic cancer diagnosis and classification using machine and deep learning: State-of-the-art techniques and emerging research directives

Hematology is the study of diagnosis and treatment options for blood diseases, including cancer. Cancer is considered one of the deadliest diseases across all age categories. Diagnosing such a deadly disease at the initial stage is essential to cure the disease. Hematologists and pathologists rely on microscopic evaluation of blood or bone marrow smear images to diagnose blood-related ailments. The abundance of overlapping cells, cells of varying densities among platelets, non-illumination levels, and the amount of red and white blood cells make it more difficult to diagnose illness using blood cell images. Pathologists are required to put more effort into the traditional, time-consuming system. Nowadays, it becomes possible with machine learning and deep learning techniques, to automate the diagnostic processes, categorize microscopic blood cells, and improve the accuracy of the procedure and its speed as the models developed using these methods may guide an assisting tool. In this article, we have acquired, analyzed, scrutinized, and finally selected around 57 research papers from various machine learning and deep learning methodologies that have been employed in the diagnosis of leukemia and its classification over the past 20 years, which have been published between the years 2003 and 2023 by PubMed, IEEE, Science Direct, Google Scholar and other pertinent sources. Our primary emphasis is on evaluating the advantages and limitations of analogous research endeavors to provide a concise and valuable research directive that can be of significant utility to fellow researchers in the field.

Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2-4 glioma patients: a deep Radiomics Approach

BACKGROUND

The role of isocitrate dehydrogenase (IDH) mutation status for glioma stratification and prognosis is established. While structural magnetic resonance image (MRI) is a promising biomarker, it may not be sufficient for non-invasive characterisation of IDH mutation status. We investigated the diagnostic value of combined diffusion tensor imaging (DTI) and structural MRI enhanced by a deep radiomics approach based on convolutional neural networks (CNNs) and support vector machine (SVM), to determine the IDH mutation status in Central Nervous System World Health Organization (CNS WHO) grade 2-4 gliomas.

METHODS

This retrospective study analyzed the DTI-derived fractional anisotropy (FA) and mean diffusivity (MD) images and structural images including fluid attenuated inversion recovery (FLAIR), non-enhanced T1-, and T2-weighted images of 206 treatment-naïve gliomas, including 146 IDH mutant and 60 IDH-wildtype ones. The lesions were manually segmented by experienced neuroradiologists and the masks were applied to the FA and MD maps. Deep radiomics features were extracted from each subject by applying a pre-trained CNN and statistical description. An SVM classifier was applied to predict IDH status using imaging features in combination with demographic data.

RESULTS

We comparatively assessed the CNN-SVM classifier performance in predicting IDH mutation status using standalone and combined structural and DTI-based imaging features. Combined imaging features surpassed stand-alone modalities for the prediction of IDH mutation status [area under the curve (AUC) = 0.846; sensitivity = 0.925; and specificity = 0.567]. Importantly, optimal model performance was noted following the addition of demographic data (patients' age) to structural and DTI imaging features [area under the curve (AUC) = 0.847; sensitivity = 0.911; and specificity = 0.617].

CONCLUSIONS

Imaging features derived from DTI-based FA and MD maps combined with structural MRI, have superior diagnostic value to that provided by standalone structural or DTI sequences. In combination with demographic information, this CNN-SVM model offers a further enhanced non-invasive prediction of IDH mutation status in gliomas.

Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas-A Comparative Study With Diffusion Kurtosis Imaging (DKI)

BACKGROUND

Glioma classification affects treatment and prognosis. Reliable imaging methods for preoperatively evaluating gliomas are essential.

PURPOSE

To evaluate tumor multiregional mean apparent propagator (MAP) features in glioma diagnosis and to compare those with diffusion-kurtosis imaging (DKI).

STUDY TYPE

Retrospective study.

SUBJECTS

70 untreated glioma patients (31 LGGs (low-grade gliomas), 34 women; mean age, 47 ± 12 years, training (60%, n = 42) and testing cohorts (40%, n = 28)).

FIELD STRENGTH/SEQUENCE

3-T, diffusion-MRI using q-space Cartesian grid sampling with 11 different b-values.

ASSESSMENT

Tumor multiregional MAP (mean squared displacement (MSD); q-space inverse variance (QIV); non-Gaussianity (NG); axial/radial non-Gaussianity (NGAx, NGRad); return-to-origin/axis/plane probability (RTOP, RTAP, and RTPP)); and DKI metrics (axial/mean/radial kurtosis (AK, MK, and RK)) on tumor parenchyma (TP) and peritumoral areas (PT) in histopathologically gliomas grading and genotyping were assessed.

STATISTICAL TESTS

Mann-Whitney U; Kruskal-Wallis; Benjamini-Hochberg; Bonferroni-correction; receiver operating curve (ROC) and area under curve (AUC); DeLong's test; Random Forest (RF). P value<0.05 was considered statistically significant after multiple comparisons correction.

RESULTS

Compared with LGGs, MSD, and QIV were significantly lower in TP, whereas NG, NGAx, NGRad, RTOP, RTAP, RTPP, and DKI metrics were significantly higher in HGGs (high-grade gliomas) (P ≤ 0.007), as well as in isocitrate-dehydrogenase (IDH)-mutated than IDH-wildtype gliomas (P ≤ 0.039). These trends were reversed for PT (tumor grades, P ≤ 0.011; IDH-mutation status, P ≤ 0.012). ROC analysis showed that, in TP, DKI metrics performed best in TP (AUC 0.83), whereas in PT, RTPP performed best (AUC 0.77) in glioma grading. AK performed best in TP (AUC 0.77), whereas MSD and RTPP performed best in PT (AUC 0.73) in IDH genotyping. Further RF analysis with DKI and MAP demonstrated good performance in grading (AUC 0.91, Accuracy 82%) and IDH genotyping (AUC 0.87, Accuracy 79%).

DATA CONCLUSION

Tumor multiregional MAP features could effectively evaluate gliomas. The performance of MAP may be similar to DKI in TP, while in PT, MAP may outperform DKI.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Diffusion heterogeneity and vascular perfusion in tumor and peritumoral areas for prediction of overall survival in patients with high-grade glioma

OBJECTIVE

To evaluation of diffusion heterogeneity and vascular perfusion in tumor and peritumoral areas for prognostic prediction in high-grade glioma (HGG, WHO III/IV grade).

METHODS

Forty patients with HGG underwent diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), and arterial spin labeling (ASL) MRI before operation. After normalization, the parameters were divided into diffusion heterogeneity parameters (rD, rMD, rMK, rKr, rKa) and vascular perfusion parameters (rD*, rF, rCBF). Univariate and multivariate Cox regression analyses were used to evaluate associations between overall survival (OS) and the above parameters, clinical factors, and IDH1 status. The Mann-Whitney test was used to evaluate differences in the parameters between different IDH1 states.

RESULTS

In the univariate Cox regression analysis, OS was significantly associated with tumor resection range, IDH1 status, tumor heterogeneity parameters (rD, rMD, rMK, rKr, rKa), and rCBF in tumor area(all p < 0.05). In addition, rD and rCBF measured in the peritumoral region were also predictors of poor OS (both p < 0.01). Multivariate Cox regression analysis indicated that rMK in the tumor area and rCBF in the peritumoral area (hazard ratio = 7.900 and 5.466, respectively, for each 0.1 increase in the normalized value) were independent predictors of OS.

CONCLUSION

The rMK of tumor area and rCBF of peritumoral area had independent predictive value for OS in patients with HGG.

ADVANCES IN KNOWLEDGE

This study explored useful imaging biomarkers from the diffusion heterogeneity and vascular perfusion of tumor and peritumoral areas in HGG, which is useful to help clinician to make precise therapeutic plans, and predict the prognostic for glioma patients.

Quantitative susceptibility mapping evaluation of glioma

OBJECTIVES

To comprehensively evaluate the glioma using quantitative susceptibility mapping (QSM).

MATERIALS AND METHODS

Forty-two patients (18 women; mean age, 45 years) with pathologically confirmed gliomas were retrospectively included. All the patients underwent conventional and advanced MRI examinations (QSM, DWI, MRS, etc.). Five patients underwent paired QSM (pre- and post-enhancement). Four Visually Accessible Rembrandt Image (VASARI) features and intratumoural susceptibility signal (ITSS) were observed. Three ROIs each were manually drawn separately in the tumour parenchyma with relatively high and low magnetic susceptibility. The association between the tumour's magnetic susceptibility and other MRI parameters was also analysed.

RESULTS

Morphologically, gliomas with heterogeneous ITSS were more similar to high-grade gliomas (p = 0.006, AUC: 0.72, sensitivity: 70%, and specificity: 73%). Heterogeneous ITSS was significantly associated with tumour haemorrhage, necrosis, diffusion restriction, and avid enhancement but did not change between pre- and post-enhanced QSM. Quantitatively, tumour parenchyma magnetic susceptibility had limited value in grading gliomas and identifying IDH mutation status, whereas the relatively low magnetic susceptibility of the tumour parenchyma helped identify oligodendrogliomas in IDH mutated gliomas (AUC = 0.78) with high specificity (100%). The relatively high tumour magnetic susceptibility significantly increased after enhancement (p = 0.039). Additionally, we found that the magnetic susceptibility of the tumour parenchyma was significantly correlated with ADC (r = 0.61) and Cho/NAA (r = 0.40).

CONCLUSIONS

QSM is a promising candidate for the comprehensive evaluation of gliomas, except for IDH mutation status. The magnetic susceptibility of tumour parenchyma may be affected by tumour cell proliferation.

KEY POINTS

• Morphologically, gliomas with a heterogeneous intratumoural susceptibility signal (ITSS) are more similar to high-grade gliomas (p = 0.006; AUC, 0.72; sensitivity, 70%; and specificity, 73%). Heterogeneous ITSS was significantly associated with tumour haemorrhage, necrosis, diffusion restriction, and avid enhancement but did not change between pre- and post-enhanced QSM. • Tumour parenchyma's relatively low magnetic susceptibility helped identify oligodendroglioma with high specificity. • Tumour parenchyma magnetic susceptibility was significantly correlated with ADC (r = 0.61) and Cho/NAA (r = 0.40).

Advances in molecular and imaging biomarkers in lower-grade gliomas

INTRODUCTION

Lower-grade (grade 2-3) gliomas (LGGs) constitutes a group of primary brain tumors with variable clinical behaviors and treatment responses. Recent advancements in molecular biology have redefined their classification, and novel imaging modalities emerged for the noninvasive diagnosis and follow-up.

AREAS COVERED

This review comprehensively analyses the current knowledge on molecular and imaging biomarkers in LGGs. Key molecular alterations, such as IDH mutations and 1p/19q codeletion, are discussed for their prognostic and predictive implications in guiding treatment decisions. Moreover, the authors explore theranostic biomarkers for the potential of tailored therapies. Additionally, they also describe the utility of advanced imaging modalities, including widely available techniques, as dynamic susceptibility contrast perfusion-weighted imaging and less validated, emerging approaches, for the noninvasive LGGs characterization and follow-up.

EXPERT OPINION

The integration of molecular markers enhanced the stratification of LGGs, leading to the new concept of integrated histomolecular classification. While the IDH mutation is an established key prognostic and predictive marker, recent results from IDH inhibitors trials showed its potential value as a theranostic marker. In this setting, advanced MRI techniques such as 2-D-hydroxyglutarate spectroscopy are very promising for the noninvasive diagnosis and monitoring of LGGs. This progress offers exciting prospects for personalized medicine and improved treatment outcomes in LGGs.

Apparent Diffusion Coefficient in the Differentiation of Common Pediatric Brain Tumors in the Posterior Fossa: Different Region-of-Interest Selection Methods for Time Efficiency, Measurement Reproducibility, and Diagnostic Utility

OBJECTIVES

This study aimed to explore the diagnostic ability of apparent diffusion coefficient (ADC) values obtained from different region of interest (ROI) measurements in tumor parenchyma for differentiating posterior fossa tumors (PFTs) and the correlations between ADC values and Ki-67.

METHODS

Seventy-three pediatric patients with PFTs who underwent conventional diffusion-weighted imaging were recruited in this study. Five different ROIs were manually drawn by 2 radiologists (ROI-polygon, ROI-3 sections, ROI-3-5 ovals, ROI-more ovals, and ROI-whole). The interreader/intrareader repeatability, time required, diagnostic ability, and Ki-67 correlation analysis of the ADC values based on these ROI strategies were calculated.

RESULTS

Both interreader and intrareader reliabilities were excellent for ADC values among the different ROI strategies (intraclass correlation coefficient, 0.899-0.992). There were statistically significant differences in time consumption among the 5 ROI selection methods ( P < 0.001). The time required for the ROI-3-5 ovals was the shortest (32.23 ± 5.14 seconds), whereas the time required for the ROI-whole was the longest (204.52 ± 92.34 seconds). The diagnostic efficiency of the ADC values showed no significant differences among the different ROI measurements ( P > 0.05). The ADC value was negatively correlated with Ki-67 ( r = -0.745 to -0.798, all P < 0.0001).

CONCLUSIONS

The ROI-3-5 ovals method has the best interobserver repeatability, the shortest amount of time spent, and the best diagnostic ability. Thus, it is considered an effective measurement to produce ADC values in the evaluation of pediatric PFTs.

Combining Multi-Shell Diffusion with Conventional MRI Improves Molecular Diagnosis of Diffuse Gliomas with Deep Learning

The WHO classification since 2016 confirms the importance of integrating molecular diagnosis for prognosis and treatment decisions of adult-type diffuse gliomas. This motivates the development of non-invasive diagnostic methods, in particular MRI, to predict molecular subtypes of gliomas before surgery. At present, this development has been focused on deep-learning (DL)-based predictive models, mainly with conventional MRI (cMRI), despite recent studies suggesting multi-shell diffusion MRI (dMRI) offers complementary information to cMRI for molecular subtyping. The aim of this work is to evaluate the potential benefit of combining cMRI and multi-shell dMRI in DL-based models. A model implemented with deep residual neural networks was chosen as an illustrative example. Using a dataset of 146 patients with gliomas (from grade 2 to 4), the model was trained and evaluated, with nested cross-validation, on pre-operative cMRI, multi-shell dMRI, and a combination of the two for the following classification tasks: (i) IDH-mutation; (ii) 1p/19q-codeletion; and (iii) three molecular subtypes according to WHO 2021. The results from a subset of 100 patients with lower grades gliomas (2 and 3 according to WHO 2016) demonstrated that combining cMRI and multi-shell dMRI enabled the best performance in predicting IDH mutation and 1p/19q codeletion, achieving an accuracy of 75 ± 9% in predicting the IDH-mutation status, higher than using cMRI and multi-shell dMRI separately (both 70 ± 7%). Similar findings were observed for predicting the 1p/19q-codeletion status, with the accuracy from combining cMRI and multi-shell dMRI (72 ± 4%) higher than from each modality used alone (cMRI: 65 ± 6%; multi-shell dMRI: 66 ± 9%). These findings remain when we considered all 146 patients for predicting the IDH status (combined: 81 ± 5% accuracy; cMRI: 74 ± 5%; multi-shell dMRI: 73 ± 6%) and for the diagnosis of the three molecular subtypes according to WHO 2021 (combined: 60 ± 5%; cMRI: 57 ± 8%; multi-shell dMRI: 56 ± 7%). Together, these findings suggest that combining cMRI and multi-shell dMRI can offer higher accuracy than using each modality alone for predicting the IDH and 1p/19q status and in diagnosing the three molecular subtypes with DL-based models.

Diagnostic performance of gliomas grading and IDH status decoding A comparison between 3D amide proton transfer APT and four diffusion-weighted MRI models

BACKGROUND

The focus of neuro-oncology research has changed from histopathologic grading to molecular characteristics, and medical imaging routinely follows this change.

PURPOSE

To compare the diagnostic performance of amide proton transfer (APT) and four diffusion models in gliomas grading and isocitrate dehydrogenase (IDH) genotype.

STUDY TYPE

Prospective.

POPULATION

A total of 62 participants (37 males, 25 females; mean age, 52 ± 13 years) whose IDH genotypes were mutant in 6 of 14 grade II gliomas, 8 of 20 of grade III gliomas, and 4 of 28 grade IV gliomas.

FIELD STRENGTH/SEQUENCE

APT imaging using sampling perfection with application optimized contrasts by using different flip angle evolutions (SPACE) and DWI with q-space Cartesian grid sampling were acquired at 3 T.

ASSESSMENT

The ability of diffusion kurtosis imaging, diffusion kurtosis imaging, neurite orientation dispersion and density imaging (NODDI), mean apparent propagator (MAP), and APT imaging for glioma grade and IDH status were assessed, with histopathological grade and genetic testing used as a reference standard. Regions of interest (ROIs) were drawn by two neuroradiologists after consensus.

STATISTICAL TESTS

T-test and Mann-Whitney U test; one-way analysis of variance (ANOVA); receiver operating curve (ROC) and area under the curve (AUC); DeLong test. P value < 0.05 was considered statistically significant.

RESULTS

Compared with IDH-mutant gliomas, IDH-wildtype gliomas showed a significantly higher mean, 5th-percentile (APT₅ ), and 95th-percentile from APTw, the 95th-percentile value of axial, mean, and radial diffusivity from DKI, and 95th-percentile value of isotropic volume fraction from NODDI, and no significantly different parameters from DTI and MAP (P = 0.075-0.998). The combined APT model showed a significantly wider area under the curve (AUC 0.870) for IDH status, when compared with DKI and NODDI. APT₅ was significantly different between two of the three groups (glioma II vs. glioma III vs. glioma IV: 1.35 ± 0.75 vs. 2.09 ± 0.93 vs. 2.71 ± 0.81).

DATA CONCLUSION

APT has higher diagnostic accuracy than DTI, DKI, MAP, and NODDI in glioma IDH genotype. APT₅ can effectively identify both tumor grading and IDH genotyping, making it a promising biomarker for glioma classification.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Advancements in Neuroimaging to Unravel Biological and Molecular Features of Brain Tumors

Simple Summary

Advanced neuroimaging is gaining increasing relevance for the characterization and the molecular profiling of brain tumor tissue. On one hand, for some tumor types, the most widespread advanced techniques, investigating diffusion and perfusion features, have been proven clinically feasible and rather robust for diagnosis and prognosis stratification. In addition, 2-hydroxyglutarate spectroscopy, for the first time, offers the possibility to directly measure a crucial molecular marker. On the other hand, numerous innovative approaches have been explored for a refined evaluation of tumor microenvironments, particularly assessing microstructural and microvascular properties, and the potential applications of these techniques are vast and still to be fully explored.

Abstract

In recent years, the clinical assessment of primary brain tumors has been increasingly dependent on advanced magnetic resonance imaging (MRI) techniques in order to infer tumor pathophysiological characteristics, such as hemodynamics, metabolism, and microstructure. Quantitative radiomic data extracted from advanced MRI have risen as potential in vivo noninvasive biomarkers for predicting tumor grades and molecular subtypes, opening the era of “molecular imaging” and radiogenomics. This review presents the most relevant advancements in quantitative neuroimaging of advanced MRI techniques, by means of radiomics analysis, applied to primary brain tumors, including lower-grade glioma and glioblastoma, with a special focus on peculiar oncologic entities of current interest. Novel findings from diffusion MRI (dMRI), perfusion-weighted imaging (PWI), and MR spectroscopy (MRS) are hereby sifted in order to evaluate the role of quantitative imaging in neuro-oncology as a tool for predicting molecular profiles, stratifying prognosis, and characterizing tumor tissue microenvironments. Furthermore, innovative technological approaches are briefly addressed, including artificial intelligence contributions and ultra-high-field imaging new techniques. Lastly, after providing an overview of the advancements, we illustrate current clinical applications and future perspectives.