Diffusion- and perfusion-weighted MRI radiomics model may predict isocitrate dehydrogenase (IDH) mutation and tumor aggressiveness in diffuse lower grade glioma

Multiparametric radiomics signature for predicting molecular genotypes in adult-type diffuse gliomas utilizing 18F-FET PET/MRI

PURPOSE

This study aimed to investigate the utility of radiomic features derived from multiparametric O-(2-18 F-fluoroethyl)-L-tyrosine (18F-FET) positron emission tomography (PET)/ magnetic resonance imaging (MRI) for the prediction of molecular genotypes in adult-type diffuse gliomas.

METHODS

This retrospective study analyzed 97 adult-type diffuse glioma patients, divided into 70% training and 30% testing cohorts. Each participant underwent hybrid PET/MRI scans, including FLAIR, 3D T1-CE, apparent diffusion coefficient (ADC), and 18F-FET PET. After the multimodal images were spatially aligned, tumor segmentation was performed on the 18F-FET PET and then applied to other MRI sequences. A total of 994 radiomic features were extracted from these specified modalities. The Naive Bayesian algorithm with five-fold validation was trained to develop prediction models for the IDH, TERT, and MGMT genotypes and to calculate the radiomics score (Rad-Score). The predictive performance of these models was evaluated via receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

RESULTS

The combined model demonstrated superior performance compared to single-modality and MRI (FLAIR + T1-CE + ADC) models in predicting certain genotype statuses in the testing cohort (IDH AUC = 0.97, MGMT AUC = 0.86, TERT AUC = 0.90). The comparisons of the Rad-Score in multimodal models for identifying IDH, TERT, and MGMT showed significant differences (all P < 0.001). Performance of the radiomics signature surpassed that of clinical and conventional radiological factors. DCA indicated that all multimodal models provided good net clinical benefits.

CONCLUSIONS

Multiparametric 18F-FET PET/MRI comprehensively analyzes the structural, proliferative, and metabolic information of adult-type diffuse gliomas, enabling precise preoperative diagnosis of molecular genotypes. This has the potential to aid in the development of personalized clinical treatment plans.

CLINICAL TRIAL NUMBER

Not applicable.

REPAIR: Reciprocal assistance imputation-representation learning for glioma diagnosis with incomplete MRI sequences

The absence of MRI sequences is a common occurrence in clinical practice, posing a significant challenge for prediction modeling of non-invasive diagnosis of glioma (GM) via fusion of multi-sequence MRI. To address this issue, we propose a novel unified reciprocal assistance imputation-representation learning framework (namely REPAIR) for GM diagnosis modeling with incomplete MRI sequences. REPAIR facilitates a cooperative process between missing value imputation and multi-sequence MRI fusion by leveraging existing samples to inform the imputation of missing values. This, in turn, facilitates the learning of a shared latent representation, which reciprocally guides more accurate imputation of missing values. To tailor the learned representation for downstream tasks, a novel ambiguity-aware intercorrelation regularization is introduced to equip REPAIR by correlating imputation ambiguity and its impacts conveying to the learned representation via a fuzzy paradigm. Additionally, a multimodal structural calibration constraint is devised to correct for the structural shift caused by missing data, ensuring structural consistency between the learned representations and the actual data. The proposed methodology is extensively validated on eight GM datasets with incomplete MRI sequences and six clinical datasets from other diseases with incomplete imaging modalities. Comprehensive comparisons with state-of-the-art methods have demonstrated the competitiveness of our approach for GM diagnosis with incomplete MRI sequences, as well as its potential for generalization to various diseases with missing imaging modalities.

The clinical implications and interpretability of computational medical imaging (radiomics) in brain tumors

Radiomics has widespread applications in the field of brain tumor research. However, radiomic analyses often function as a 'black box' due to their use of complex algorithms, which hinders the translation of brain tumor radiomics into clinical applications. In this review, we will elaborate extensively on the application of radiomics in brain tumors. Additionally, we will address the interpretability of handcrafted-feature radiomics and deep learning-based radiomics by integrating biological domain knowledge of brain tumors with interpretability methods. Furthermore, we will discuss the current challenges and prospects concerning the interpretability of brain tumor radiomics. Enhancing the interpretability of radiomics may make it more understandable for physicians, ultimately facilitating its translation into clinical practice. CRITICAL RELEVANCE STATEMENT: The interpretability of brain tumor radiomics empowers neuro-oncologists to make well-informed decisions from radiomic models. KEY POINTS: Radiomics makes a significant impact on the management of brain tumors in several key clinical areas. Transparent models, habitat analysis, and feature attribute explanations can enhance the interpretability of traditional handcrafted-feature radiomics in brain tumors. Various interpretability methods have been applied to explain deep learning-based models; however, there is a lack of biological mechanisms underlying these models.

MRI transformer deep learning and radiomics for predicting IDH wild type TERT promoter mutant gliomas

This study aims to predict IDH wt with TERTp-mut gliomas using multiparametric MRI sequences through a novel fusion model, while matching model classification metrics with patient risk stratification aids in crafting personalized diagnostic and prognosis evaluations.Preoperative T1CE and T2FLAIR sequences from 1185 glioma patients were analyzed. A MultiChannel_2.5D_DL model and a 2D DL model, both based on the cross-scale attention vision transformer (CrossFormer) neural network, along with a Radiomics model, were developed. These were integrated via ensemble learning into a stacking model. The MultiChannel_2.5D_DL model outperformed the 2D_DL and Radiomics models, with AUCs of 0.806-0.870. The stacking model achieved the highest AUC (0.855-0.904) across validation sets. Patients were stratified into high-risk and low-risk groups based on stacking model scores, with significant survival differences observed via Kaplan-Meier analysis and log-rank tests. The stacking model effectively identifies IDH wt TERTp-mutant gliomas and stratifies patient risk, aiding personalized prognosis.

Integrating quantitative DCE-MRI parameters and radiomic features for improved IDH mutation prediction in gliomas

Objectives

To develop and validate a multiparametric prognostic model, incorporating dynamic contrast-enhanced (DCE) quantitative parameters and multi-modality radiomic features, for the accurate identification of isocitrate dehydrogenase 1 (IDH1) mutation status from glioma patients.

Methods

A total of 152 glioma patient data with confirmed IDH1 mutation status were retrospectively collected. A segmentation neural network was used to measure MRI quantitative parameters compared with the empirically oriented ROI selection. Radiomic features, extracted from conventional MR images (T1CE, T2W, and ADC), and DCE quantitative parameter images were combined with MRI quantitative parameters in our research to predict IDH1 mutation status. We constructed and analyzed Clinical Models 1-2 (corresponding to manual and automatic MRI quantitative parameters), Radiomic Feature Models 1-3 (corresponding to structural MRI, DCE, and multi-modality respectively), and a Multivariable Combined Model. We tried different usual classifiers and selected logistic regression according to AUC. Fivefold cross-validation was applied for validation.

Results

The Multivariable Combined Model showed the best prediction performance (AUC, 0.915; 95% CI: 0.87, 0.96) in the validation cohort. The Multivariable Combined Model performed better than Clinical Model 1 and Radiomic Feature Model 1 (DeLong all p < 0.05), and Radiomic Feature Model 3 performed better than Radiomic Feature Model 1 (DeLong p < 0.05).

Conclusions

Compared with the conventional MRI Radiomics and Clinical Models, the Multivariable Combined Model, mainly based on DCE quantitative parameters and multi-modality Radiomics features, is the most promising and deserves attention in the current study.

Detecting B-cell lymphoma-6 overexpression status in primary central nervous system lymphoma using multiparametric MRI-based machine learning

PURPOSE

In primary central nervous system lymphoma (PCNSL), B-cell lymphoma-6 (BCL-6) is an unfavorable prognostic biomarker. We aim to non-invasively detect BCL-6 overexpression in PCNSL patients using multiparametric MRI and machine learning techniques.

METHODS

65 patients (101 lesions) with primary central nervous system lymphoma (PCNSL) diagnosed from January 2013 to July 2023, and all patients were randomly divided into a training set and a validation set according to a ratio of 8 to 2. ADC map derived from DWI (b = 0/1000 s/mm2), fast spin echo T2WI, T2FLAIR, were collected at 3.0 T. A total of 2234 radiomics features from the tumor segmentation area were extracted and LASSO were used to select features. Logistic regression (LR), Naive bayes (NB), Support vector machine (SVM), K-nearest Neighbor, (KNN) and Multilayer Perceptron (MLP), were used for machine learning, and sensitivity, specificity, accuracy F1-score, and area under the curve (AUC) was used to evaluate the detection performance of five classifiers, 6 groups with combinations of different sequences were fitted to 5 classifiers, and optimal classifier was obtained.

RESULTS

BCL-6 status could be identified to varying degrees with 30 models based on radiomics, and model performance could be improved by combining different sequences and classifiers. Support vector machine (SVM) combined with three sequence group had the largest AUC (0.95) in training set and satisfactory AUC (0.87) in validation set.

CONCLUSION

Multiparametric MRI based machine learning is promising in detecting BCL-6 overexpression.

Diffusion imaging in gliomas: how ADC values forecast glioma genetics

Purpose

This study investigates the relationship between diffusion-weighted imaging (DWI) and mean apparent diffusion coefficient (ADC) values in predicting the genetic and molecular features of gliomas. The goal is to enhance non-invasive diagnostic methods and support personalised treatment strategies by clarifying the association between imaging biomarkers and tumour genotypes.

Material and methods

A total of 91 glioma patients treated between August 2023 and March 2024 were included in the analysis. All patients underwent preoperative magnetic resonance imaging (MRI), including DWI, and had available histopathological and genetic test results. Clinical data, tumour characteristics, and genetic markers such as IDH1 mutation, MGMT promoter methylation, EGFR amplification, TERT pathogenic variant, and CDKN2A deletion were collected. Statistical analysis was performed to identify correlations between ADC values, MRI perfusion parameters, and genetic characteristics.

Results

Significant associations were found between lower ADC values and aggressive tumour features, including IDH1-wildtype, MGMT unmethylated status, TERT pathogenic variant, and EGFR amplification. Additionally, distinct ADC patterns were observed in gliomas with CDKN2A, TP53, and PTEN gene deletions. These findings were further supported by contrast enhancement and other MRI parameters, indicating their role in tumour characterisation.

Conclusions

DWI and ADC measurements demonstrate strong potential as non-invasive tools for predicting glioma genetics. These imaging biomarkers can aid in tumour characterisation and provide valuable insights for guiding personalised treatment strategies.

Utilizing machine-learning techniques on MRI radiomics to identify primary tumors in brain metastases

Objective

To develop a machine learning-based clinical and/or radiomics model for predicting the primary site of brain metastases using multiparametric magnetic resonance imaging (MRI).

Materials and methods

A total of 202 patients (87 males, 115 females) with 439 brain metastases were retrospectively included, divided into training sets (brain metastases of lung cancer [BMLC] n = 194, brain metastases of breast cancer [BMBC] n = 108, brain metastases of gastrointestinal tumor [BMGiT] n = 48) and test sets (BMLC n = 50, BMBC n = 27, BMGiT n = 12). A total of 3,404 quantitative image features were obtained through semi-automatic segmentation from MRI images (T1WI, T2WI, FLAIR, and T1-CE). Intra-class correlation coefficient (ICC) was used to examine segmentation stability between two radiologists. Radiomics features were selected using analysis of variance (ANOVA), recursive feature elimination (RFE), and Kruskal-Wallis test. Three machine learning classifiers were used to build the radiomics model, which was validated using five-fold cross-validation on the training set. A comprehensive model combining radiomics and clinical features was established, and the diagnostic performance was compared by area under the curve (AUC) and evaluated in an independent test set.

Results

The radiomics model differentiated BMGiT from BMLC (13 features, AUC = 0.915 ± 0.071) or BMBC (20 features, AUC = 0.954 ± 0.064) with high accuracy, while the classification between BMLC and BMBC was unsatisfactory (11 features, AUC = 0.729 ± 0.114). However, the combined model incorporating radiomics and clinical features improved the predictive performance, with AUC values of 0.965 for BMLC vs. BMBC, 0.991 for BMLC vs. BMGiT, and 0.935 for BMBC vs. BMGiT.

Conclusion

The machine learning-based radiomics model demonstrates significant potential in distinguishing the primary sites of brain metastases, and may assist screening of primary tumor when brain metastasis is suspected whereas history of primary tumor is absent.

Bi-exponential diffusion-weighted imaging for differentiating high-grade gliomas from solitary brain metastases: a VOI-based histogram analysis

This study investigated the use of bi-exponential diffusion-weighted imaging (DWI) combined with structural features to differentiate high-grade glioma (HGG) from solitary brain metastasis (SBM). A total of 57 patients (31 HGG, 26 SBM) who underwent pre-surgical multi-b DWI and structural MRI (T1W, T2W, T1W + C) were included. Volumes of interest (VOI) in the peritumoral edema area (PTEA) and enhanced tumor area (ETA) were selected for analysis. Histogram features of slow diffusion coefficient (Dslow), fast diffusion coefficient (Dfast), and perfusion fraction (frac) were extracted. Results showed that HGG patients had higher skewness of Dfast (P = 0.022) and frac (P = 0.077), higher kurtosis of Dslow (P = 0.019) and frac (P = 0.025), and lower entropy of Dslow (P = 0.005) and frac (P = 0.001) within the ETA. Additionally, HGG exhibited lower mean frac in both ETA (P = 0.007) and PTEA (P = 0.017). Combining skewness of frac in ETA with clear tumor margin enhanced diagnostic performance, achieving an optimal AUC of 0.79. These findings suggest that histogram analysis of diffusion and perfusion characteristics in ETA and structural features can effectively differentiate HGG from SBM.

Comprehensive analysis of transcriptomics and radiomics revealed the potential of TEDC2 as a diagnostic marker for lung adenocarcinoma

Background

Lung adenocarcinoma (LUAD) is a widely occurring cancer with a high death rate. Radiomics, as a high-throughput method, has a wide range of applications in different aspects of the management of multiple cancers. However, the molecular mechanism of LUAD by combining transcriptomics and radiomics in order to probe LUAD remains unclear.

Methods

The transcriptome data and radiomics features of LUAD were extracted from the public database. Subsequently, we used weighted gene co-expression network analysis (WGCNA) and a series of machine learning algorithms including Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression, and Support Vector Machines Recursive Feature Elimination (SVM-RFE) to proceed with the screening of diagnostic genes for LUAD. In addition, the CIBERSORT and ESTIMATE algorithms were utilized to assess the association of these genes with immune profiles. The LASSO algorithm further identified the features most relevant to the expression levels of LUAD diagnostic genes and validated the model based on receiver operating characteristic (ROC), precision-recall (PR), calibration curves and decision curve analysis (DCA) curves. Finally, RT-qPCR, transwell and cell counting kit-8 (CCK8) based assays were performed to assess the expression levels and potential functions of the screened genes in LUAD cell lines.

Results

We screened a total of 214 modular genes with the highest correlation with LUAD samples based on WGCNA, of which 192 genes were shown to be highly expressed in LUAD patients. Subsequently, three machine learning algorithms identified a total of four genes, including UBE2T, TEDC2, RCC1, and FAM136A, as diagnostic molecules for LUAD, and the ROC curves showed that these diagnostic molecules had good diagnostic performance (AUC values of 0.989, 0.989, 989, and 0.987, respectively). The expression of these diagnostic molecules was significantly higher in tumor samples than in normal para-cancerous tissue samples and also correlated significantly and negatively with stromal and immune scores. Specifically, we also constructed a model based on TEDC2 expression consisting of seven radiomic features. Among them, the ROC and PR curves showed that the model had an AUC value of up to 0.96, respectively. Knockdown of TEDC2 slowed down the proliferation, migration and invasion efficiency of LUAD cell lines.

Conclusion

In this study, we screened for diagnostic markers of LUAD and developed a non-invasive radiomics model by innovatively combining transcriptomics and radiomics data. These findings contribute to our understanding of LUAD biology and offer potential avenues for further exploration in clinical practice.

Clinicopathological and radiological characteristics of false-positive and false-negative results in T2-FLAIR mismatch sign of IDH-mutated gliomas

PURPOSE

To explore the clinicopathological and radiological characteristics associated with false-positive and false-negative results in the identification of isocitrate dehydrogenase (IDH) mutations in gliomas using the T2-fluid-attenuated inversion recovery (FLAIR) mismatch sign.

METHODS

In 1515 patients with cerebral gliomas, tumor location, restricted diffusion using diffusion-weighted imaging, and the T2-FLAIR mismatch sign were retrospectively analyzed using preoperative magnetic resonance imaging. Moreover, both the false-positive and false-negative results of the T2-FLAIR mismatch sign were obtained. Univariate and multivariate logistic analyses were performed to evaluate the risk factors associated with false-positive and false-negative results.

RESULTS

The overall false-positive rate was 3.5 % (53/1515), and its independent risk factors were the patient's age (adjusted odds ratio [OR], 0.977; 95 % confidence interval [CI], 0.957, 0.997; P = 0.027) and non-restricted diffusion (adjusted OR, 1.968; 95 % CI, 1.060, 3.652; P = 0.032). The overall false-negative rate was 39.7 % (602/1515); its independent risk factors were the patient's age (adjusted OR, 1.022; 95 % CI, 1.005, 1.038; P = 0.008), 1p/19q co-deletion (adjusted OR, 3.334; 95 % CI, 1.913, 5.810; P < 0.001), and telomerase reverse transcriptase promoter mutation (adjusted OR, 2.004; 95 % CI, 1.181, 3.402; P = 0.010). For the mismatch sign in idiopathic IDH, the area under the receiver operating characteristic curve (AUC) was 0.602. The combined AUC for the T2-FLAIR mismatch sign and risk factors was 0.871.

CONCLUSIONS

Clinicopathological and radiological characteristics can lead to the misinterpretation of IDH status in gliomas based on the T2-FLAIR mismatch sign. However, this can be avoided if careful attention is paid.

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 1: review of current advancements

The development, application, and benchmarking of artificial intelligence (AI) tools to improve diagnosis, prognostication, and therapy in neuro-oncology are increasing at a rapid pace. This Policy Review provides an overview and critical assessment of the work to date in this field, focusing on diagnostic AI models of key genomic markers, predictive AI models of response before and after therapy, and differentiation of true disease progression from treatment-related changes, which is a considerable challenge based on current clinical care in neuro-oncology. Furthermore, promising future directions, including the use of AI for automated response assessment in neuro-oncology, are discussed.

Predicting IDH and ATRX mutations in gliomas from radiomic features with machine learning: a systematic review and meta-analysis

Objective

This systematic review aims to evaluate the quality and accuracy of ML algorithms in predicting ATRX and IDH mutation status in patients with glioma through the analysis of radiomic features extracted from medical imaging. The potential clinical impacts and areas for further improvement in non-invasive glioma diagnosis, classification and prognosis are also identified and discussed.

Methods

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic and Test Accuracy (PRISMA-DTA) statement. Databases including PubMed, Science Direct, CINAHL, Academic Search Complete, Medline, and Google Scholar were searched from inception to April 2024. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess the risk of bias and applicability concerns. Additionally, meta-regression identified covariates contributing to heterogeneity before a subgroup meta-analysis was conducted. Pooled sensitivities, specificities and area under the curve (AUC) values were calculated for the prediction of ATRX and IDH mutations.

Results

Eleven studies involving 1,685 patients with grade I-IV glioma were included. Primary contributors to heterogeneity included the MRI modalities utilised (conventional only vs. combined) and the types of ML models employed. The meta-analysis revealed pooled sensitivities of 0.682 for prediction of ATRX loss and 0.831 for IDH mutations, specificities of 0.874 and 0.828, and AUC values of 0.842 and 0.948, respectively. Interestingly, incorporating semantics and clinical data, including patient demographics, improved the diagnostic performance of ML models.

Conclusions

The high AUC in the prediction of both mutations demonstrates an overall robust diagnostic performance of ML, indicating the potential for accurate, non-invasive diagnosis and precise prognosis. Future research should focus on integrating diverse data types, including advanced imaging, semantics and clinical data while also aiming to standardise the collection and integration of multimodal data. This approach will enhance clinical applicability and consistency.

-New frontiers in domain-inspired radiomics and radiogenomics: increasing role of molecular diagnostics in CNS tumor classification and grading following WHO CNS-5 updates

Gliomas and Glioblastomas represent a significant portion of central nervous system (CNS) tumors associated with high mortality rates and variable prognosis. In 2021, the World Health Organization (WHO) updated its Glioma classification criteria, most notably incorporating molecular markers including CDKN2A/B homozygous deletion, TERT promoter mutation, EGFR amplification, + 7/-10 chromosome copy number changes, and others into the grading and classification of adult and pediatric Gliomas. The inclusion of these markers and the corresponding introduction of new Glioma subtypes has allowed for more specific tailoring of clinical interventions and has inspired a new wave of Radiogenomic studies seeking to leverage medical imaging information to explore the diagnostic and prognostic implications of these new biomarkers. Radiomics, deep learning, and combined approaches have enabled the development of powerful computational tools for MRI analysis correlating imaging characteristics with various molecular biomarkers integrated into the updated WHO CNS-5 guidelines. Recent studies have leveraged these methods to accurately classify Gliomas in accordance with these updated molecular-based criteria based solely on non-invasive MRI, demonstrating the great promise of Radiogenomic tools. In this review, we explore the relative benefits and drawbacks of these computational frameworks and highlight the technical and clinical innovations presented by recent studies in the landscape of fast evolving molecular-based Glioma subtyping. Furthermore, the potential benefits and challenges of incorporating these tools into routine radiological workflows, aiming to enhance patient care and optimize clinical outcomes in the evolving field of CNS tumor management, have been highlighted.

Systematic review and meta-analysis of the prognostic value of 18F-Fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) and/or computed tomography (CT)-based radiomics in head and neck cancer

AIM

Radiomics involves the extraction of quantitative data from medical images to facilitate the diagnosis, prognosis, and staging of tumors. This study provides a comprehensive overview of the efficacy of radiomics in prognostic applications for head and neck cancer (HNC) in recent years. It undertakes a systematic review of prognostic models specific to HNC and conducts a meta-analysis to evaluate their predictive performance.

MATERIALS AND METHODS

This study adhered rigorously to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for literature searches. The literature databases, including PubMed, Embase, Cochrane, and Scopus were systematically searched individually. The methodological quality of the incorporated studies underwent assessment utilizing the radiomics quality score (RQS) tool. A random-effects meta-analysis employing the Harrell concordance index (C-index) was conducted to evaluate the performance of all radiomics models.

RESULTS

Among the 388 studies retrieved, 24 studies encompassing a total of 6,978 cases were incorporated into the systematic review. Furthermore, eight studies, focusing on overall survival as an endpoint, were included in the meta-analysis. The meta-analysis revealed that the estimated random effect of the C-index for all studies utilizing radiomics alone was 0.77 (0.71-0.82), with a substantial degree of heterogeneity indicated by an I2 of 80.17%.

CONCLUSIONS

Based on this review, prognostic modeling utilizing radiomics has demonstrated enhanced efficacy for head and neck cancers; however, there remains room for improvement in this approach. In the future, advancements are warranted in the integration of clinical parameters and multimodal features, balancing multicenter data, as well as in feature screening and model construction within this field.

Ultra-high b-value DWI accurately identifies isocitrate dehydrogenase genotypes and tumor subtypes of adult-type diffuse gliomas

OBJECTIVES

To distinguish isocitrate dehydrogenase (IDH) genotypes and tumor subtypes of adult-type diffuse gliomas based on the fifth edition of the World Health Organization classification of central nervous system tumors (WHO CNS5) in 2021 using standard, high, and ultra-high b-value diffusion-weighted imaging (DWI).

MATERIALS AND METHODS

This prospective study enrolled 70 patients with adult-type diffuse gliomas who underwent multiple b-value DWI. Apparent diffusion coefficient (ADC) values including ADCb500/b1000, ADCb500/b2000, ADCb500/b3000, ADCb500/b4000, ADCb500/b6000, ADCb500/b8000, and ADCb500/b10000 in tumor parenchyma (TP) and contralateral normal-appearing white matter (NAWM) were calculated. The ADC ratios of TP/NAWM were assessed for correlations with IDH genotypes, tumor subtypes, and Ki-67 status; diagnostic performances were compared.

RESULTS

All ADCs were significantly higher in IDH mutant gliomas than in IDH wild-type gliomas (p < 0.01 for all); ADCb500/b8000 had the highest area under the curve (AUC) of 0.866. All ADCs were significantly lower in glioblastoma than in astrocytoma (p < 0.01 for all). ADCs other than ADCb500/b1000 were significantly lower in glioblastoma than in oligodendroglioma (p < 0.05 for all). ADCb500/b8000 and ADCb500/b10000 were significantly higher in oligodendroglioma than in astrocytoma (p = 0.034 and 0.023). The highest AUCs were 0.818 for ADCb500/b6000 when distinguishing glioblastoma from astrocytoma, 0.979 for ADCb500/b8000 and ADCb500/b10000 when distinguishing glioblastoma from oligodendroglioma, and 0.773 for ADCb500/b10000 when distinguishing astrocytoma from oligodendroglioma. Additionally, all ADCs were negatively correlated with Ki-67 status (p < 0.05 for all).

CONCLUSION

Ultra-high b-value DWI can reliably separate IDH genotypes and tumor subtypes of adult-type diffuse gliomas using WHO CNS5 criteria.

CLINICAL RELEVANCE STATEMENT

Ultra-high b-value diffusion-weighted imaging can accurately distinguish isocitrate dehydrogenase genotypes and tumor subtypes of adult-type diffuse gliomas, which may facilitate personalized treatment and prognostic assessment for patients with glioma.

KEY POINTS

• Ultra-high b-value diffusion-weighted imaging can accurately distinguish subtle differences in water diffusion among biological tissues. • Ultra-high b-value diffusion-weighted imaging can reliably separate isocitrate dehydrogenase genotypes and tumor subtypes of adult-type diffuse gliomas. • Compared with standard b-value diffusion-weighted imaging, high and ultra-high b-value diffusion-weighted imaging demonstrate better diagnostic performances.

Radiogenomic profiling of global DNA methylation associated with molecular phenotypes and immune features in glioma

BACKGROUND

The radiogenomic analysis has provided valuable imaging biomarkers with biological insights for gliomas. The radiogenomic markers for molecular profile such as DNA methylation remain to be uncovered to assist the molecular diagnosis and tumor treatment.

METHODS

We apply the machine learning approaches to identify the magnetic resonance imaging (MRI) features that are associated with molecular profiles in 146 patients with gliomas, and the fitting models for each molecular feature (MoRad) are developed and validated. To provide radiological annotations for the molecular profiles, we devise two novel approaches called radiomic oncology (RO) and radiomic set enrichment analysis (RSEA).

RESULTS

The generated MoRad models perform well for profiling each molecular feature with radiomic features, including mutational, methylation, transcriptional, and protein profiles. Among them, the MoRad models have a remarkable performance in quantitatively mapping global DNA methylation. With RO and RSEA approaches, we find that global DNA methylation could be reflected by the heterogeneity in volumetric and textural features of enhanced regions in T2-weighted MRI. Finally, we demonstrate the associations of global DNA methylation with clinicopathological, molecular, and immunological features, including histological grade, mutations of IDH and ATRX, MGMT methylation, multiple methylation-high subtypes, tumor-infiltrating lymphocytes, and long-term survival outcomes.

CONCLUSIONS

Global DNA methylation is highly associated with radiological profiles in glioma. Radiogenomic global methylation is an imaging-based quantitative molecular biomarker that is associated with specific consensus molecular subtypes and immune features.

Targeting Isocitrate Dehydrogenase (IDH) in Solid Tumors: Current Evidence and Future Perspectives

The isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2) enzymes are involved in key metabolic processes in human cells, regulating differentiation, proliferation, and oxidative damage response. IDH mutations have been associated with tumor development and progression in various solid tumors such as glioma, cholangiocarcinoma, chondrosarcoma, and other tumor types and have become crucial markers in molecular classification and prognostic assessment. The intratumoral and serum levels of D-2-hydroxyglutarate (D-2-HG) could serve as diagnostic biomarkers for identifying IDH mutant (IDHmut) tumors. As a result, an increasing number of clinical trials are evaluating targeted treatments for IDH1/IDH2 mutations. Recent studies have shown that the focus of these new therapeutic strategies is not only the neomorphic activity of the IDHmut enzymes but also the epigenetic shift induced by IDH mutations and the potential role of combination treatments. Here, we provide an overview of the current knowledge about IDH mutations in solid tumors, with a particular focus on available IDH-targeted treatments and emerging results from clinical trials aiming to explore IDHmut tumor-specific features and to identify the clinical benefit of IDH-targeted therapies and their combination strategies. An insight into future perspectives and the emerging roles of circulating biomarkers and radiomic features is also included.

Auto-segmentation of Adult-Type Diffuse Gliomas: Comparison of Transfer Learning-Based Convolutional Neural Network Model vs. Radiologists

Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (n = 210) and B (n = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset (n = 197) containing ADC, T2WI, and CE-T1WI, manually annotated by radiologists, and split into training (n = 100) and testing (n = 97) sets. The Dice similarity coefficient (DSC) was used to compare model outputs and manual labels. A third independent radiologist assessed segmentation quality on a semi-quantitative 5-scale score. Differences in DSC between new and recurrent gliomas, and between uni or multifocal gliomas were analyzed using the Mann-Whitney test. Semi-quantitative analyses were compared using the chi-square test. We found that there was good agreement between segmentations from the fine-tuned DL model and ground truth manual segmentations (median DSC: 0.729, std-dev: 0.134). DSC was higher for newly diagnosed (0.807) than recurrent (0.698) (p < 0.001), and higher for unifocal (0.747) than multi-focal (0.613) cases (p = 0.001). Semi-quantitative scores of DL and manual segmentation were not significantly different (mean: 3.567 vs. 3.639; 93.8% vs. 97.9% scoring ≥ 3, p = 0.107). In conclusion, the proposed transfer learning DL performed similarly to human radiologists in glioma segmentation on both structural and ADC sequences. Further improvement in segmenting challenging postoperative and multifocal glioma cases is needed.

Machine-Learning and Radiomics-Based Preoperative Prediction of Ki-67 Expression in Glioma Using MRI Data

BACKGROUND

Gliomas are the most common primary brain tumours and constitute approximately half of all malignant glioblastomas. Unfortunately, patients diagnosed with malignant glioblastomas typically survive for less than a year. In light of this circumstance, genotyping is an effective means of categorising gliomas. The Ki67 proliferation index, a widely used marker of cellular proliferation in clinical contexts, has demonstrated potential for predicting tumour classification and prognosis. In particular, magnetic resonance imaging (MRI) plays a vital role in the diagnosis of brain tumours. Using MRI to extract glioma-related features and construct a machine learning model offers a viable avenue to classify and predict the level of Ki67 expression.

METHODS

This study retrospectively collected MRI data and postoperative immunohistochemical results from 613 glioma patients from the First Affliated Hospital of Nanjing Medical University. Subsequently, we performed registration and skull stripping on the four MRI modalities: T1-weighted (T1), T2-weighted (T2), T1-weighted with contrast enhancement (T1CE), and Fluid Attenuated Inversion Recovery (FLAIR). Each modality's segmentation yielded three distinct tumour regions. Following segmentation, a comprehensive set of features encompassing texture, first-order, and shape attributes were extracted from these delineated regions. Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) algorithm with subsequent sorting to identify the most important features. These selected features were further analysed using correlation analysis to finalise the selection for machine learning model development. Eight models: logistic regression (LR), naive bayes, decision tree, gradient boosting tree, and support vector classification (SVM), random forest (RF), XGBoost, and LightGBM were used to objectively classify Ki67 expression.

RESULTS

In total, 613 patients were enroled in the study, and 24,455 radiomic features were extracted from each patient's MRI. These features were eventually reduced to 36 after LASSO screening, RF importance ranking, and correlation analysis. Among all the tested machine learning models, LR and linear SVM exhibited superior performance. LR achieved the highest area under the curve score of 0.912 ± 0.036, while linear SVM obtained the top accuracy with a score of 0.884 ± 0.031.

CONCLUSION

This study introduced a novel approach for classifying Ki67 expression levels using MRI, which has been proven to be highly effective. With the LR model at its core, our method demonstrated its potential in signalling a promising avenue for future research. This innovative approach of predicting Ki67 expression based on MRI features not only enhances our understanding of cell activity but also represents a significant leap forward in brain glioma research. This underscores the potential of integrating machine learning with medical imaging to aid in the diagnosis and prognosis of complex diseases.

Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT

OBJECTIVES

Preoperative diagnosis of oral ameloblastoma (AME) and odontogenic keratocyst (OKC) has been a challenge in dentistry. This study uses radiomics approaches and machine learning (ML) algorithms to characterize cone-beam CT (CBCT) image features for the preoperative differential diagnosis of AME and OKC and compares ML algorithms to expert radiologists to validate performance.

METHODS

We retrospectively collected the data of 326 patients with AME and OKC, where all diagnoses were confirmed by histopathologic tests. A total of 348 features were selected to train six ML models for differential diagnosis by a 5-fold cross-validation. We then compared the performance of ML-based diagnoses to those of radiologists.

RESULTS

Among the six ML models, XGBoost was effective in distinguishing AME and OKC in CBCT images, with its classification performance outperforming the other models. The mean precision, recall, accuracy, F1-score, and area under the curve (AUC) were 0.900, 0.807, 0.843, 0.841, and 0.872, respectively. Compared to the diagnostics by radiologists, ML-based radiomic diagnostics performed better.

CONCLUSIONS

Radiomic-based ML algorithms allow CBCT images of AME and OKC to be distinguished accurately, facilitating the preoperative differential diagnosis of AME and OKC.

ADVANCES IN KNOWLEDGE

ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC.

7 Tesla magnetic resonance spectroscopic imaging predicting IDH status and glioma grading

INTRODUCTION

With the application of high-resolution 3D 7 Tesla Magnetic Resonance Spectroscopy Imaging (MRSI) in high-grade gliomas, we previously identified intratumoral metabolic heterogeneities. In this study, we evaluated the potential of 3D 7 T-MRSI for the preoperative noninvasive classification of glioma grade and isocitrate dehydrogenase (IDH) status. We demonstrated that IDH mutation and glioma grade are detectable by ultra-high field (UHF) MRI. This technique might potentially optimize the perioperative management of glioma patients.

METHODS

We prospectively included 36 patients with WHO 2021 grade 2-4 gliomas (20 IDH mutated, 16 IDH wildtype). Our 7 T 3D MRSI sequence provided high-resolution metabolic maps (e.g., choline, creatine, glutamine, and glycine) of these patients' brains. We employed multivariate random forest and support vector machine models to voxels within a tumor segmentation, for classification of glioma grade and IDH mutation status.

RESULTS

Random forest analysis yielded an area under the curve (AUC) of 0.86 for multivariate IDH classification based on metabolic ratios. We distinguished high- and low-grade tumors by total choline (tCho) / total N-acetyl-aspartate (tNAA) ratio difference, yielding an AUC of 0.99. Tumor categorization based on other measured metabolic ratios provided comparable accuracy.

CONCLUSIONS

We successfully classified IDH mutation status and high- versus low-grade gliomas preoperatively based on 7 T MRSI and clinical tumor segmentation. With this approach, we demonstrated imaging based tumor marker predictions at least as accurate as comparable studies, highlighting the potential application of MRSI for pre-operative tumor classifications.

MRI-based intratumoral and peritumoral radiomics for preoperative prediction of glioma grade: a multicenter study

Background

Accurate preoperative prediction of glioma is crucial for developing individualized treatment decisions and assessing prognosis. In this study, we aimed to establish and evaluate the value of integrated models by incorporating the intratumoral and peritumoral features from conventional MRI and clinical characteristics in the prediction of glioma grade.

Methods

A total of 213 glioma patients from two centers were included in the retrospective analysis, among which, 132 patients were classified as the training cohort and internal validation set, and the remaining 81 patients were zoned as the independent external testing cohort. A total of 7728 features were extracted from MRI sequences and various volumes of interest (VOIs). After feature selection, 30 radiomic models depended on five sets of machine learning classifiers, different MRI sequences, and four different combinations of predictive feature sources, including features from the intratumoral region only, features from the peritumoral edema region only, features from the fusion area including intratumoral and peritumoral edema region (VOI-fusion), and features from the intratumoral region with the addition of features from peritumoral edema region (feature-fusion), were established to select the optimal model. A nomogram based on the clinical parameter and optimal radiomic model was constructed for predicting glioma grade in clinical practice.

Results

The intratumoral radiomic models based on contrast-enhanced T1-weighted and T2-flair sequences outperformed those based on a single MRI sequence. Moreover, the internal validation and independent external test underscored that the XGBoost machine learning classifier, incorporating features extracted from VOI-fusion, showed superior predictive efficiency in differentiating between low-grade gliomas (LGG) and high-grade gliomas (HGG), with an AUC of 0.805 in the external test. The radiomic models of VOI-fusion yielded higher prediction efficiency than those of feature-fusion. Additionally, the developed nomogram presented an optimal predictive efficacy with an AUC of 0.825 in the testing cohort.

Conclusion

This study systematically investigated the effect of intratumoral and peritumoral radiomics to predict glioma grading with conventional MRI. The optimal model was the XGBoost classifier coupled radiomic model based on VOI-fusion. The radiomic models that depended on VOI-fusion outperformed those that depended on feature-fusion, suggesting that peritumoral features should be rationally utilized in radiomic studies.

Diffusion- and Perfusion-Weighted MRI Radiomics for Survival Prediction in Patients with Lower-Grade Gliomas

PURPOSE

Lower-grade gliomas of histologic grades 2 and 3 follow heterogenous clinical outcomes, which necessitates risk stratification. This study aimed to evaluate whether diffusion-weighted and perfusion-weighted MRI radiomics allow overall survival (OS) prediction in patients with lower-grade gliomas and investigate its prognostic value.

MATERIALS AND METHODS

In this retrospective study, radiomic features were extracted from apparent diffusion coefficient, relative cerebral blood volume map, and Ktrans map in patients with pathologically confirmed lower-grade gliomas (January 2012-February 2019). The radiomics risk score (RRS) calculated from selected features constituted a radiomics model. Multivariable Cox regression analysis, including clinical features and RRS, was performed. The models' integrated area under the receiver operating characteristic curves (iAUCs) were compared. The radiomics model combined with clinical features was presented as a nomogram.

RESULTS

The study included 129 patients (median age, 44 years; interquartile range, 37-57 years; 63 female): 90 patients for training set and 39 patients for test set. The RRS was an independent risk factor for OS with a hazard ratio of 6.01. The combined clinical and radiomics model achieved superior performance for OS prediction compared to the clinical model in both training (iAUC, 0.82 vs. 0.72, p=0.002) and test sets (0.88 vs. 0.76, p=0.04). The radiomics nomogram combined with clinical features exhibited good agreement between the actual and predicted OS with C-index of 0.83 and 0.87 in the training and test sets, respectively.

CONCLUSION

Adding diffusion- and perfusion-weighted MRI radiomics to clinical features improved survival prediction in lower-grade glioma.

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes

OBJECTIVES

Radiomic features have demonstrated encouraging results for non-invasive detection of molecular biomarkers, but the lack of guidelines for pre-processing MRI-data has led to poor generalizability. Here, we assessed the influence of different MRI-intensity normalization techniques on the performance of radiomics-based models for predicting molecular glioma subtypes.

METHODS

Preoperative MRI-data from n = 615 patients with newly diagnosed glioma and known isocitrate dehydrogenase (IDH) and 1p/19q status were pre-processed using four different methods: no normalization (naive), N4 bias field correction (N4), N4 followed by either WhiteStripe (N4/WS), or z-score normalization (N4/z-score). A total of 377 Image-Biomarker-Standardisation-Initiative-compliant radiomic features were extracted from each normalized data, and 9 different machine-learning algorithms were trained for multiclass prediction of molecular glioma subtypes (IDH-mutant 1p/19q codeleted vs. IDH-mutant 1p/19q non-codeleted vs. IDH wild type). External testing was performed in public glioma datasets from UCSF (n = 410) and TCGA (n = 160).

RESULTS

Support vector machine yielded the best performance with macro-average AUCs of 0.84 (naive), 0.84 (N4), 0.87 (N4/WS), and 0.87 (N4/z-score) in the internal test set. Both N4/WS and z-score outperformed the other approaches in the external UCSF and TCGA test sets with macro-average AUCs ranging from 0.85 to 0.87, replicating the performance of the internal test set, in contrast to macro-average AUCs ranging from 0.19 to 0.45 for naive and 0.26 to 0.52 for N4 alone.

CONCLUSION

Intensity normalization of MRI data is essential for the generalizability of radiomic-based machine-learning models. Specifically, both N4/WS and N4/z-score approaches allow to preserve the high model performance, yielding generalizable performance when applying the developed radiomic-based machine-learning model in an external heterogeneous, multi-institutional setting.

CLINICAL RELEVANCE STATEMENT

Intensity normalization such as N4/WS or N4/z-score can be used to develop reliable radiomics-based machine learning models from heterogeneous multicentre MRI datasets and provide non-invasive prediction of glioma subtypes.

KEY POINTS

• MRI-intensity normalization increases the stability of radiomics-based models and leads to better generalizability. • Intensity normalization did not appear relevant when the developed model was applied to homogeneous data from the same institution. • Radiomic-based machine learning algorithms are a promising approach for simultaneous classification of IDH and 1p/19q status of glioma.

Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment

This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent a significant global health issue. AI has brought transformative innovations to brain tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, and treatment planning. Assessing its influence across all facets of malignant brain tumor management- diagnosis, prognosis, and therapy- AI models outperform human evaluations in terms of accuracy and specificity. Their ability to discern molecular aspects from imaging may reduce reliance on invasive diagnostics and may accelerate the time to molecular diagnoses. The review covers AI techniques, from classical machine learning to deep learning, highlighting current applications and challenges. Promising directions for future research include multimodal data integration, generative AI, large medical language models, precise tumor delineation and characterization, and addressing racial and gender disparities. Adaptive personalized treatment strategies are also emphasized for optimizing clinical outcomes. Ethical, legal, and social implications are discussed, advocating for transparency and fairness in AI integration for neuro-oncology and providing a holistic understanding of its transformative impact on patient care.

Radiomics advances in the evaluation of pancreatic cystic neoplasms

With the development of medical imaging, the detection rate of pancreatic cystic neoplasms (PCNs) has increased greatly. Serous cystic neoplasm, solid pseudopapillary neoplasm, intraductal papillary mucinous neoplasm and mucinous cystic neoplasm are the main subtypes of PCN, and their treatment options vary greatly due to the different biological behaviours of the tumours. Different from conventional qualitative imaging evaluation, radiomics is a promising noninvasive approach for the diagnosis, classification, and risk stratification of diseases involving high-throughput extraction of medical image features. We present a review of radiomics in the diagnosis of serous cystic neoplasm and mucinous cystic neoplasm, risk classification of intraductal papillary mucinous neoplasm and prediction of solid pseudopapillary neoplasm invasiveness compared to conventional imaging diagnosis. Radiomics is a promising tool in the field of medical imaging, providing a noninvasive, high-performance model for preoperative diagnosis and risk stratification of PCNs and improving prospects regarding management of these diseases. Further studies are warranted to investigate MRI image radiomics in connection with PCNs to improve the diagnosis and treatment strategies in the management of PCN patients.

Development and External Validation of an MRI-based Radiomics Nomogram to Distinguish Circumscribed Astrocytic Gliomas and Diffuse Gliomas: A Multicenter Study

RATIONALE AND OBJECTIVES

The 5th edition of the World Health Organization classification of tumors of the Central Nervous System (WHO CNS) has introduced the term "diffuse" and its counterpart "circumscribed" to the category of gliomas. This study aimed to develop and validate models for distinguishing circumscribed astrocytic gliomas (CAGs) from diffuse gliomas (DGs).

MATERIALS AND METHODS

We retrospectively analyzed magnetic resonance imaging (MRI) data from patients with CAGs and DGs across three institutions. After tumor segmentation, three volume of interest (VOI) types were obtained: VOItumor and peritumor, VOIwhole, and VOIinterface. Clinical and combined models (incorporating radiomics and clinical features) were also established. To address imbalances in training dataset, Synthetic Minority Oversampling Technique was employed.

RESULTS

A total of 475 patients (DGs: n = 338, CAGs: n = 137) were analyzed. The VOIinterface model demonstrated the best performance for differentiating CAGs from DGs, achieving an area under the curve (AUC) of 0.806 and area under the precision-recall curve (PRAUC)of 0.894 in the cross-validation set. Using analysis of variance (ANOVA) feature selector and Support Vector Machine (SVM) classifier, seven features were selected. The model achieved an AUC and AUPRC of 0.912 and 0.972 in the internal validation dataset, and 0.897 and 0.930 in the external validation dataset. The combined model, incorporating interface radiomics and clinical features, showed improved performance in the external validation set, with an AUC of 0.94 and PRAUC of 0.959.

CONCLUSION

Radiomics models incorporating the peritumoral area demonstrate greater potential for distinguishing CAGs from DGs compared to intratumoral models. These findings may hold promise for evaluating tumor nature before surgery and improving clinical management of glioma patients.

Development of End-to-End AI-Based MRI Image Analysis System for Predicting IDH Mutation Status of Patients with Gliomas: Multicentric Validation

Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.

A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma

OBJECTIVES

To develop a high-accuracy MRI-based deep learning method for predicting cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion status in isocitrate dehydrogenase (IDH)-mutant astrocytoma.

METHODS

Multiparametric brain MRI data and corresponding genomic information of 234 subjects (111 positives for CDKN2A/B homozygous deletion and 123 negatives for CDKN2A/B homozygous deletion) were obtained from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) respectively. Two independent multi-sequence networks (ResFN-Net and FN-Net) are built on the basis of ResNet and ConvNeXt network combined with attention mechanism to classify CDKN2A/B homozygous deletion status using MR images including contrast-enhanced T1-weighted imaging (CE-T1WI) and T2-weighted imaging (T2WI). The performance of the network is summarized by three-way cross-validation; ROC analysis is also performed.

RESULTS

The average cross-validation accuracy (ACC) of ResFN-Net is 0.813. The average cross-validation area under curve (AUC) of ResFN-Net is 0.8804. The average cross-validation ACC and AUC of FN-Net is 0.9236 and 0.9704, respectively. Comparing all sequence combinations of the two networks (ResFN-Net and FN-Net), the sequence combination of CE-T1WI and T2WI performed the best, and the ACC and AUC were 0.8244, 0.8975 and 0.8971, 0.9574, respectively.

CONCLUSIONS

The FN-Net deep learning networks based on ConvNeXt network achieved promising performance for predicting CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma.

CLINICAL RELEVANCE STATEMENT

A novel deep learning network (FN-Net) based on preoperative MRI was developed to predict the CDKN2A/B homozygous deletion status. This network has the potential to be a practical tool for the noninvasive characterization of CDKN2A/B in glioma to support personalized classification and treatment planning.

KEY POINTS

• CDKN2A/B homozygous deletion status is an important marker for glioma grading and prognosis. • An MRI-based deep learning approach was developed to predict CDKN2A/B homozygous deletion status. • The predictive performance based on ConvNeXt network was better than that of ResNet network.

Radiogenomic landscape: Assessment of specific phagocytosis regulators in lower-grade gliomas

Genome-wide CRISPR-Cas9 knockout screens have emerged as a powerful method for identifying key genes driving tumor growth. The aim of this study was to explore the phagocytosis regulators (PRs) specifically associated with lower-grade glioma (LGG) using the CRISPR-Cas9 screening database. Identifying these core PRs could lead to novel therapeutic targets and pave the way for a non-invasive radiogenomics approach to assess LGG patients' prognosis and treatment response. We selected 24 PRs that were overexpressed and lethal in LGG for analysis. The identified PR subtypes (PRsClusters, geneClusters, and PRs-score models) effectively predicted clinical outcomes in LGG patients. Immune response markers, such as CTLA4, were found to be significantly associated with PR-score. Nine radiogenomics models using various machine learning classifiers were constructed to uncover survival risk. The area under the curve (AUC) values for these models in the test and training datasets were 0.686 and 0.868, respectively. The CRISPR-Cas9 screen identified novel prognostic radiogenomics biomarkers that correlated well with the expression status of specific PR-related genes in LGG patients. These biomarkers successfully stratified patient survival outcomes and treatment response using The Cancer Genome Atlas (TCGA) database. This study has important implications for the development of precise clinical treatment strategies and holds promise for more accurate therapeutic approaches for LGG patients in the future.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

PURPOSE OF REVIEW

To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption.

RECENT FINDINGS

A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation.

SUMMARY

While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.

Coordinatized lesion location analysis empowering ROI-based radiomics diagnosis on brain gliomas

OBJECTIVES

To assess the value of coordinatized lesion location analysis (CLLA), in empowering ROI-based imaging diagnosis of gliomas by improving accuracy and generalization performances.

METHODS

In this retrospective study, pre-operative contrasted T1-weighted and T2-weighted MR images were obtained from patients with gliomas from three centers: Jinling Hospital, Tiantan Hospital, and the Cancer Genome Atlas Program. Based on CLLA and ROI-based radiomic analyses, a fusion location-radiomics model was constructed to predict tumor grades, isocitrate dehydrogenase (IDH) status, and overall survival (OS). An inter-site cross-validation strategy was used for assessing the performances of the fusion model on accuracy and generalization with the value of area under the curve (AUC) and delta accuracy (ACC) (ACCtesting-ACCtraining). Comparisons of diagnostic performances were performed between the fusion model and the other two models constructed with location and radiomics analysis using DeLong's test and Wilcoxon signed ranks test.

RESULTS

A total of 679 patients (mean age, 50 years ± 14 [standard deviation]; 388 men) were enrolled. Based on tumor location probabilistic maps, fusion location-radiomics models (averaged AUC values of grade/IDH/OS: 0.756/0.748/0.768) showed the highest accuracy in contrast to radiomics models (0.731/0.686/0.716) and location models (0.706/0.712/0.740). Notably, fusion models ([median Delta ACC: - 0.125, interquartile range: 0.130]) demonstrated improved generalization than that of radiomics model ([- 0.200, 0.195], p = 0.018).

CONCLUSIONS

CLLA could empower ROI-based radiomics diagnosis of gliomas by improving the accuracy and generalization of the models.

CLINICAL RELEVANCE STATEMENT

This study proposed a coordinatized lesion location analysis for glioma diagnosis, which could improve the performances of the conventional ROI-based radiomics model in accuracy and generalization.

KEY POINTS

• Using coordinatized lesion location analysis, we mapped anatomic distribution patterns of gliomas with specific pathological and clinical features and constructed glioma prediction models. • We integrated coordinatized lesion location analysis into ROI-based analysis of radiomics to propose new fusion location-radiomics models. • Fusion location-radiomics models, with the advantages of being less influenced by variabilities, improved accuracy, and generalization performances of ROI-based radiomics models on predicting the diagnosis of gliomas.

A novel deep learning model for glioma epilepsy associated with the identification of human cytomegalovirus infection injuries based on head MR

Purpose

In this study, a deep learning model was established based on head MRI to predict a crucial evaluation parameter in the assessment of injuries resulting from human cytomegalovirus infection: the occurrence of glioma-related epilepsy. The relationship between glioma and epilepsy was investigated, which serves as a significant indicator of labor force impairment.

Methods

This study enrolled 142 glioma patients, including 127 from Shengjing Hospital of China Medical University, and 15 from the Second Affiliated Hospital of Dalian Medical University. T1 and T2 sequence images of patients' head MRIs were utilized to predict the occurrence of glioma-associated epilepsy. To validate the model's performance, the results of machine learning and deep learning models were compared. The machine learning model employed manually annotated texture features from tumor regions for modeling. On the other hand, the deep learning model utilized fused data consisting of tumor-containing T1 and T2 sequence images for modeling.

Results

The neural network based on MobileNet_v3 performed the best, achieving an accuracy of 86.96% on the validation set and 75.89% on the test set. The performance of this neural network model significantly surpassed all the machine learning models, both on the validation and test sets.

Conclusion

In this study, we have developed a neural network utilizing head MRI, which can predict the likelihood of glioma-associated epilepsy in untreated glioma patients based on T1 and T2 sequence images. This advancement provides forensic support for the assessment of injuries related to human cytomegalovirus infection.

Deep wavelet scattering orthogonal fusion network for glioma IDH mutation status prediction

Accurately predicting the isocitrate dehydrogenase (IDH) mutation status of gliomas is greatly significant for formulating appropriate treatment plans and evaluating the prognoses of gliomas. Although existing studies can accurately predict the IDH mutation status of gliomas based on multimodal magnetic resonance (MR) images and machine learning methods, most of these methods cannot fully explore multimodal information and effectively predict IDH status for datasets acquired from multiple centers. To address this issue, a novel wavelet scattering (WS)-based orthogonal fusion network (WSOFNet) was proposed in this work to predict the IDH mutation status of gliomas from multiple centers. First, transformation-invariant features were extracted from multimodal MR images with a WS network, and then the multimodal WS features were used instead of the original images as the inputs of WSOFNet and were fully fused through an adaptive multimodal feature fusion module (AMF2M) and an orthogonal projection module (OPM). Finally, the fused features were input into a fully connected classifier to predict IDH mutation status. In addition, to achieve improved prediction accuracy, four auxiliary losses were also used in the feature extraction modules. The comparison results showed that the prediction area under the curve (AUC) of WSOFNet on a single-center dataset was 0.9966 and that on a multicenter dataset was approximately 0.9655, which was at least 3.9% higher than that of state-of-the-art methods. Moreover, the ablation experimental results also proved that the adaptive multimodal feature fusion strategy based on orthogonal projection could effectively improve the prediction performance of the model, especially for an external validation dataset.

Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports

OBJECTIVES

To evaluate the performance of natural language processing (NLP) models to predict isocitrate dehydrogenase (IDH) mutation status in diffuse glioma using routine MR radiology reports.

MATERIALS AND METHODS

This retrospective, multi-center study included consecutive patients with diffuse glioma with known IDH mutation status from May 2009 to November 2021 whose initial MR radiology report was available prior to pathologic diagnosis. Five NLP models (long short-term memory [LSTM], bidirectional LSTM, bidirectional encoder representations from transformers [BERT], BERT graph convolutional network [GCN], BioBERT) were trained, and area under the receiver operating characteristic curve (AUC) was assessed to validate prediction of IDH mutation status in the internal and external validation sets. The performance of the best performing NLP model was compared with that of the human readers.

RESULTS

A total of 1427 patients (mean age ± standard deviation, 54 ± 15; 779 men, 54.6%) with 720 patients in the training set, 180 patients in the internal validation set, and 527 patients in the external validation set were included. In the external validation set, BERT GCN showed the highest performance (AUC 0.85, 95% CI 0.81-0.89) in predicting IDH mutation status, which was higher than LSTM (AUC 0.77, 95% CI 0.72-0.81; p = .003) and BioBERT (AUC 0.81, 95% CI 0.76-0.85; p = .03). This was higher than that of a neuroradiologist (AUC 0.80, 95% CI 0.76-0.84; p = .005) and a neurosurgeon (AUC 0.79, 95% CI 0.76-0.84; p = .04).

CONCLUSION

BERT GCN was externally validated to predict IDH mutation status in patients with diffuse glioma using routine MR radiology reports with superior or at least comparable performance to human reader.

CLINICAL RELEVANCE STATEMENT

Natural language processing may be used to extract relevant information from routine radiology reports to predict cancer genotype and provide prognostic information that may aid in guiding treatment strategy and enabling personalized medicine.

KEY POINTS

• A transformer-based natural language processing (NLP) model predicted isocitrate dehydrogenase mutation status in diffuse glioma with an AUC of 0.85 in the external validation set. • The best NLP models were superior or at least comparable to human readers in both internal and external validation sets. • Transformer-based models showed higher performance than conventional NLP model such as long short-term memory.

Application of radiomics-based multiomics combinations in the tumor microenvironment and cancer prognosis

The advent of immunotherapy, a groundbreaking advancement in cancer treatment, has given rise to the prominence of the tumor microenvironment (TME) as a critical area of research. The clinical implications of an improved understanding of the TME are significant and far-reaching. Radiomics has been increasingly utilized in the comprehensive assessment of the TME and cancer prognosis. Similarly, the advancement of pathomics, which is based on pathological images, can offer additional insights into the panoramic view and microscopic information of tumors. The combination of pathomics and radiomics has revolutionized the concept of a "digital biopsy". As genomics and transcriptomics continue to evolve, integrating radiomics with genomic and transcriptomic datasets can offer further insights into tumor and microenvironment heterogeneity and establish correlations with biological significance. Therefore, the synergistic analysis of digital image features (radiomics, pathomics) and genetic phenotypes (genomics) can comprehensively decode and characterize the heterogeneity of the TME as well as predict cancer prognosis. This review presents a comprehensive summary of the research on important radiomics biomarkers for predicting the TME, emphasizing the interplay between radiomics, genomics, transcriptomics, and pathomics, as well as the application of multiomics in decoding the TME and predicting cancer prognosis. Finally, we discuss the challenges and opportunities in multiomics research. In conclusion, this review highlights the crucial role of radiomics and multiomics associations in the assessment of the TME and cancer prognosis. The combined analysis of radiomics, pathomics, genomics, and transcriptomics is a promising research direction with substantial research significance and value for comprehensive TME evaluation and cancer prognosis assessment.

Decision system for extent of resection in WHO grade 3 gliomas: a Chinese Glioma Genome Atlas database analysis

BACKGROUND

Extensive surgical resection has been found to be associated with longer survival in patients with gliomas, but the interactive prognostic value of molecular pathology of the surgical resection is unclear. This study evaluated the impact of molecular pathology and clinical characteristics on the surgical benefit in WHO grade 3 IDH-mutant gliomas.

METHODS

Clinical and pathological information of 246 patients with WHO grade 3 IDH-mutant gliomas were collected from the Chinese Glioma Genome Atlas database (2006-2020). The role of the extent of resection on overall survival, stratified by molecular pathology and clinical characteristics, was investigated. We then assessed prognostic factors using a univariate log-rank test and multivariate Cox proportional hazards model in the subgroups.

RESULTS

The extent of resection was an independent prognostic factor in the entire cohort, even when adjusted for molecular pathology. Gross total resection was found to be associated with longer survival in all patients and in the astrocytoma group but not in the oligodendroglioma group. Compared with subtotal resections, gross total resections resulted in a longer survival time for astrocytoma patients aged ≤ 45 years. However, there was no survival benefit from total resection in patients with astrocytoma aged > 45 years.

CONCLUSIONS

Extensive resection benefits only a proportion of patients with WHO grade 3 IDH-mutant gliomas. Younger patients with astrocytomas had survival benefits from extensive resection. In addition to clinical characteristics (especially age), molecular pathology impacted prognosis in patients with gliomas. Our findings provide guiding information to neurosurgeons while planning surgeries.

Dynamic contrast-enhanced MRI radiomics model predicts epidermal growth factor receptor amplification in glioblastoma, IDH-wildtype

PURPOSE

To develop and validate a dynamic contrast-enhanced (DCE) MRI-based radiomics model to predict epidermal growth factor receptor (EGFR) amplification in patients with glioblastoma, isocitrate dehydrogenase (IDH) wildtype.

METHODS

Patients with pathologically confirmed glioblastoma, IDH wildtype, from January 2015 to December 2020, with an EGFR amplification status, were included. Patients who did not undergo DCE or conventional brain MRI were excluded. Patients were categorized into training and test sets by a ratio of 7:3. DCE MRI data were used to generate volume transfer constant (Ktrans) and extracellular volume fraction (Ve) maps. Ktrans, Ve, and conventional MRI were then used to extract the radiomics features, from which the prediction models for EGFR amplification status were developed and validated.

RESULTS

A total of 190 patients (mean age, 59.9; male, 55.3%), divided into training (n = 133) and test (n = 57) sets, were enrolled. In the test set, the radiomics model using the Ktrans map exhibited the highest area under the receiver operating characteristic curve (AUROC), 0.80 (95% confidence interval [CI], 0.65-0.95). The AUROC for the Ve map-based and conventional MRI-based models were 0.74 (95% CI, 0.58-0.90) and 0.76 (95% CI, 0.61-0.91).

CONCLUSION

The DCE MRI-based radiomics model that predicts EGFR amplification in glioblastoma, IDH wildtype, was developed and validated. The MRI-based radiomics model using the Ktrans map has higher AUROC than conventional MRI.

Deep-learning and conventional radiomics to predict IDH genotyping status based on magnetic resonance imaging data in adult diffuse glioma

Objectives

In adult diffuse glioma, preoperative detection of isocitrate dehydrogenase (IDH) status helps clinicians develop surgical strategies and evaluate patient prognosis. Here, we aim to identify an optimal machine-learning model for prediction of IDH genotyping by combining deep-learning (DL) signatures and conventional radiomics (CR) features as model predictors.

Methods

In this study, a total of 486 patients with adult diffuse gliomas were retrospectively collected from our medical center (n=268) and the public database (TCGA, n=218). All included patients were randomly divided into the training and validation sets by using nested 10-fold cross-validation. A total of 6,736 CR features were extracted from four MRI modalities in each patient, namely T1WI, T1CE, T2WI, and FLAIR. The LASSO algorithm was performed for CR feature selection. In each MRI modality, we applied a CNN+LSTM-based neural network to extract DL features and integrate these features into a DL signature after the fully connected layer with sigmoid activation. Eight classic machine-learning models were analyzed and compared in terms of their prediction performance and stability in IDH genotyping by combining the LASSO-selected CR features and integrated DL signatures as model predictors. In the validation sets, the prediction performance was evaluated by using accuracy and the area under the curve (AUC) of the receiver operating characteristics, while the model stability was analyzed by using the relative standard deviation of the AUC (RSDAUC). Subgroup analyses of DL signatures and CR features were also individually conducted to explore their independent prediction values.

Results

Logistic regression (LR) achieved favorable prediction performance (AUC: 0.920 ± 0.043, accuracy: 0.843 ± 0.044), whereas support vector machine with the linear kernel (l-SVM) displayed low prediction performance (AUC: 0.812 ± 0.052, accuracy: 0.821 ± 0.050). With regard to stability, LR also showed high robustness against data perturbation (RSDAUC: 4.7%). Subgroup analyses showed that DL signatures outperformed CR features (DL, AUC: 0.915 ± 0.054, accuracy: 0.835 ± 0.061, RSDAUC: 5.9%; CR, AUC: 0.830 ± 0.066, accuracy: 0.771 ± 0.051, RSDAUC: 8.0%), while DL and DL+CR achieved similar prediction results.

Conclusion

In IDH genotyping, LR is a promising machine-learning classification model. Compared with CR features, DL signatures exhibit markedly superior prediction values and discriminative capability.

Bibliometric research on the developments of artificial intelligence in radiomics toward nervous system diseases

Background

The growing interest suggests that the widespread application of radiomics has facilitated the development of neurological disease diagnosis, prognosis, and classification. The application of artificial intelligence methods in radiomics has increasingly achieved outstanding prediction results in recent years. However, there are few studies that have systematically analyzed this field through bibliometrics. Our destination is to study the visual relationships of publications to identify the trends and hotspots in radiomics research and encourage more researchers to participate in radiomics studies.

Methods

Publications in radiomics in the field of neurological disease research can be retrieved from the Web of Science Core Collection. Analysis of relevant countries, institutions, journals, authors, keywords, and references is conducted using Microsoft Excel 2019, VOSviewer, and CiteSpace V. We analyze the research status and hot trends through burst detection.

Results

On October 23, 2022, 746 records of studies on the application of radiomics in the diagnosis of neurological disorders were retrieved and published from 2011 to 2023. Approximately half of them were written by scholars in the United States, and most were published in Frontiers in Oncology, European Radiology, Cancer, and SCIENTIFIC REPORTS. Although China ranks first in the number of publications, the United States is the driving force in the field and enjoys a good academic reputation. NORBERT GALLDIKS and JIE TIAN published the most relevant articles, while GILLIES RJ was cited the most. RADIOLOGY is a representative and influential journal in the field. "Glioma" is a current attractive research hotspot. Keywords such as "machine learning," "brain metastasis," and "gene mutations" have recently appeared at the research frontier.

Conclusion

Most of the studies focus on clinical trial outcomes, such as the diagnosis, prediction, and prognosis of neurological disorders. The radiomics biomarkers and multi-omics studies of neurological disorders may soon become a hot topic and should be closely monitored, particularly the relationship between tumor-related non-invasive imaging biomarkers and the intrinsic micro-environment of tumors.

Advanced MR Techniques for Preoperative Glioma Characterization: Part 2

Preoperative clinical MRI protocols for gliomas, brain tumors with dismal outcomes due to their infiltrative properties, still rely on conventional structural MRI, which does not deliver information on tumor genotype and is limited in the delineation of diffuse gliomas. The GliMR COST action wants to raise awareness about the state of the art of advanced MRI techniques in gliomas and their possible clinical translation. This review describes current methods, limits, and applications of advanced MRI for the preoperative assessment of glioma, summarizing the level of clinical validation of different techniques. In this second part, we review magnetic resonance spectroscopy (MRS), chemical exchange saturation transfer (CEST), susceptibility-weighted imaging (SWI), MRI-PET, MR elastography (MRE), and MR-based radiomics applications. The first part of this review addresses dynamic susceptibility contrast (DSC) and dynamic contrast-enhanced (DCE) MRI, arterial spin labeling (ASL), diffusion-weighted MRI, vessel imaging, and magnetic resonance fingerprinting (MRF). EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Radiomic features from dynamic susceptibility contrast perfusion-weighted imaging improve the three-class prediction of molecular subtypes in patients with adult diffuse gliomas

OBJECTIVES

To investigate whether radiomic features extracted from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) can improve the prediction of the molecular subtypes of adult diffuse gliomas, and to further develop and validate a multimodal radiomic model by integrating radiomic features from conventional and perfusion MRI.

METHODS

We extracted 1197 radiomic features from each sequence of conventional MRI and DSC-PWI, respectively. The Boruta algorithm was used for feature selection and combination, and a three-class random forest method was applied to construct the models. We also constructed a combined model by integrating radiomic features and clinical metrics. The models' diagnostic performance for discriminating the molecular subtypes (IDH wild type [IDHwt], IDH mutant and 1p/19q-noncodeleted [IDHmut-noncodel], and IDH mutant and 1p/19q-codeleted [IDHmut-codel]) was compared using AUCs in the validation set.

RESULTS

We included 272 patients (training set, n = 166; validation set, n = 106) with grade II-IV gliomas (mean age, 48.7 years; range, 19-77 years). The proportions of the molecular subtypes were 66.2% IDHwt, 15.1% IDHmut-noncodel, and 18.8% IDHmut-codel. Nineteen radiomic features (13 from conventional MRI and 6 from DSC-PWI) were selected to build the multimodal radiomic model. In the validation set, the multimodal radiomic model showed better performance than the conventional radiomic model did in predicting the IDHwt and IDHmut-codel subtypes, which was comparable to the conventional radiomic model in predicting the IDHmut-noncodel subtype. The multimodal radiomic model yielded similar performance as the combined model in predicting the three molecular subtypes.

CONCLUSIONS

Adding DSC-PWI to conventional MRI can improve molecular subtype prediction in patients with diffuse gliomas.

KEY POINTS

• The multimodal radiomic model outperformed conventional MRI when predicting both the IDH wild type and IDH mutant and 1p/19q-codeleted subtypes of gliomas. • The multimodal radiomic model showed comparable performance to the combined model in the prediction of the three molecular subtypes. • Radiomic features from T1-weighted gadolinium contrast-enhanced and relative cerebral blood volume images played an important role in the prediction of molecular subtypes.

Prediction of the Molecular Subtype of IDH Mutation Combined with MGMT Promoter Methylation in Gliomas via Radiomics Based on Preoperative MRI

BACKGROUND

The molecular subtype of IDH mut combined with MGMT meth in gliomas suggests a good prognosis and potential benefit from TMZ chemotherapy. The aim of this study was to establish a radiomics model to predict this molecular subtype.

METHOD

The preoperative MR images and genetic data of 498 patients with gliomas were retrospectively collected from our institution and the TCGA/TCIA dataset. A total of 1702 radiomics features were extracted from the tumour region of interest (ROI) of CE-T1 and T2-FLAIR MR images. Least absolute shrinkage and selection operator (LASSO) and logistic regression were used for feature selection and model building. Receiver operating characteristic (ROC) curves and calibration curves were used to evaluate the predictive performance of the model.

RESULTS

Regarding clinical variables, age and tumour grade were significantly different between the two molecular subtypes in the training, test and independent validation cohorts (p < 0.05). The areas under the curve (AUCs) of the radiomics model based on 16 selected features in the SMOTE training cohort, un-SMOTE training cohort, test set and independent TCGA/TCIA validation cohort were 0.936, 0.932, 0.916 and 0.866, respectively, and the corresponding F1-scores were 0.860, 0.797, 0.880 and 0.802. The AUC of the independent validation cohort increased to 0.930 for the combined model when integrating the clinical risk factors and radiomics signature.

CONCLUSIONS

radiomics based on preoperative MRI can effectively predict the molecular subtype of IDH mut combined with MGMT meth.

An initial study on the predictive value using multiple MRI characteristics for Ki-67 labeling index in glioma

BACKGROUND AND PURPOSE

Ki-67 labeling index (LI) is an important indicator of tumor cell proliferation in glioma, which can only be obtained by postoperative biopsy at present. This study aimed to explore the correlation between Ki-67 LI and apparent diffusion coefficient (ADC) parameters and to predict the level of Ki-67 LI noninvasively before surgery by multiple MRI characteristics.

METHODS

Preoperative MRI data of 166 patients with pathologically confirmed glioma in our hospital from 2016 to 2020 were retrospectively analyzed. The cut-off point of Ki-67 LI for glioma grading was defined. The differences in MRI characteristics were compared between the low and high Ki-67 LI groups. The receiver operating characteristic (ROC) curve was used to estimate the accuracy of each ADC parameter in predicting the Ki-67 level, and finally a multivariate logistic regression model was constructed based on the results of ROC analysis.

RESULTS

ADC_min, ADC_mean, rADC_min, rADC_mean and Ki-67 LI showed a negative correlation (r = - 0.478, r = - 0.369, r = - 0.488, r = - 0.388, all P < 0.001). The Ki-67 LI of low-grade gliomas (LGGs) was different from that of high-grade gliomas (HGGs), and the cut-off point of Ki-67 LI for distinguishing LGGs from HGGs was 9.5%, with an area under the ROC curve (AUROC) of 0.962 (95%CI 0.933-0.990). The ADC parameters in the high Ki-67 group were significantly lower than those in the low Ki-67 group (all P < 0.05). The peritumoral edema (PTE) of gliomas in the high Ki-67 LI group was higher than that in the low Ki-67 LI group (P < 0.05). The AUROC of Ki-67 LI level assessed by the multivariate logistic regression model was 0.800 (95%CI 0.721-0.879).

CONCLUSIONS

There was a negative correlation between ADC parameters and Ki-67 LI, and the multivariate logistic regression model combined with peritumoral edema and ADC parameters could improve the prediction ability of Ki-67 LI.

Glioma radiogenomics and artificial intelligence: road to precision cancer medicine

Radiogenomics refers to the study of the relationship between imaging phenotypes and gene expression patterns/molecular characteristics, which might allow improved diagnosis, decision-making, and predicting patient outcomes in the context of multiple diseases. Central nervous system (CNS) tumours contribute to significant cancer-related mortality in the present age. Although historically CNS neoplasms were classified and graded based on microscopic appearance, there was discordance between two histologically similar tumours that showed varying prognosis and behaviour, attributable to their molecular signatures. These led to the incorporation of molecular markers in the classification of CNS neoplasms. Meanwhile, advancements in imaging technology such as diffusion-based imaging (including tractography), perfusion, and spectroscopy in addition to the conventional imaging of glial neoplasms, have opened an avenue for radiogenomics. This review touches upon the schema of the current classification of gliomas, concepts behind molecular markers, and parameters that are used in radiogenomics to characterise gliomas and the role of artificial intelligence for the same. Further, the role of radiomics in the grading of brain tumours, prediction of treatment response and prognosis has been discussed. Use of automated and semi-automated tumour segmentation for radiotherapy planning and follow-up has also been discussed briefly.

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.

Predicting IDH Mutation Status in Low-Grade Gliomas Based on Optimal Radiomic Features Combined with Multi-Sequence Magnetic Resonance Imaging

The IDH somatic mutation status is an important basis for the diagnosis and classification of gliomas. We proposed a "6-Step" general radiomics model to noninvasively predict the IDH mutation status by simultaneously tuning combined multi-sequence MRI and optimizing the full radiomics processing pipeline. Radiomic features (n = 3776) were extracted from multi-sequence MRI (T1, T2, FLAIR, and T1Gd) in low-grade gliomas (LGGs), and a total of 45,360 radiomics pipeline were investigated according to different settings. The predictive ability of the general radiomics model was evaluated with regards to accuracy, stability, and efficiency. Based on numerous experiments, we finally reached an optimal pipeline for classifying IDH mutation status, namely the T2+FLAIR combined multi-sequence with the wavelet image filter, mean data normalization, PCC dimension reduction, RFE feature selection, and SVM classifier. The mean and standard deviation of AUC, accuracy, sensitivity, and specificity were 0.873 ± 0.05, 0.876 ± 0.09, 0.875 ± 0.11, and 0.877 ± 0.15, respectively. Furthermore, 14 radiomic features that best distinguished the IDH mutation status of the T2+FLAIR multi-sequence were analyzed, and the gray level co-occurrence matrix (GLCM) features were shown to be of high importance. Apart from the promising prediction of the molecular subtypes, this study also provided a general tool for radiomics investigation.