Radiomics Strategy for Molecular Subtype Stratification of Lower-Grade Glioma: Detecting IDH and TP53 Mutations Based on Multimodal MRI

Association of Pathological Features and Multiparametric MRI-Based Radiomics With TP53-Mutated Prostate Cancer

BACKGROUND

TP53 mutations are associated with prostate cancer (PCa) prognosis and therapy.

PURPOSE

To develop TP53 mutation classification models for PCa using MRI radiomics and clinicopathological features.

STUDY TYPE

Retrospective.

POPULATION

388 patients with PCa from two centers (Center 1: 281 patients; Center 2: 107 patients). Cases from Center 1 were randomly divided into training and internal validation sets (7:3). Cases from Center 2 were used for external validation.

FIELD STRENGTH/SEQUENCE

3.0T/T2-weighted imaging, dynamic contrast-enhanced imaging, diffusion-weighted imaging.

ASSESSMENT

Each patient's index tumor lesion was manually delineated on the above MRI images. Five clinicopathological and 428 radiomics features were obtained from each lesion. Radiomics features were selected by least absolute shrinkage and selection operator and binary logistic regression (LR) analysis, while clinicopathological features were selected using Mann-Whitney U test. Radiomics models were constructed using LR, support vector machine (SVM), and random forest (RF) classifiers. Clinicopathological-radiomics combined models were constructed using the selected radiomics and clinicopathological features with the aforementioned classifiers.

STATISTICAL TESTS

Mann-Whitney U test. Receiver operating characteristic (ROC) curve analysis and area under the curve (AUC). P value <0.05 indicates statistically significant.

RESULTS

In the internal validation set, the radiomics model had an AUC of 0.74 with the RF classifier, which was significantly higher than LR (AUC = 0.61), but similar to SVM (AUC = 0.69; P = 0.422). For the combined model, the AUC of RF model was 0.84, which was significantly higher than LR (0.64), but similar to SVM (0.80; P = 0.548). Both the combined RF and combined SVM models showed significantly higher AUCs than the radiomics models. In the external validation set, the combined RF and combined SVM models showed AUCs of 0.83 and 0.82.

DATA CONCLUSION

Pathological-radiomics combined models with RF, SVM show the association of TP53 mutations and pathological-radiomics features of PCa.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Diagnostic accuracy of a machine learning-based radiomics approach of MR in predicting IDH mutations in glioma patients: a systematic review and meta-analysis

Objectives

To assess the diagnostic accuracy of machine learning (ML)-based radiomics for predicting isocitrate dehydrogenase (IDH) mutations in patients with glioma.

Methods

A systematic search of PubMed, Web of Science, Embase, and the Cochrane Library from inception to 1 September 2023, was conducted to collect all articles investigating the diagnostic performance of ML for the prediction of IDH mutations in gliomas. Two reviewers independently screened all papers for eligibility. Methodological quality and risk of bias were assessed using the METhodological RadiomICs Score and Quality Assessment of Diagnostic Accuracy Studies-2, respectively. The pooled sensitivity, specificity, and 95% confidence intervals were calculated, and the area under the receiver operating characteristic curve (AUC) was obtained.

Results

In total, 14 original articles assessing 1740 patients with gliomas were included. The AUC of ML for predicting IDH mutation was 0.90 (0.87-0.92). The pooled sensitivity, specificity, and diagnostic odds ratio were 0.83 (0.71-0.90), 0.84 (0.74-0.90), and 25 (12,50) respectively. In subgroup analyses, modeling methods, glioma grade, and the combination of magnetic resonance imaging and clinical features affected the diagnostic performance in predicting IDH mutations in gliomas.

Conclusion

ML-based radiomics demonstrated excellent diagnostic performance in predicting IDH mutations in gliomas. Factors influencing the diagnosis included the modeling methods employed, glioma grade, and whether the model incorporated clinical features.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/#myprospero, PROSPERO registry (CRD 42023395444).

Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning

OBJECTIVES

Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status.

MATERIAL AND METHODS

In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data.

RESULTS

Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power.

CONCLUSIONS

Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

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.

Multimodal MRI-based radiomic nomogram for predicting telomerase reverse transcriptase promoter mutation in IDH-wildtype histological lower-grade gliomas

The presence of TERTp mutation in isocitrate dehydrogenase-wildtype (IDHwt) histologically lower-grade glioma (LGA) has been linked to a poor prognosis. In this study, we aimed to develop and validate a radiomic nomogram based on multimodal MRI for predicting TERTp mutations in IDHwt LGA. One hundred and nine IDH wildtype glioma patients (TERTp-mutant, 78; TERTp-wildtype, 31) with clinical, radiomic, and molecular information were collected and randomly divided into training and validation set. Clinical model, fusion radiomic model, and combined radiomic nomogram were constructed for the discrimination. Radiomic features were screened with 3 algorithms (Wilcoxon rank sum test, elastic net, and the recursive feature elimination) and the clinical characteristics of combined radiomic nomogram were screened by the Akaike information criterion. Finally, receiver operating characteristic curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis were utilized to assess these models. Fusion radiomic model with 4 radiomic features achieved an area under the curve value of 0.876 and 0.845 in the training and validation set. And, the combined radiomic nomogram achieved area under the curve value of 0.897 (training set) and 0.882 (validation set). Above that, calibration curve and Hosmer-Lemeshow test showed that the radiomic model and combined radiomic nomogram had good agreement between observations and predictions in the training set and the validation set. Finally, the decision curve analysis revealed that the 2 models had good clinical usefulness for the prediction of TERTp mutation status in IDHwt LGA. The combined radiomics nomogram performed great performance and high sensitivity in prediction of TERTp mutation status in IDHwt LGA, and has good clinical application.

Systematic Literature Review of Machine Learning Algorithms Using Pretherapy Radiologic Imaging for Glioma Molecular Subtype Prediction

BACKGROUND

The molecular profile of gliomas is a prognostic indicator for survival, driving clinical decision-making for treatment. Pathology-based molecular diagnosis is challenging because of the invasiveness of the procedure, exclusion from neoadjuvant therapy options, and the heterogeneous nature of the tumor.

PURPOSE

We performed a systematic review of algorithms that predict molecular subtypes of gliomas from MR Imaging.

DATA SOURCES

Data sources were Ovid Embase, Ovid MEDLINE, Cochrane Central Register of Controlled Trials, Web of Science.

STUDY SELECTION

Per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 12,318 abstracts were screened and 1323 underwent full-text review, with 85 articles meeting the inclusion criteria.

DATA ANALYSIS

We compared prediction results from different machine learning approaches for predicting molecular subtypes of gliomas. Bias analysis was conducted for each study, following the Prediction model Risk Of Bias Assessment Tool (PROBAST) guidelines.

DATA SYNTHESIS

Isocitrate dehydrogenase mutation status was reported with an area under the curve and accuracy of 0.88 and 85% in internal validation and 0.86 and 87% in limited external validation data sets, respectively. For the prediction of O6-methylguanine-DNA methyltransferase promoter methylation, the area under the curve and accuracy in internal validation data sets were 0.79 and 77%, and in limited external validation, 0.89 and 83%, respectively. PROBAST scoring demonstrated high bias in all articles.

LIMITATIONS

The low number of external validation and studies with incomplete data resulted in unequal data analysis. Comparing the best prediction pipelines of each study may introduce bias.

CONCLUSIONS

While the high area under the curve and accuracy for the prediction of molecular subtypes of gliomas are reported in internal and external validation data sets, limited use of external validation and the increased risk of bias in all articles may present obstacles for clinical translation of these techniques.

MRI-Based Deep Learning Method for Classification of IDH Mutation Status

Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. This study sought to develop deep learning networks for non-invasive IDH classification using T2w MR images while comparing their performance to a multi-contrast network. Methods: Multi-contrast brain tumor MRI and genomic data were obtained from The Cancer Imaging Archive (TCIA) and The Erasmus Glioma Database (EGD). Two separate 2D networks were developed using nnU-Net, a T2w-image-only network (T2-net) and a multi-contrast network (MC-net). Each network was separately trained using TCIA (227 subjects) or TCIA + EGD data (683 subjects combined). The networks were trained to classify IDH mutation status and implement single-label tumor segmentation simultaneously. The trained networks were tested on over 1100 held-out datasets including 360 cases from UT Southwestern Medical Center, 136 cases from New York University, 175 cases from the University of Wisconsin-Madison, 456 cases from EGD (for the TCIA-trained network), and 495 cases from the University of California, San Francisco public database. A receiver operating characteristic curve (ROC) was drawn to calculate the AUC value to determine classifier performance. Results: T2-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 85.4% and 87.6% with AUCs of 0.86 and 0.89, respectively. MC-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 91.0% and 92.8% with AUCs of 0.94 and 0.96, respectively. We developed reliable, high-performing deep learning algorithms for IDH classification using both a T2-image-only and a multi-contrast approach. The networks were tested on more than 1100 subjects from diverse databases, making this the largest study on image-based IDH classification to date.

TP53 Mutation Estimation Based on MRI Radiomics Analysis for Breast Cancer

BACKGROUND

Noninvasive detection of TP53 mutations is useful for the molecular stratification of breast cancer.

PURPOSE

To explore MRI radiomics features reflecting TP53 mutations in breast cancer and propose a classifier for detecting such mutations.

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

A total of 139 breast cancer patients with TP53 expression profiling (98 with TP53 mutations and 41 without TP53 mutations).

FIELD STRENGTH/SEQUENCE

1.5 T, T1-weighted (T1W) DCE-MRI.

ASSESSMENT

Lesions were manually segmented using subtracted T1WI. A total of 944 radiomics features (including 744 wavelet-related features) and 7 clinicopathological features were extracted from each lesion. Principal component analysis and Pearson's correlation analysis were used to preprocess the features. Linear discriminant analysis, logistic regression (LR), support vector machine (SVM), and random forest (RF) were used as the classifiers.

STATISTICAL TESTS

Analysis of variance, Kruskal-Wallis and recursive features elimination were used to select features. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic accuracy.

RESULTS

For the radiomics model, the validation cohorts AUCs of the four classifiers ranged from 0.69 (RF) to 0.74 (LR), and LR (0.74) attained the highest AUCs. For the clinicopathological-radiomics combined model, the validation AUCs of the four classifiers ranged from 0.68 (RF) to 0.86 (SVM), and SVM (0.86) attained highest AUCs. In the subgroup analysis of triple-negative (TN) and luminal type breast cancer, RF achieved the highest AUCs (0.83 and 0.94).

DATA CONCLUSION

Clinicopathological-radiomics combined model with SVM could be used as noninvasive biomarkers for predicting TP53 mutations. RF was recommended for the detection of TP53 mutations in TN and luminal type breast cancer.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Multimodality MRI radiomics analysis of TP53 mutations in triple negative breast cancer

Objectives

To explore the value of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) radiomics features reflecting TP53 mutations in patients with triple negative breast cancer (TNBC).

Study design

This retrospective study enrolled 91 patients with TNBC with TP53 testing (64 patients in the training cohort and 27 patients in the validation cohort). A total of 2832 radiomics features were extracted from the first phase of dynamic contrast-enhanced T1WI, T2WI and ADC maps. Analysis of variance (ANOVA) and the Kruskal-Wallis-test were used for feature selection. Then, linear discriminant analysis (LDA), multilayer perceptron (MLP), logistic regression (LR), LR with LASSO, decision tree (DT), naïve Bayes (NB), random forest (RF), and support vector machine (SVM) models were used for classification.

Results

The validation AUCs of the eight classifiers ranged from 0.74 (NB) to 0.85 (SVM). SVM attained the highest AUC (0.85) and diagnostic accuracy (0.82) of all tested models. The top 3 ranking features in the SVM model were T1-square-first order-skewness (coefficient: 1.735), T2-wavelet-LHH-GLCM-joint energy, and T2-wavelet-LHH-GLCM-inverse difference moment (coefficient: -0.654, -0.634).

Conclusions

Radiomics-based analysis with the SVM model is recommended for the detection of TP53 mutations in TNBC. Furthermore, T1WI- and T2WI-related features could be used as noninvasive biomarkers for predicting TP53 mutations.

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.

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.

Tumor Progression and Treatment-Related Changes: Radiological Diagnosis Challenges for the Evaluation of Post Treated Glioma

Simple Summary

Glioma is the most common primary malignant tumor of the adult central nervous system. Despite aggressive multimodal treatment, its prognosis remains poor. During follow-up, it remains challenging to distinguish treatment-related changes from tumor progression in treated patients with gliomas due to both share clinical symptoms and morphological imaging characteristics (with new and/or increasing enhancing mass lesions). The early effective identification of tumor progression and treatment-related changes is of great significance for the prognosis and treatment of gliomas. We believe that advanced neuroimaging techniques can provide additional information for distinguishing both at an early stage. In this article, we focus on the research of magnetic resonance imaging technology and artificial intelligence in tumor progression and treatment-related changes. Finally, it provides new ideas and insights for clinical diagnosis.

Abstract

As the most common neuro-epithelial tumors of the central nervous system in adults, gliomas are highly malignant and easy to recurrence, with a dismal prognosis. Imaging studies are indispensable for tracking tumor progression (TP) or treatment-related changes (TRCs). During follow-up, distinguishing TRCs from TP in treated patients with gliomas remains challenging as both share similar clinical symptoms and morphological imaging characteristics (with new and/or increasing enhancing mass lesions) and fulfill criteria for progression. Thus, the early identification of TP and TRCs is of great significance for determining the prognosis and treatment. Histopathological biopsy is currently the gold standard for TP and TRC diagnosis. However, the invasive nature of this technique limits its clinical application. Advanced imaging methods (e.g., diffusion magnetic resonance imaging (MRI), perfusion MRI, magnetic resonance spectroscopy (MRS), positron emission tomography (PET), amide proton transfer (APT) and artificial intelligence (AI)) provide a non-invasive and feasible technical means for identifying of TP and TRCs at an early stage, which have recently become research hotspots. This paper reviews the current research on using the abovementioned advanced imaging methods to identify TP and TRCs of gliomas. First, the review focuses on the pathological changes of the two entities to establish a theoretical basis for imaging identification. Then, it elaborates on the application of different imaging techniques and AI in identifying the two entities. Finally, the current challenges and future prospects of these techniques and methods are discussed.

Glioblastoma Associated Natural Killer Cell EVs Generating Tumour-Specific Signatures: Noninvasive GBM Liquid Biopsy with Self-Functionalized Quantum Probes

Diagnosis of glioblastoma (GBM) poses a recurring struggle due to many factors, including the presence of the blood-brain barrier (BBB) in addition to the significant tumor heterogeneity. Natural killer (NK) cells of the innate immune system are the primary immune surveillance mechanism for GBM and identify GBM tumors without any previous sensitization. The metabolic reprogramming of NK cells during GBM association is expected to be reflected in its extracellular vesicles. Therefore, tracking the activity of NK cell vesicles in circulation (circulating immune vesicles, CIVs) has great potential for accurate GBM diagnosis. However, identification GBM associated CIVs in circulation is immensely challenging as there is no availability of clinically validated GBM-specific circulating biomarkers. Here, we present GBM associated CIV profiling for noninvasive GBM diagnosis. We investigated the feasibility of using the signals derived from GBM associated CIVs as a de novo methodology for GBM diagnosis. An ultrasensitive sensor and a marker-free approach were essential for the detection of rare signals of GBM associated CIVs. For this purpose, we designed GBM ImmunoProfiler platform using scalable ultrafast laser multiphoton ionization mechanism and adopted surface enhanced Raman spectroscopy (SERS) ensuring simultaneous detection of multiple CIV signals to identify GBM. We experimentally demonstrated that GBM associated CIVs carry unique, tumor-specific signals. The features of GBM associated CIVs were explored through machine learning identifying its similarity with GBM patient blood (without cell isolation) using a very small amount of peripheral blood (5 μL) with 96.82% sensitivity and 100% specificity. In addition, we demonstrated that a tumor associated CIV profile can classify between multiple brain cancer types (astrocytoma, oligodendroglioma, and glioblastoma). We also experimentally demonstrated significant variation in the immune checkpoint protein expression (PDL-1 and CTLA-4) between GBM associated CIVs and uninteracted CIVs. Preclinical analysis with serum specimens of GBM patients showed the possibility of using our technology for minimally invasive GBM diagnosis. With clinical validation, our technology has potential to improve GBM diagnostics with a useful, minimally invasive GBM liquid biopsy.

A Survey of Radiomics in Precision Diagnosis and Treatment of Adult Gliomas

Glioma is the most common primary malignant tumor of the adult central nervous system (CNS), which mostly shows invasive growth. In most cases, surgery is often difficult to completely remove, and the recurrence rate and mortality of patients are high. With the continuous development of molecular genetics and the great progress of molecular biology technology, more and more molecular biomarkers have been proved to have important guiding significance in the individualized diagnosis, treatment, and prognosis evaluation of glioma. With the updates of the World Health Organization (WHO) classification of tumors of the CNS in 2021, the diagnosis and treatment of glioma has entered the era of precision medicine in the true sense. Due to its ability to non-invasively achieve accurate identification of glioma from other intracranial tumors, and to predict the grade, genotyping, treatment response, and prognosis of glioma, which provides a scientific basis for the clinical application of individualized diagnosis and treatment model of glioma, radiomics has become a research hotspot in the field of precision medicine. This paper reviewed the research related to radiomics of adult gliomas published in recent years and summarized the research proceedings of radiomics in differential diagnosis, preoperative grading and genotyping, treatment and efficacy evaluation, and survival prediction of adult gliomas.

Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics

This study aimed to investigate the feasibility of predicting oxygen 6-methylguanine-DNA methyltransferase (MGMT) promoter methylation in diffuse gliomas by developing a deep learning approach using MRI radiomics. A total of 111 patients with diffuse gliomas participated in the retrospective study (56 patients with MGMT promoter methylation and 55 patients with MGMT promoter unmethylation). The radiomics features of the two regions of interest (ROI) (the whole tumor area and the tumor core area) for four sequences, including T1 weighted image (T1WI), T2 weighted image (T2WI), apparent diffusion coefficient (ADC) maps, and T1 contrast-enhanced (T1CE) MR images were extracted and jointly fed into the residual network. Then the deep learning method was developed and evaluated with a five-fold cross-validation, where in each fold, the dataset was randomly divided into training (80%) and validation (20%) cohorts. We compared the performance of all models using area under the curve (AUC) and average accuracy of validation cohorts and calculated the 10 most important features of the best model via a class activation map. Based on the ROI of the whole tumor, the predictive capacity of the T1CE and ADC model achieved the highest AUC value of 0.85. Based on the ROI of the tumor core, the T1CE and ADC model achieved the highest AUC value of 0.90. After comparison, the T1CE combined with the ADC model based on the ROI of the tumor core exhibited the best performance, with the highest average accuracy (0.91) and AUC (0.90) among all models. The deep learning method using MRI radiomics has excellent diagnostic performance with a high accuracy in predicting MGMT promoter methylation in diffuse gliomas.

Preoperative Diagnosis and Molecular Characterization of Gliomas With Liquid Biopsy and Radiogenomics

Gliomas are a heterogenous group of central nervous system tumors with different outcomes and different therapeutic needs. Glioblastoma, the most common subtype in adults, has a very poor prognosis and disabling consequences. The World Health Organization (WHO) classification specifies that the typing and grading of gliomas should include molecular markers. The molecular characterization of gliomas has implications for prognosis, treatment planning, and prediction of treatment response. At present, gliomas are diagnosed via tumor resection or biopsy, which are always invasive and frequently risky methods. In recent years, however, substantial advances have been made in developing different methods for the molecular characterization of tumors through the analysis of products shed in body fluids. Known as liquid biopsies, these analyses can potentially provide diagnostic and prognostic information, guidance on choice of treatment, and real-time information on tumor status. In addition, magnetic resonance imaging (MRI) is another good source of tumor data; radiomics and radiogenomics can link the imaging phenotypes to gene expression patterns and provide insights to tumor biology and underlying molecular signatures. Machine and deep learning and computational techniques can also use quantitative imaging features to non-invasively detect genetic mutations. The key molecular information obtained with liquid biopsies and radiogenomics can be useful not only in the diagnosis of gliomas but can also help predict response to specific treatments and provide guidelines for personalized medicine. In this article, we review the available data on the molecular characterization of gliomas using the non-invasive methods of liquid biopsy and MRI and suggest that these tools could be used in the future for the preoperative diagnosis of gliomas.

Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors

Background

For brain tumors, identifying the molecular subtypes from magnetic resonance imaging (MRI) is desirable, but remains a challenging task. Recent machine learning and deep learning (DL) approaches may help the classification/prediction of tumor subtypes through MRIs. However, most of these methods require annotated data with ground truth (GT) tumor areas manually drawn by medical experts. The manual annotation is a time consuming process with high demand on medical personnel. As an alternative automatic segmentation is often used. However, it does not guarantee the quality and could lead to improper or failed segmented boundaries due to differences in MRI acquisition parameters across imaging centers, as segmentation is an ill-defined problem. Analogous to visual object tracking and classification, this paper shifts the paradigm by training a classifier using tumor bounding box areas in MR images. The aim of our study is to see whether it is possible to replace GT tumor areas by tumor bounding box areas (e.g. ellipse shaped boxes) for classification without a significant drop in performance.

Method

In patients with diffuse gliomas, training a deep learning classifier for subtype prediction by employing tumor regions of interest (ROIs) using ellipse bounding box versus manual annotated data. Experiments were conducted on two datasets (US and TCGA) consisting of multi-modality MRI scans where the US dataset contained patients with diffuse low-grade gliomas (dLGG) exclusively.

Results

Prediction rates were obtained on 2 test datasets: 69.86% for 1p/19q codeletion status on US dataset and 79.50% for IDH mutation/wild-type on TCGA dataset. Comparisons with that of using annotated GT tumor data for training showed an average of 3.0% degradation (2.92% for 1p/19q codeletion status and 3.23% for IDH genotype).

Conclusion

Using tumor ROIs, i.e., ellipse bounding box tumor areas to replace annotated GT tumor areas for training a deep learning scheme, cause only a modest decline in performance in terms of subtype prediction. With more data that can be made available, this may be a reasonable trade-off where decline in performance may be counteracted with more data.

Non-Invasive Prediction of Survival Time of Midline Glioma Patients Using Machine Learning on Multiparametric MRI Radiomics Features

Objectives

To explore the feasibility of predicting overall survival (OS) of patients with midline glioma using multi-parameter magnetic resonance imaging (MRI) features.

Methods

Data of 84 patients with midline gliomas were retrospectively collected, including 40 patients with OS > 12 months (28 cases were adults, 14 cases were H3 K27M-mutation) and 44 patients with OS < 12 months (29 cases were adults, 31 cases were H3 K27M-mutation). Features were extracted from the largest slice of tumors, which were manually segmented on T2-weighted (T2w), T2 fluid-attenuated inversion recovery (T2 FLAIR), and contrast-enhanced T1-weighted (T1c) images. Data were randomly divided into training (70%) and test cohorts (30%) and normalized and standardized using Z-scores. Feature dimensionality reduction was performed using the variance method and maximum relevance and minimum redundancy (mRMR) algorithm. We used the logistic regression algorithm to construct three models for T2w, T2 FLAIR, and T1c images as well as one combined model. The test cohort was used to evaluate the models, and receiver operating characteristic (ROC) curves, areas under the curve (AUCs), sensitivity, specificity, and accuracy were calculated. The nomogram of the combined model was built and evaluated using a calibration curve. Decision curve analysis (DCA) was used to evaluate the clinical application value of the four models.

Results

A total of 1,316 features were extracted from T2w, T2 FLAIR, and T1c images, respectively. And then the best non-redundant features were selected from the extracted features using the variance method and mRMR. Finally, five features were extracted each from T2w, T2 FLAIR, and T1c images, and 12 features were extracted for the combined model. Four models were established using the optimal features. In the test cohort, the combined model performed the best out of all models. The AUCs of the T2w, T2 FLAIR, T1c, and combined models were 0.73, 0.78, 0.74, and 0.87, respectively, and accuracies were 0.72, 0.76, 0.72, and 0.84, respectively. The ROC curves and DCA showed that the combined model had the highest efficiency and most favorable clinical benefits.

Conclusion

The combined radiomics model based on multi-parameter MRI features provided a reliable non-invasive method for the prognostic prediction of midline gliomas.

Added value of radiomics analysis in MRI invisible early-stage cervical cancers

OBJECTIVES

To determine the diagnostic ability of cervical mucosa radiomics signature of sagittal T2WI and T1 contrast-enhanced (CE) imaging in detecting early-stage cervical cancers with negative MRI.

METHODS

Preoperative images of postoperative pathology confirmed early-stage cervical cancer patients and normal cervix patients admitted to our hospital between January 2013 and December 2020 were retrospectively reviewed. Patients with cancer signals on T2WI, T1CE and DWI were deleted. Regions of interests (ROIs) were delineated on cervical mucosa (from cervical canal to cervical dome) with 5 mm width on sagittal T2WI and T1CE. The maximum-relevance and minimumredundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods were used for the calculation of radiomics signature scores. Diagnostic performance was assessed and compared between radiomics prediction models (model 1: T1CE; model 2: T2WI; model 3: model one combined with model 2). Differential diagnostic ability of radiomics signature in detecting lymphatic vascular space invasion (LVSI) was further explored.

RESULTS

Diagnostic performance of model three was higher than model 1 and model 2 both in primary (model 3 0.874, model 1 0.857, model 2 0.816) and validation (model 3 0.853, model 1 0.847, model 2 0.634) cohorts. Model 3 showed statistical diagnostic difference compared with model 2 (primary p = 0.008, validation p = 0.000). However, the diagnostic improvement ability of model 3 showed no statistical difference compared with model 1 (primary p = 0.351, validation p = 0.739). Diagnostic efficiency of model 3 in detecting LVSI was not apparent (AUC 0.64).

CONCLUSIONS

Radiomics analysis of cervical mucosa combining T1CE and T2WI is promising for predicting MRI invisible early-stage cervical cancers, however further ability in detecting LVSI was not apparent.

ADVANCES IN KNOWLEDGE

Conventional MRI was originally defined as meaningless in very early-stage cervical cancers. However, whether MRI radiomics analysis of cervical mucosa can detecting tiny changes of invisible early stage cervical cancers has not been researched yet.

Radiomics Nomogram Improves the Prediction of Epilepsy in Patients With Gliomas

Purpose

To investigate the association between clinic-radiological features and glioma-associated epilepsy (GAE), we developed and validated a radiomics nomogram for predicting GAE in WHO grade II~IV gliomas.

Methods

This retrospective study consecutively enrolled 380 adult patients with glioma (266 in the training cohort and 114 in the testing cohort). Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. The semantic radiological characteristics were assessed by a radiologist with 15 years of experience in neuro-oncology. A clinic-radiological model, radiomic signature, and a combined model were built for predicting GAE. The combined model was visualized as a radiomics nomogram. The AUC was used to evaluate model classification performance, and the McNemar test and Delong test were used to compare the performance among the models. Statistical analysis was performed using SPSS software, and p < 0.05 was regarded as statistically significant.

Results

The combined model reached the highest AUC with the testing cohort (training cohort, 0.911 [95% CI, 0.878-0.942]; testing cohort, 0.866 [95% CI, 0.790-0.929]). The McNemar test revealed that the differences among the accuracies of the clinic-radiological model, radiomic signature, and combined model in predicting GAE in the testing cohorts (p > 0.05) were not significantly different. The DeLong tests showed that the difference between the performance of the radiomic signature and the combined model was significant (p < 0.05).

Conclusion

The radiomics nomogram predicted seizures in patients with glioma non-invasively, simply, and practically. Compared with the radiomics models, comprehensive clinic-radiological imaging signs observed by the naked eye have non-discriminatory performance in predicting GAE.

Radiomics-Based Method for Predicting the Glioma Subtype as Defined by Tumor Grade, IDH Mutation, and 1p/19q Codeletion

Gliomas are among the most common types of central nervous system (CNS) tumors. A prompt diagnosis of the glioma subtype is crucial to estimate the prognosis and personalize the treatment strategy. The objective of this study was to develop a radiomics pipeline based on the clinical Magnetic Resonance Imaging (MRI) scans to noninvasively predict the glioma subtype, as defined based on the tumor grade, isocitrate dehydrogenase (IDH) mutation status, and 1p/19q codeletion status. A total of 212 patients from the public retrospective The Cancer Genome Atlas Low Grade Glioma (TCGA-LGG) and The Cancer Genome Atlas Glioblastoma Multiforme (TCGA-GBM) datasets were used for the experiments and analyses. Different settings in the radiomics pipeline were investigated to improve the classification, including the Z-score normalization, the feature extraction strategy, the image filter applied to the MRI images, the introduction of clinical information, ComBat harmonization, the classifier chain strategy, etc. Based on numerous experiments, we finally reached an optimal pipeline for classifying the glioma tumors. We then tested this final radiomics pipeline on the hold-out test data with 51 randomly sampled random seeds for reliable and robust conclusions. The results showed that, after tuning the radiomics pipeline, the mean AUC improved from 0.8935 (±0.0351) to 0.9319 (±0.0386), from 0.8676 (±0.0421) to 0.9283 (±0.0333), and from 0.6473 (±0.1074) to 0.8196 (±0.0702) in the test data for predicting the tumor grade, IDH mutation, and 1p/19q codeletion status, respectively. The mean accuracy for predicting the five glioma subtypes also improved from 0.5772 (±0.0816) to 0.6716 (±0.0655). Finally, we analyzed the characteristics of the radiomic features that best distinguished the glioma grade, the IDH mutation, and the 1p/19q codeletion status, respectively. Apart from the promising prediction of the glioma subtype, this study also provides a better understanding of the radiomics model development and interpretability. The results in this paper are replicable with our python codes publicly available in github.

Radiomics as an emerging tool in the management of brain metastases

Brain metastases (BM) are associated with significant morbidity and mortality in patients with advanced cancer. Despite significant advances in surgical, radiation, and systemic therapy in recent years, the median overall survival of patients with BM is less than 1 year. The acquisition of medical images, such as computed tomography (CT) and magnetic resonance imaging (MRI), is critical for the diagnosis and stratification of patients to appropriate treatments. Radiomic analyses have the potential to improve the standard of care for patients with BM by applying artificial intelligence (AI) with already acquired medical images to predict clinical outcomes and direct the personalized care of BM patients. Herein, we outline the existing literature applying radiomics for the clinical management of BM. This includes predicting patient response to radiotherapy and identifying radiation necrosis, performing virtual biopsies to predict tumor mutation status, and determining the cancer of origin in brain tumors identified via imaging. With further development, radiomics has the potential to aid in BM patient stratification while circumventing the need for invasive tissue sampling, particularly for patients not eligible for surgical resection.

Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma

Objective

This study was conducted in order to investigate the association between radiomics features and frontal glioma-associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE.

Methods

This retrospective study consecutively enrolled 166 adult patients with frontal glioma (111 in the training cohort and 55 in the testing cohort). A total 1,130 features were extracted from T2 fluid-attenuated inversion recovery images, including first-order statistics, 3D shape, texture, and wavelet features. Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. Pearson correlation coefficient, 10-fold cross-validation, area under curve (AUC) analysis, and support vector machine were adopted to select the most relevant features to build a clinical model, a radiomics model, and a clinical-radiomics model for GAE. The receiver operating characteristic curve (ROC) and AUC were used to evaluate the classification performance of the models in each cohort, and DeLong's test was used to compare the performance of the models. A two-sided t-test and Fisher's exact test were used to compare the clinical variables. Statistical analysis was performed using SPSS software (version 22.0; IBM, Armonk, New York), and p <0.05 was set as the threshold for significance.

Results

The classification accuracy of seven scout models, except the wavelet first-order model (0.793) and the wavelet texture model (0.784), was <0.75 in cross-validation. The clinical-radiomics model, including 17 magnetic resonance imaging-based features selected among the 1,130 radiomics features and two clinical features (patient age and tumor grade), achieved better discriminative performance for GAE prediction in both the training [AUC = 0.886, 95% confidence interval (CI) = 0.819-0.940] and testing cohorts (AUC = 0.836, 95% CI = 0.707-0.937) than the radiomics model (p = 0.008) with 82.0% and 78.2% accuracy, respectively.

Conclusion

Radiomics analysis can non-invasively predict GAE, thus allowing adequate treatment of frontal glioma. The clinical-radiomics model may enable a more precise prediction of frontal GAE. Furthermore, age and pathology grade are important risk factors for GAE.

AI in spotting high-risk characteristics of medical imaging and molecular pathology

Medical imaging provides a comprehensive perspective and rich information for disease diagnosis. Combined with artificial intelligence technology, medical imaging can be further mined for detailed pathological information. Many studies have shown that the macroscopic imaging characteristics of tumors are closely related to microscopic gene, protein and molecular changes. In order to explore the function of artificial intelligence algorithms in in-depth analysis of medical imaging information, this paper reviews the articles published in recent years from three perspectives: medical imaging analysis method, clinical applications and the development of medical imaging in the direction of pathological molecular prediction. We believe that AI-aided medical imaging analysis will be extensively contributing to precise and efficient clinical decision.

A Review of Radiomics and Deep Predictive Modeling in Glioma Characterization

Recent developments in glioma categorization based on biological genotypes and application of computational machine learning or deep learning based predictive models using multi-modal MRI biomarkers to assess these genotypes provides potential assurance for optimal and personalized treatment plans and efficacy. Artificial intelligence based quantified assessment of glioma using MRI derived hand-crafted or auto-extracted features have become crucial as genomic alterations can be associated with MRI based phenotypes. This survey integrates all the recent work carried out in state-of-the-art radiomics, and Artificial Intelligence based learning solutions related to molecular diagnosis, prognosis, and treatment monitoring with the aim to create a structured resource on radiogenomic analysis of glioma. Challenges such as inter-scanner variability, requirement of benchmark datasets, prospective validations for clinical applicability are discussed with further scope for designing optimal solutions for glioma stratification with immediate recommendations for further diagnostic decisions and personalized treatment plans for glioma patients.

Reverse Engineering Glioma Radiomics to Conventional Neuroimaging

A novel radiological research field pursuing comprehensive quantitative image, namely “Radiomics,” gained traction along with the advancement of computational technology and artificial intelligence. This novel concept for analyzing medical images brought extensive interest to the neuro-oncology and neuroradiology research community to build a diagnostic workflow to detect clinically relevant genetic alteration of gliomas noninvasively. Although quite a few promising results were published regarding MRI-based diagnosis of isocitrate dehydrogenase (IDH) mutation in gliomas, it has become clear that an ample amount of effort is still needed to render this technology clinically applicable. At the same time, many significant insights were discovered through this research project, some of which could be “reverse engineered” to improve conventional non-radiomic MR image acquisition. In this review article, the authors aim to discuss the recent advancements and encountering issues of radiomics, how we can apply the knowledge provided by radiomics to standard clinical images, and further expected technological advances in the realm of radiomics and glioma.

Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients

Gliomas can be classified into five molecular groups based on the status of IDH mutation, 1p/19q codeletion, and TERT promoter mutation, whereas they need to be obtained by biopsy or surgery. Thus, we aimed to use MRI-based radiomics to noninvasively predict the molecular groups and assess their prognostic value. We retrospectively identified 357 patients with gliomas and extracted radiomic features from their preoperative MRI images. Single-layered radiomic signatures were generated using a single MR sequence using Bayesian-regularization neural networks. Image fusion models were built by combing the significant radiomic signatures. By separately predicting the molecular markers, the predictive molecular groups were obtained. Prognostic nomograms were developed based on the predictive molecular groups and clinicopathologic data to predict progression-free survival (PFS) and overall survival (OS). The results showed that the image fusion model incorporating radiomic signatures from contrast-enhanced T1-weighted imaging (cT1WI) and apparent diffusion coefficient (ADC) achieved an AUC of 0.884 and 0.669 for predicting IDH and TERT status, respectively. cT1WI-based radiomic signature alone yielded favorable performance in predicting 1p/19q status (AUC = 0.815). The predictive molecular groups were comparable to actual ones in predicting PFS (C-index: 0.709 vs. 0.722, P = 0.241) and OS (C-index: 0.703 vs. 0.751, P = 0.359). Subgroup analyses by grades showed similar findings. The prognostic nomograms based on grades and the predictive molecular groups yielded a C-index of 0.736 and 0.735 in predicting PFS and OS, respectively. Accordingly, MRI-based radiomics may be useful for noninvasively detecting molecular groups and predicting survival in gliomas regardless of grades.

Radiogenomics in brain, breast, and lung cancer: opportunities and challenges

The field of radiogenomics largely focuses on developing imaging surrogates for genomic signatures and integrating imaging, genomic, and molecular data to develop combined personalized biomarkers for characterizing various diseases. Our study aims to highlight the current state-of-the-art and the role of radiogenomics in cancer research, focusing mainly on solid tumors, and is broadly divided into four sections. The first section reviews representative studies that establish the biologic basis of radiomic signatures using gene expression and molecular profiling information. The second section includes studies that aim to non-invasively predict molecular subtypes of tumors using radiomic signatures. The third section reviews studies that evaluate the potential to augment the performance of established prognostic signatures by combining complementary information encoded by radiomic and genomic signatures derived from cancer tumors. The fourth section includes studies that focus on ascertaining the biological significance of radiomic phenotypes. We conclude by discussing current challenges and opportunities in the field, such as the importance of coordination between imaging device manufacturers, regulatory organizations, health care providers, pharmaceutical companies, academic institutions, and physicians for the effective standardization of the results from radiogenomic signatures and for the potential use of these findings to improve precision care for cancer patients.

Systematic Review on the Association of Radiomics with Tumor Biological Endpoints

Radiomics supposes an alternative non-invasive tumor characterization tool, which has experienced increased interest with the advent of more powerful computers and more sophisticated machine learning algorithms. Nonetheless, the incorporation of radiomics in cancer clinical-decision support systems still necessitates a thorough analysis of its relationship with tumor biology. Herein, we present a systematic review focusing on the clinical evidence of radiomics as a surrogate method for tumor molecular profile characterization. An extensive literature review was conducted in PubMed, including papers on radiomics and a selected set of clinically relevant and commonly used tumor molecular markers. We summarized our findings based on different cancer entities, additionally evaluating the effect of different modalities for the prediction of biomarkers at each tumor site. Results suggest the existence of an association between the studied biomarkers and radiomics from different modalities and different tumor sites, even though a larger number of multi-center studies are required to further validate the reported outcomes.

Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis

Simple Summary

Glioma prognosis and treatment are based on histopathological characteristics and molecular profile. Following the World Health Organization (WHO) guidelines (2016), the most important molecular diagnostic markers include IDH1/2-genotype and 1p/19q codeletion status, although more recent publications also include ARTX genotype and TERT- and MGMT promoter methylation. Machine learning algorithms (MLAs), however, were described to successfully determine these molecular characteristics non-invasively by using magnetic resonance imaging (MRI) data. The aim of this review and meta-analysis was to define the diagnostic accuracy of MLAs with regard to these different molecular markers. We found high accuracies of MLAs to predict each individual molecular marker, with IDH1/2-genotype being the most investigated and the most accurate. Radiogenomics could therefore be a promising tool for discriminating genetically determined gliomas in a non-invasive fashion. Although encouraging results are presented here, large-scale, prospective trials with external validation groups are warranted.

Abstract

Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.

Differentiating TP53 Mutation Status in Pancreatic Ductal Adenocarcinoma Using Multiparametric MRI-Derived Radiomics

Objectives

This study assessed the preoperative prediction of TP53 status based on multiparametric magnetic resonance imaging (mpMRI) radiomics extracted from two-dimensional (2D) and 3D images.

Methods

57 patients with pancreatic cancer who underwent preoperative MRI were included. The diagnosis and TP53 gene test were based on resections. Of the 57 patients included 37 mutated TP53 genes and the remaining 20 had wild-type TP53 genes. Two radiologists performed manual tumour segmentation on seven different MRI image acquisition sequences per patient, including multi-phase [pre-contrast, late arterial phase (ap), portal venous phase, and delayed phase] dynamic contrast enhanced (DCE) T1-weighted imaging, T2-weighted imaging (T2WI), Diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC). PyRadiomics-package was used to generate 558 two-dimensional (2D) and 994 three-dimensional (3D) image features. Models were constructed by support vector machine (SVM) for differentiating TP53 status and DX score method were used for feature selection. The evaluation of the model performance included area under the curve (AUC), accuracy, calibration curves, and decision curve analysis.

Results

The 3D ADC-ap-DWI-T2WI model with 11 selected features yielded the best performance for differentiating TP53 status, with accuracy = 0.91 and AUC = 0.96. The model showed the good calibration. The decision curve analysis indicated that the radiomics model had clinical utility.

Conclusions

A non-invasive and quantitative mpMRI-based radiomics model can accurately predict TP53 mutation status in pancreatic cancer patients and contribute to the precision treatment.

Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review

Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine.

Improving performance and generalizability in radiogenomics: a pilot study for prediction of IDH1/2 mutation status in gliomas with multicentric data

Purpose: Radiogenomics offers a potential virtual and noninvasive biopsy. However, radiogenomics models often suffer from generalizability issues, which cause a performance degradation on unseen data. In MRI, differences in the sequence parameters, manufacturers, and scanners make this generalizability issue worse. Such image acquisition information may be used to define different environments and select robust and invariant radiomic features associated with the clinical outcome that should be included in radiomics/radiogenomics models. Approach: We assessed 77 low-grade gliomas and glioblastomas multiform patients publicly available in TCGA and TCIA. Radiomics features were extracted from multiparametric MRI images (T1-weighted, contrast-enhanced T1-weighted, T2-weighted, and fluid-attenuated inversion recovery) and different regions-of-interest (enhancing tumor, nonenhancing tumor/necrosis, and edema). A method developed to find variables that are part of causal structures was used for feature selection and compared with an embedded feature selection approach commonly used in radiomics/radiogenomics studies, across two different scenarios: (1) leaving data from a center as an independent held-out test set and tuning the model with the data from the remaining centers and (2) use stratified partitioning to obtain the training and the held-out test sets. Results: In scenario (1), the performance of the proposed methodology and the traditional embedded method was AUC: 0.75 [0.25; 1.00] versus 0.83 [0.50; 1.00], Sens.: 0.67 [0.20; 0.93] versus 0.67 [0.20; 0.93], Spec.: 0.75 [0.30; 0.95] versus 0.75 [0.30; 0.95], and MCC: 0.42 [0.19; 0.68] versus 0.42 [0.19; 0.68] for center 1 as the held-out test set. The performance of both methods for center 2 as the held-out test set was AUC: 0.64 [0.36; 0.91] versus 0.55 [0.27; 0.82], Sens.: 0.00 [0.00; 0.73] versus 0.00 [0.00; 0.73], Spec.: 0.82 [0.52; 0.94] versus 0.91 [0.62; 0.98], and MCC: - 0.13 [ - 0.38 ; - 0.04 ] versus - 0.09 [ - 0.38 ; - 0.02 ] , whereas for center 3 was AUC: 0.80 [0.62; 0.95] versus 0.89 [0.56; 0.96], Sens.: 0.86 [0.48; 0.97] versus 0.86 [0.48; 0.97], Spec.: 0.72 [0.54; 0.85] versus 0.79 [0.61; 0.90], and MCC: 0.47 [0.41; 0.53] versus 0.55 [0.48; 0.60]. For center 4, the performance of both methods was AUC: 0.77 [0.51; 1.00] versus 0.75 [0.47; 0.97], Sens.: 0.53 [0.30; 0.75] versus 0.00 [0.00; 0.15], Spec.: 0.71 [0.35; 0.91] versus 0.86 [0.48; 0.97], and MCC: 0.23 [0.16; 0.31] versus. - 0.32 [ - 0.46 ; - 0.20 ] . In scenario (2), the performance of these methods was AUC: 0.89 [0.71; 1.00] versus 0.79 [0.58; 0.94], Sens.: 0.86 [0.80; 0.92] versus 0.43 [0.15; 0.74], Spec.: 0.87 [0.62; 0.96] versus 0.87 [0.62; 0.96], and MCC: 0.70 [0.60; 0.77] versus 0.33 [0.24; 0.42]. Conclusions: This proof-of-concept study demonstrated good performance by the proposed feature selection method in the majority of the studied scenarios, as it promotes robustness of features included in the models and the models' generalizability by making used imaging data of different scanners or with sequence parameters.

Multiparametric MRI texture analysis in prediction of glioma biomarker status: added value of MR diffusion

Background

Early identification of glioma molecular phenotypes can lead to understanding of patient prognosis and treatment guidance. We aimed to develop a multiparametric MRI texture analysis model using a combination of conventional and diffusion MRI to predict a wide range of biomarkers in patients with glioma.

Methods

In this retrospective study, patients were included if they (1) had diagnosis of gliomas with known IDH1, EGFR, MGMT, ATRX, TP53, and PTEN status from surgical pathology and (2) had preoperative MRI including FLAIR, T1c+ and diffusion for radiomic texture analysis. Statistical analysis included logistic regression and receiver-operating characteristic (ROC) curve analysis to determine the optimal model for predicting glioma biomarkers. A comparative analysis between ROCs (conventional only vs conventional + diffusion) was performed.

Results

From a total of 111 patients included, 91 (82%) were categorized to training and 20 (18%) to test datasets. Constructed cross-validated model using a combination of texture features from conventional and diffusion MRI resulted in overall AUC/accuracy of 1/79% for IDH1, 0.99/80% for ATRX, 0.79/67% for MGMT, and 0.77/66% for EGFR. The addition of diffusion data to conventional MRI features significantly (P < .05) increased predictive performance for IDH1, MGMT, and ATRX. The overall accuracy of the final model in predicting biomarkers in the test group was 80% (IDH1), 70% (ATRX), 70% (MGMT), and 75% (EGFR).

Conclusion

Addition of MR diffusion to conventional MRI features provides added diagnostic value in preoperative determination of IDH1, MGMT, and ATRX in patients with glioma.

Machine Learning for the Prediction of Molecular Markers in Glioma on Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis

BACKGROUND

Molecular characterization of glioma has implications for prognosis, treatment planning, and prediction of treatment response. Current histopathology is limited by intratumoral heterogeneity and variability in detection methods. Advances in computational techniques have led to interest in mining quantitative imaging features to noninvasively detect genetic mutations.

OBJECTIVE

To evaluate the diagnostic accuracy of machine learning (ML) models in molecular subtyping gliomas on preoperative magnetic resonance imaging (MRI).

METHODS

A systematic search was performed following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify studies up to April 1, 2020. Methodological quality of studies was assessed using the Quality Assessment for Diagnostic Accuracy Studies (QUADAS)-2. Diagnostic performance estimates were obtained using a bivariate model and heterogeneity was explored using metaregression.

RESULTS

Forty-four original articles were included. The pooled sensitivity and specificity for predicting isocitrate dehydrogenase (IDH) mutation in training datasets were 0.88 (95% CI 0.83-0.91) and 0.86 (95% CI 0.79-0.91), respectively, and 0.83 to 0.85 in validation sets. Use of data augmentation and MRI sequence type were weakly associated with heterogeneity. Both O6-methylguanine-DNA methyltransferase (MGMT) gene promoter methylation and 1p/19q codeletion could be predicted with a pooled sensitivity and specificity between 0.76 and 0.83 in training datasets.

CONCLUSION

ML application to preoperative MRI demonstrated promising results for predicting IDH mutation, MGMT methylation, and 1p/19q codeletion in glioma. Optimized ML models could lead to a noninvasive, objective tool that captures molecular information important for clinical decision making. Future studies should use multicenter data, external validation and investigate clinical feasibility of ML models.

Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomics for Prediction of H3K27M Mutation in Midline Gliomas

OBJECTIVE

H3K27M mutation in gliomas has prognostic implications. Previous magnetic resonance imaging (MRI) studies have reported variable rates of tumoral enhancement, necrotic changes, and peritumoral edema in H3K27M-mutant gliomas, with no distinguishing imaging features compared with wild-type gliomas. We aimed to construct an MRI machine learning (ML)-based radiomic model to predict H3K27M mutation in midline gliomas.

METHODS

A total of 109 patients from 3 academic centers were included in this study. Fifty patients had H3K27M mutation and 59 were wild-type. Conventional MRI sequences (T1-weighted, T2-weighted, T2-fluid-attenuated inversion recovery, postcontrast T1-weighted, and apparent diffusion coefficient maps) were used for feature extraction. A total of 651 radiomic features per each sequence were extracted. Patients were randomly selected with a 7:3 ratio to create training (n = 76) and test (n = 33) data sets. An extreme gradient boosting algorithm (XGBoost) was used in ML-based model development. Performance of the model was assessed by area under the receiver operating characteristic curve.

RESULTS

Pediatric patients accounted for a larger proportion of the study cohort (60 pediatric [55%] vs. 49 adult [45%] patients). XGBoost with additional feature selection had an area under the receiver operating characteristic curve of 0.791 and 0.737 in the training and test data sets, respectively. The model achieved accuracy, precision (positive predictive value), recall (sensitivity), and F1 (harmonic mean of precision and recall) measures of 72.7%, 76.5%, 72.2%, and 74.3%, respectively, in the test set.

CONCLUSIONS

Our multi-institutional study suggests that ML-based radiomic analysis of multiparametric MRI can be a promising noninvasive technique to predict H3K27M mutation status in midline gliomas.

A computed tomography (CT)-derived radiomics approach for predicting primary co-mutations involving TP53 and epidermal growth factor receptor (EGFR) in patients with advanced lung adenocarcinomas (LUAD)

Background

Epidermal growth factor receptor (EGFR) co-mutated with TP53 could reduce responsiveness to tyrosine kinase inhibitors (TKIs) and worsen patients' prognosis compared to TP53 wild type patients in.

EGFR

mutated lung adenocarcinomas (LUAD). To identify this genetically unique subset prior to treatment through computed tomography (CT) images had not been reported yet.

Methods

Stage III and IV LUAD with known mutation status of EGFR and TP53 from The First Affiliated Hospital of Sun Yat-sen University (May 1, 2017 to June 1, 2020) were collected. Characteristics of pretreatment enhanced-CT images were analyzed. One-versus-one was used as the multiclass classification strategy to distinguish the three subtypes of co-mutations: EGFR ⁺ & TP53 ⁺, EGFR ⁺ & TP53 ^-, EGFR ^-. The clinical model, semantic model, radiomics model and integrated model were built. Area under the receiver-operating characteristic curves (AUCs) were used to evaluate the prediction efficacy.

Results

A total of 199 patients were enrolled, including 83 (42%) cases of EGFR ^-, 55 (28%) cases of EGFR ⁺ & TP53 ⁺, 61 (31%) cases of EGFR ⁺ & TP53 ^-. Among the four different models, the integrated model displayed the best performance for all the three subtypes of co-mutations: EGFR ^- (AUC, 0.857; accuracy, 0.817; sensitivity, 0.998; specificity, 0.663), EGFR ⁺ & TP53 ⁺ (AUC, 0.791; accuracy, 0.758; sensitivity, 0.762; specificity, 0.783), EGFR ⁺ & TP53 ^- (AUC, 0.761; accuracy, 0.813; sensitivity, 0.594; specificity, 0.977). The radiomics model was slightly inferior to the integrated model. The results for the clinical and the semantic models were dissatisfactory, with AUCs less than 0.700 for all the three subtypes.

Conclusions

CT imaging based artificial intelligence (AI) is expected to distinguish co-mutation status involving TP53 and EGFR. The proposed integrated model may serve as an important alternative marker for preselecting patients who will be adaptable to and sensitive to TKIs.

Relations between Electronics, Artificial Intelligence and Information Society through Information Society Rules

This paper presents relations between information society (IS), electronics and artificial intelligence (AI) mainly through twenty-four IS laws. The laws not only make up a novel collection, currently non-existing in the literature, but they also highlight the core boosting mechanism for the progress of what is called the information society and AI. The laws mainly describe the exponential growth in a particular field, be it the processing, storage or transmission capabilities of electronic devices. Other rules describe the relations to production prices and human interaction. Overall, the IS laws illustrate the most recent and most vibrant part of human history based on the unprecedented growth of device capabilities spurred by human innovation and ingenuity. Although there are signs of stalling, at the same time there are still many ways to prolong the fascinating progress of electronics that stimulates the field of artificial intelligence. There are constant leaps in new areas, such as the perception of real-world signals, where AI is already occasionally exceeding human capabilities and will do so even more in the future. In some areas where AI is presumed to be incapable of performing even at a modest level, such as the production of art or programming software, AI is making progress that can sometimes reflect true human skills. Maybe it is time for AI to boost the progress of electronics in return.

Radiogenomic modeling predicts survival-associated prognostic groups in glioblastoma

Background

Combined whole-exome sequencing (WES) and somatic copy number alteration (SCNA) information can separate isocitrate dehydrogenase (IDH)1/2-wildtype glioblastoma into two prognostic molecular subtypes, which cannot be distinguished by epigenetic or clinical features. The potential for radiographic features to discriminate between these molecular subtypes has yet to be established.

Methods

Radiologic features (n = 35 340) were extracted from 46 multisequence, pre-operative magnetic resonance imaging (MRI) scans of IDH1/2-wildtype glioblastoma patients from The Cancer Imaging Archive (TCIA), all of whom have corresponding WES/SCNA data. We developed a novel feature selection method that leverages the structure of extracted MRI features to mitigate the dimensionality challenge posed by the disparity between a large number of features and the limited patients in our cohort. Six traditional machine learning classifiers were trained to distinguish molecular subtypes using our feature selection method, which was compared to least absolute shrinkage and selection operator (LASSO) feature selection, recursive feature elimination, and variance thresholding.

Results

We were able to classify glioblastomas into two prognostic subgroups with a cross-validated area under the curve score of 0.80 (±0.03) using ridge logistic regression on the 15-dimensional principle component analysis (PCA) embedding of the features selected by our novel feature selection method. An interrogation of the selected features suggested that features describing contours in the T2 signal abnormality region on the T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI sequence may best distinguish these two groups from one another.

Conclusions

We successfully trained a machine learning model that allows for relevant targeted feature extraction from standard MRI to accurately predict molecularly-defined risk-stratifying IDH1/2-wildtype glioblastoma patient groups.

Automated machine learning based on radiomics features predicts H3 K27M mutation in midline gliomas of the brain

BACKGROUND

Conventional MRI cannot be used to identify H3 K27M mutation status. This study aimed to investigate the feasibility of predicting H3 K27M mutation status by applying an automated machine learning (autoML) approach to the MR radiomics features of patients with midline gliomas.

METHODS

This single-institution retrospective study included 100 patients with midline gliomas, including 40 patients with H3 K27M mutations and 60 wild-type patients. Radiomics features were extracted from fluid-attenuated inversion recovery images. Prior to autoML analysis, the dataset was randomly stratified into separate 75% training and 25% testing cohorts. The Tree-based Pipeline Optimization Tool (TPOT) was applied to optimize the machine learning pipeline and select important radiomics features. We compared the performance of 10 independent TPOT-generated models based on training and testing cohorts using the area under the curve (AUC) and average precision to obtain the final model. An independent cohort of 22 patients was used to validate the best model.

RESULTS

Ten prediction models were generated by TPOT, and the accuracy obtained with the best pipeline ranged from 0.788 to 0.867 for the training cohort and from 0.60 to 0.84 for the testing cohort. After comparison, the AUC value and average precision of the final model were 0.903 and 0.911 in the testing cohort, respectively. In the validation set, the AUC was 0.85, and the average precision was 0.855 for the best model.

CONCLUSIONS

The autoML classifier using radiomics features of conventional MR images provides high discriminatory accuracy in predicting the H3 K27M mutation status of midline glioma.

Noninvasive Determination of IDH and 1p19q Status of Lower-grade Gliomas Using MRI Radiomics: A Systematic Review

BACKGROUND

Determination of isocitrate dehydrogenase (IDH) status and, if IDH-mutant, assessing 1p19q codeletion are an important component of diagnosis of World Health Organization grades II/III or lower-grade gliomas. This has led to research into noninvasively correlating imaging features ("radiomics") with genetic status.

PURPOSE

Our aim was to perform a diagnostic test accuracy systematic review for classifying IDH and 1p19q status using MR imaging radiomics, to provide future directions for integration into clinical radiology.

DATA SOURCES

Ovid (MEDLINE), Scopus, and the Web of Science were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Diagnostic Test Accuracy guidelines.

STUDY SELECTION

Fourteen journal articles were selected that included 1655 lower-grade gliomas classified by their IDH and/or 1p19q status from MR imaging radiomic features.

DATA ANALYSIS

For each article, the classification of IDH and/or 1p19q status using MR imaging radiomics was evaluated using the area under curve or descriptive statistics. Quality assessment was performed with the Quality Assessment of Diagnostic Accuracy Studies 2 tool and the radiomics quality score.

DATA SYNTHESIS

The best classifier of IDH status was with conventional radiomics in combination with convolutional neural network-derived features (area under the curve  = 0.95, 94.4% sensitivity, 86.7% specificity). Optimal classification of 1p19q status occurred with texture-based radiomics (area under the curve  = 0.96, 90% sensitivity, 89% specificity).

LIMITATIONS

A meta-analysis showed high heterogeneity due to the uniqueness of radiomic pipelines.

CONCLUSIONS

Radiogenomics is a potential alternative to standard invasive biopsy techniques for determination of IDH and 1p19q status in lower-grade gliomas but requires translational research for clinical uptake.

Predicting Isocitrate Dehydrogenase (IDH) Mutation Status in Gliomas Using Multiparameter MRI Radiomics Features

BACKGROUND

Accurate and noninvasive detection of isocitrate dehydrogenase (IDH, including IDH1 and IDH2) status is clinically meaningful for molecular stratification of glioma, but remains challenging.

PURPOSE

To establish a model for classifying IDH status in gliomas based on multiparametric MRI.

STUDY TYPE

Retrospective, radiomics.

POPULATION

In all, 105 consecutive cases of grade II-IV glioma with 50 IDH1 or IDH2 mutant (IDHm) and 55 IDH wildtype (IDHw) were separated into a training cohort (n = 73) and a test cohort (n = 32).

FIELD STRENGTH/SEQUENCE

Contrast-enhanced T₁ -weighted (CE-T₁ W), T₂ -weighted (T₂ W), and arterial spin labeling (ASL) images were acquired at 3.0T.

ASSESSMENT

Two doctors manually labeled the volume of interest (VOI) on CE-T₁ W, then T₂ W and ASL were coregistered to CE-T₁ W. A total of 851 radiomics features were extracted on each VOI of three sequences. From the training cohort, all radiomics features with age and gender were processed by the Mann-Whitney U-test, Pearson test, and least absolute shrinkage and selection operator to obtain optimal feature groups to train support vector machine models. The accuracy and area under curve (AUC) of all models for classifying the IDH status were calculated on the test cohort. Two subtasks were performed to verify the efficiency of texture features and the Pearson test in IDH status classification, respectively.

STATISTICAL TESTS

The permutation test with Bonferroni correction; chi-square test.

RESULTS

The accuracy and AUC of the classifier, which combines the features of all three sequences, achieved 0.823 and 0.770 (P < 0.05), respectively. The best model established by texture features only had an AUC of 0.819 and an accuracy of 0.761. The best model established without the Pearson test got an AUC of 0.747 and an accuracy of 0.719.

DATA CONCLUSION

IDH genotypes of glioma can be identified by radiomics features from multiparameter MRI. The Pearson test improved the performance of the IDH classification models.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 1.

MRI Radiomic Features to Predict IDH1 Mutation Status in Gliomas: A Machine Learning Approach using Gradient Tree Boosting

Patients with gliomas, isocitrate dehydrogenase 1 (IDH1) mutation status have been studied as a prognostic indicator. Recent advances in machine learning (ML) have demonstrated promise in utilizing radiomic features to study disease processes in the brain. We investigate whether ML analysis of multiparametric radiomic features from preoperative Magnetic Resonance Imaging (MRI) can predict IDH1 mutation status in patients with glioma. This retrospective study included patients with glioma with known IDH1 status and preoperative MRI. Radiomic features were extracted from Fluid-Attenuated Inversion Recovery (FLAIR) and Diffused Weighted Imaging (DWI). The dataset was split into training, validation, and testing sets by stratified sampling. Synthetic Minority Oversampling Technique (SMOTE) was applied to the training sets. eXtreme Gradient Boosting (XGBoost) classifiers were trained, and the hyperparameters were tuned. Receiver operating characteristic curve (ROC), accuracy, and f1-scores were collected. A total of 100 patients (age: 55 ± 15, M/F 60/40); with IDH1 mutant (n = 22) and IDH1 wildtype (n = 78) were included. The best performance was seen with a DWI-trained XGBoost model, which achieved ROC with Area Under the Curve (AUC) of 0.97, accuracy of 0.90, and f1-score of 0.75 on the test set. The FLAIR-trained XGBoost model achieved ROC with AUC of 0.95, accuracy of 0.90, f1-score of 0.75 on the test set. A model that was trained on combined FLAIR-DWI radiomic features did not provide incremental accuracy. The results show that a XGBoost classifier using multiparametric radiomic features derived from preoperative MRI can predict IDH1 mutation status with > 90% accuracy.

Pretreatment structural and arterial spin labeling MRI is predictive for p53 mutation in high-grade gliomas

OBJECTIVES

To determine the performance of pretreatment structural and arterial spin labelling (ASL) MRI in predicting p53 mutation in patients with high-grade gliomas (HGGs).

METHODS

Pre-treatment structural and ASL MRI were performed in 57 patients with histologically confirmed HGGs and information of p53 status. Whole-lesion histogram analysis of cerebral blood flow (CBF) images of the enhancing tumour and the peritumoral oedema in the HGGs were performed. Visually AcceSAble Rembrandt Images features were used as qualitative analysis. The differences of ASL histogram parameters and Visually AcceSAble Rembrandt Images features between HGGs with or without p53 mutation were analyzed with post hoc correction for multiple comparisons. LASSO regression was performed to select the optimal features that could predict p53 mutation, followed by receiver operating characteristic analysis to determine the predictive efficacy.

RESULTS

A total of 33 HGGs with p53 mutation and 24 without p53 mutation were included. HGGs with mutant p53 showed lower CBF_percentile5 and CBF_uniformity of the enhancing tumour (p < 0.05) and higher prevalence of the qualitative MRI feature of enhancing tumour crossing midline (ETCM) (p < 0.05) as compared with HGGs with wild-type p53. LASSO regression showed that the CBF_uniformity of the enhancing tumour and ETCM were predictive features for p53 mutation. CBF_uniformity showed an acceptable performance in predicting p53 mutation (area under the curve = 0.721), when combined with the feature of ETCM, its predictive efficacy was significantly improved (area under the curve = 0.814, p = 0.012).

CONCLUSION

An integrated pre-treatment structural and ASL MRI can help to predict p53 mutation in HGGs.

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning

Background

Sarcopenia has been confirmed as a poor prognostic indicator of lung cancer. However, the lack of abdominal computed tomography (CT) hindered the application to assess the status of sarcopenia. The purpose of this study was to assess the ability of chest CT radiomics combined with machine learning classifiers to identify sarcopenia in advanced non‐small cell lung cancer (NSCLC) patients.

Methods

This study retrospectively analyzed CT images of 99 patients with NSCLC. Skeletal muscle radiomics were extracted from a single axial slice of the chest CT scan at the 12th thoracic vertebrae level. In total, 854 radiomic and clinical features were obtained from each patient. Feature selection was conducted with FeatureSelector module, optimal key features were fed into the lightGBM classifier for model construction, and Bayesian optimization was adopted to tune hyperparameters. The model's performance was evaluated by specificity, sensitivity, accuracy, precision, F1‐score, Matthew's correlation coefficient (MCC), Cohen's kappa coefficient (Kappa), and AUC.

Results

A total of 40 patients were found to have sarcopenia. Five optimal features were selected. In the base lightGBM model, the specificity, sensitivity, accuracy, precision, F1‐score, AUC, MCC, Kappa of validation set were 0.889, 0.750, 0.833, 0.818, 0.783, 0.819, 0.649, 0.648, respectively. After Bayesian hyperparameter tuning, the optimized lightGBM model achieved better prediction performance, and the corresponding values were 0.944, 0.833, 0.900, 0.909, 0.870, 0.889, 0.791, 0.789, respectively.

Conclusions

Chest CT‐based radiomics has the potential to identify sarcopenia in NSCLC patients with the lightGBM classifier, and the optimal lightGBM model via Bayesian hyperparameter tuning demonstrated better performance.

Key points

Significant findings of the study

Our study demonstrates that chest CT‐based radiomics combined with lightGBM classifier has the ability to identify sarcopenia in NSCLC patients.

What this study adds

Skeletal muscle radiomics would be a potential biomarker for sarcopenia identity in NSCLC patients.

Radiomics risk score may be a potential imaging biomarker for predicting survival in isocitrate dehydrogenase wild-type lower-grade gliomas

OBJECTIVES

Isocitrate dehydrogenase wild-type (IDHwt) lower-grade gliomas of histologic grades II and III follow heterogeneous clinical outcomes, which necessitates risk stratification. We aimed to evaluate whether radiomics from MRI would allow prediction of overall survival in patients with IDHwt lower-grade gliomas and to investigate the added prognostic value of radiomics over clinical features.

METHODS

Preoperative MRIs of 117 patients with IDHwt lower-grade gliomas from January 2007 to February 2018 were retrospectively analyzed. The external validation cohort consisted of 33 patients from The Cancer Genome Atlas. A total of 182 radiomic features were extracted. Radiomics risk scores (RRSs) for overall survival were derived from the least absolute shrinkage and selection operator (LASSO) and elastic net. Multivariable Cox regression analyses, including clinical features and RRSs, were performed. The integrated areas under the receiver operating characteristic curves (iAUCs) from models with and without RRSs were calculated for comparisons. The prognostic value of RRS was assessed in the validation cohort.

RESULTS

The RRS derived from LASSO and elastic net independently predicted survival with hazard ratios of 9.479 (95% confidence interval [CI], 3.220-27.847) and 6.148 (95% CI, 3.009-12.563), respectively. Those RRSs enhanced model performance for predicting overall survival (iAUC increased to 0.780-0.797 from 0.726), which was externally validated. The RRSs stratified IDHwt lower-grade gliomas in the validation cohort with significantly different survival.

CONCLUSION

Radiomics has the potential for noninvasive risk stratification and can improve prediction of overall survival in patients with IDHwt lower-grade gliomas when integrated with clinical features.

KEY POINTS

• Isocitrate dehydrogenase wild-type lower-grade gliomas with histologic grades II and III follow heterogeneous clinical outcomes, which necessitates further risk stratification. • Radiomics risk scores derived from MRI independently predict survival even after incorporating strong clinical prognostic features (hazard ratios 6.148-9.479). • Radiomics risk scores derived from MRI have the potential to improve survival prediction when added to clinical features (integrated areas under the receiver operating characteristic curves increased from 0.726 to 0.780-0.797).

Deep semi-supervised learning for brain tumor classification

Background

This paper addresses issues of brain tumor, glioma, classification from four modalities of Magnetic Resonance Image (MRI) scans (i.e., T1 weighted MRI, T1 weighted MRI with contrast-enhanced, T2 weighted MRI and FLAIR). Currently, many available glioma datasets often contain some unlabeled brain scans, and many datasets are moderate in size.

Methods

We propose to exploit deep semi-supervised learning to make full use of the unlabeled data. Deep CNN features were incorporated into a new graph-based semi-supervised learning framework for learning the labels of the unlabeled data, where a new 3D-2D consistent constraint is added to make consistent classifications for the 2D slices from the same 3D brain scan. A deep-learning classifier is then trained to classify different glioma types using both labeled and unlabeled data with estimated labels. To alleviate the overfitting caused by moderate-size datasets, synthetic MRIs generated by Generative Adversarial Networks (GANs) are added in the training of CNNs.

Results

The proposed scheme has been tested on two glioma datasets, TCGA dataset for IDH-mutation prediction (molecular-based glioma subtype classification) and MICCAI dataset for glioma grading. Our results have shown good performance (with test accuracies 86.53% on TCGA dataset and 90.70% on MICCAI dataset).

Conclusions

The proposed scheme is effective for glioma IDH-mutation prediction and glioma grading, and its performance is comparable to the state-of-the-art.

Radiomics and Deep Learning from Research to Clinical Workflow: Neuro-Oncologic Imaging

Imaging plays a key role in the management of brain tumors, including the diagnosis, prognosis, and treatment response assessment. Radiomics and deep learning approaches, along with various advanced physiologic imaging parameters, hold great potential for aiding radiological assessments in neuro-oncology. The ongoing development of new technology needs to be validated in clinical trials and incorporated into the clinical workflow. However, none of the potential neuro-oncological applications for radiomics and deep learning has yet been realized in clinical practice. In this review, we summarize the current applications of radiomics and deep learning in neuro-oncology and discuss challenges in relation to evidence-based medicine and reporting guidelines, as well as potential applications in clinical workflows and routine clinical practice.

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first- and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen–Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and second-order features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61–0.73) to 0.82 (95% CI 0.79–0.84, P = .006), 0.79 (95% CI 0.76–0.82, P = .021) and 0.82 (95% CI 0.80–0.85, P = .005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained using the 32 bins considering both T1w-gd and T2w-flair sequences. No significant improvements in classification performances were observed using feature selection. A standardized pre-processing pipeline is proposed for the use of radiomics in MRI of brain tumours. For models based on first- and second-order features, we recommend normalizing images with the Z-Score method and adopting an absolute discretization approach. For second-order feature-based signatures, relative discretization can be used without prior normalization. In both cases, 32 bins for discretization are recommended. This study may pave the way for the multicentric development and validation of MR-based radiomics biomarkers.