Textural features of dynamic contrast-enhanced MRI derived model-free and model-based parameter maps in glioma grading

Artificial intelligence-based MRI radiomics and radiogenomics in glioma

The specific genetic subtypes that gliomas exhibit result in variable clinical courses and the need to involve multidisciplinary teams of neurologists, epileptologists, neurooncologists and neurosurgeons. Currently, the diagnosis of gliomas pivots mainly around the preliminary radiological findings and the subsequent definitive surgical diagnosis (via surgical sampling). Radiomics and radiogenomics present a potential to precisely diagnose and predict survival and treatment responses, via morphological, textural, and functional features derived from MRI data, as well as genomic data. In spite of their advantages, it is still lacking standardized processes of feature extraction and analysis methodology among different research groups, which have made external validations infeasible. Radiomics and radiogenomics can be used to better understand the genomic basis of gliomas, such as tumor spatial heterogeneity, treatment response, molecular classifications and tumor microenvironment immune infiltration. These novel techniques have also been used to predict histological features, grade or even overall survival in gliomas. In this review, workflows of radiomics and radiogenomics are elucidated, with recent research on machine learning or artificial intelligence in glioma.

An image-based modeling framework for predicting spatiotemporal brain cancer biology within individual patients

Imaging is central to the clinical surveillance of brain tumors yet it provides limited insight into a tumor's underlying biology. Machine learning and other mathematical modeling approaches can leverage paired magnetic resonance images and image-localized tissue samples to predict almost any characteristic of a tumor. Image-based modeling takes advantage of the spatial resolution of routine clinical scans and can be applied to measure biological differences within a tumor, changes over time, as well as the variance between patients. This approach is non-invasive and circumvents the intrinsic challenges of inter- and intratumoral heterogeneity that have historically hindered the complete assessment of tumor biology and treatment responsiveness. It can also reveal tumor characteristics that may guide both surgical and medical decision-making in real-time. Here we describe a general framework for the acquisition of image-localized biopsies and the construction of spatiotemporal radiomics models, as well as case examples of how this approach may be used to address clinically relevant questions.

Textural Features of Mouse Glioma Models Measured by Dynamic Contrast-Enhanced MR Images with 3D Isotropic Resolution

This paper investigates the effect of anisotropic resolution on the image textural features of pharmacokinetic (PK) parameters of a murine glioma model using dynamic contrast-enhanced (DCE) MR images acquired with an isotropic resolution at 7T with pre-contrast T1 mapping. The PK parameter maps of whole tumors at isotropic resolution were generated using the two-compartment exchange model combined with the three-site-two-exchange model. The textural features of these isotropic images were compared with those of simulated, thick-slice, anisotropic images to assess the influence of anisotropic voxel resolution on the textural features of tumors. The isotropic images and parameter maps captured distributions of high pixel intensity that were absent in the corresponding anisotropic images with thick slices. A significant difference was observed in 33% of the histogram and textural features extracted from anisotropic images and parameter maps, compared to those extracted from corresponding isotropic images. Anisotropic images in different orthogonal orientations demonstrated 42.1% of the histogram and textural features to be significantly different from those of isotropic images. This study demonstrates that the anisotropy of voxel resolution needs to be carefully considered when comparing the textual features of tumor PK parameters and contrast-enhanced images.

Diagnostic Performance of Selected MRI-Derived Radiomics Able to Discriminate Progression-Free and Overall Survival in Patients with Midline Glioma and the H3F3AK27M Mutation

BACKGROUND

Radiomics refers to a recent area of knowledge that studies features extracted from different imaging techniques and subsequently transformed into high-dimensional data that can be associated with biological events. Diffuse midline gliomas (DMG) are one of the most devastating types of cancer, with a median survival of approximately 11 months after diagnosis and 4-5 months after radiological and clinical progression.

METHODS

A retrospective study. From a database of 91 patients with DMG, only 12 had the H3.3K27M mutation and brain MRI DICOM files available. Radiomic features were extracted from MRI T1 and T2 sequences using LIFEx software. Statistical analysis included normal distribution tests and the Mann-Whitney U test, ROC analysis, and calculation of cut-off values.

RESULTS

A total of 5760 radiomic values were included in the analyses. AUROC demonstrated 13 radiomics with statistical significance for progression-free survival (PFS) and overall survival (OS). Diagnostic performance tests showed nine radiomics with specificity for PFS above 90% and one with a sensitivity of 97.2%. For OS, 3 out of 4 radiomics demonstrated between 80 and 90% sensitivity.

CONCLUSIONS

Several radiomic features demonstrated statistical significance and have the potential to further aid DMG diagnostic assessment non-invasively. The most significant radiomics were first- and second-order features with GLCM texture profile, GLZLM_GLNU, and NGLDM_Contrast.

MRI radiomics and potential applications to glioblastoma

MRI plays an important role in the evaluation of glioblastoma, both at initial diagnosis and follow up after treatment. Quantitative analysis via radiomics can augment the interpretation of MRI in terms of providing insights regarding the differential diagnosis, genotype, treatment response, and prognosis. The various MRI radiomic features of glioblastoma are reviewed in this article.

A new biomarker combining multimodal MRI radiomics and clinical indicators for differentiating inverted papilloma from nasal polyp invaded the olfactory nerve possibly

Background and purpose

Inverted papilloma (IP) and nasal polyp (NP), as two benign lesions, are difficult to distinguish on MRI imaging and clinically, especially in predicting whether the olfactory nerve is damaged, which is an important aspect of treatment and prognosis. We plan to establish a new biomarker to distinguish IP and NP that may invade the olfactory nerve, and to analyze its diagnostic efficacy.

Materials and methods

A total of 74 cases of IP and 55 cases of NP were collected. A total of 80% of 129 patients were used as the training set (59 IP and 44 NP); the remaining were used as the testing set. As a multimodal study (two MRI sequences and clinical indicators), preoperative MR images including T2-weighted magnetic resonance imaging (T2-WI) and contrast-enhanced T1-weighted magnetic resonance imaging (CE-T1WI) were collected. Radiomic features were extracted from MR images. Then, the least absolute shrinkage and selection operator (LASSO) regression method was used to decrease the high degree of redundancy and irrelevance. Subsequently, the radiomics model is constructed by the rad scoring formula. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the model have been calculated. Finally, the decision curve analysis (DCA) is used to evaluate the clinical practicability of the model.

Results

There were significant differences in age, nasal bleeding, and hyposmia between the two lesions (p < 0.05). In total, 1,906 radiomic features were extracted from T2-WI and CE-T1WI images. After feature selection, using 12 key features to bulid model. AUC, sensitivity, specificity, and accuracy on the testing cohort of the optimal model were, respectively, 0.9121, 0.828, 0.9091, and 0.899. AUC on the testing cohort of the optimal model was 0.9121; in addition, sensitivity, specificity, and accuracy were, respectively, 0.828, 0.9091, and 0.899.

Conclusion

A new biomarker combining multimodal MRI radiomics and clinical indicators can effectively distinguish between IP and NP that may invade the olfactory nerve, which can provide a valuable decision basis for individualized treatment.

A triple-classification for differentiating renal oncocytoma from renal cell carcinoma subtypes and CK7 expression evaluation: a radiomics analysis

Background

To investigate the value of computed tomography (CT)-based radiomics model analysis in differentiating renal oncocytoma (RO) from renal cell carcinoma subtypes (chromophobe renal cell carcinoma, clear cell carcinoma) and predicting the expression of Cytokeratin 7 (CK7).

Methods

In this retrospective study, radiomics was applied for patients with RO, chRCC and ccRCC who underwent surgery between January 2013 and December 2019 comprised the training cohort, and the testing cohort was collected between January and October 2020. The corticomedullary (CMP) and nephrographic phases (NP) were manually segmented, and radiomics texture parameters were extracted. Support vector machine was generated from CMP and NP after feature selection. Shapley additive explanations were applied to interpret the radiomics features. A radiomics signature was built using the selected features from the two phases, and the radiomics nomogram was constructed by incorporating the radiomics features and clinical factors. Receiver operating characteristic curve was calculated to evaluate the above models in the two sets. Furthermore, Rad-score was used for correlation analysis with CK7.

Results

A total of 123 patients with RO, chRCC and ccRCC were analyzed in the training cohort and 57 patients in the testing cohort. Subsequently, 396 radiomics features were selected from each phase. The radiomics features combining two phases yielded the highest area under the curve values of 0.941 and 0.935 in the training and testing sets, respectively. The Pearson’s correlation coefficient was statistically significant between Rad-score and CK7.

Conclusion

We proposed a non-invasive and individualized CT-based radiomics nomogram to differentiation among RO, chRCC and ccRCC preoperatively and predict the immunohistochemical protein expression for accurate clinical diagnosis and treatment decision.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12894-022-01099-0.

Dynamic contrast-enhanced (DCE) imaging: state of the art and applications in whole-body imaging

Dynamic contrast-enhanced (DCE) imaging is a non-invasive technique used for the evaluation of tissue vascularity features through imaging series acquisition after contrast medium administration. Over the years, the study technique and protocols have evolved, seeing a growing application of this method across different imaging modalities for the study of almost all body districts. The main and most consolidated current applications concern MRI imaging for the study of tumors, but an increasing number of studies are evaluating the use of this technique also for inflammatory pathologies and functional studies. Furthermore, the recent advent of artificial intelligence techniques is opening up a vast scenario for the analysis of quantitative information deriving from DCE. The purpose of this article is to provide a comprehensive update on the techniques, protocols, and clinical applications - both established and emerging - of DCE in whole-body imaging.

Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging

This article is a comprehensive review of the basic background, technique, and clinical applications of artificial intelligence (AI) and radiomics in the field of neuro-oncology. A variety of AI and radiomics utilized conventional and advanced techniques to differentiate brain tumors from non-neoplastic lesions such as inflammatory and demyelinating brain lesions. It is used in the diagnosis of gliomas and discrimination of gliomas from lymphomas and metastasis. Also, semiautomated and automated tumor segmentation has been developed for radiotherapy planning and follow-up. It has a role in the grading, prediction of treatment response, and prognosis of gliomas. Radiogenomics allowed the connection of the imaging phenotype of the tumor to its molecular environment. In addition, AI is applied for the assessment of extra-axial brain tumors and pediatric tumors with high performance in tumor detection, classification, and stratification of patient's prognoses.

Radiomics and radiogenomics in gliomas: a contemporary update

The natural history and treatment landscape of primary brain tumours are complicated by the varied tumour behaviour of primary or secondary gliomas (high-grade transformation of low-grade lesions), as well as the dilemmas with identification of radiation necrosis, tumour progression, and pseudoprogression on MRI. Radiomics and radiogenomics promise to offer precise diagnosis, predict prognosis, and assess tumour response to modern chemotherapy/immunotherapy and radiation therapy. This is achieved by a triumvirate of morphological, textural, and functional signatures, derived from a high-throughput extraction of quantitative voxel-level MR image metrics. However, the lack of standardisation of acquisition parameters and inconsistent methodology between working groups have made validations unreliable, hence multi-centre studies involving heterogenous study populations are warranted. We elucidate novel radiomic and radiogenomic workflow concepts and state-of-the-art descriptors in sub-visual MR image processing, with relevant literature on applications of such machine learning techniques in glioma management.

Advanced Diagnosis of Glioma by Using Emerging Magnetic Resonance Sequences

Glioma, the most common primary brain tumor in adults, can be difficult to discern radiologically from other brain lesions, which affects surgical planning and follow-up treatment. Recent advances in MRI demonstrate that preoperative diagnosis of glioma has stepped into molecular and algorithm-assisted levels. Specifically, the histology-based glioma classification is composed of multiple different molecular subtypes with distinct behavior, prognosis, and response to therapy, and now each aspect can be assessed by corresponding emerging MR sequences like amide proton transfer-weighted MRI, inflow-based vascular-space-occupancy MRI, and radiomics algorithm. As a result of this novel progress, the clinical practice of glioma has been updated. Accurate diagnosis of glioma at the molecular level can be achieved ahead of the operation to formulate a thorough plan including surgery radical level, shortened length of stay, flexible follow-up plan, timely therapy response feedback, and eventually benefit patients individually.

Association Between Histopathology and Magnetic Resonance Imaging Texture in Grading Gliomas Based on Intraoperative Magnetic Resonance Navigated Stereotactic Biopsy

OBJECTIVE

To explore the value of magnetic resonance imaging (MRI) textures and its correlation with histopathological malignancy of gliomas by magnetic resonance (MR) navigated stereotactic biopsy.

METHODS

A total of 36 diffuse glioma cases and 64 puncture targets were included. All patients underwent a preoperative MR scan and intraoperative MR-navigated stereotactic biopsy. The histopathological diagnosis was grade II or grade III diffuse glioma. Regions of interest consistent with puncture targets were delineated on T1-weighted brain volume with gadolinium contrast enhancement images, and textures were extracted using Omni Kinetics software. Mann-Whitney rank sum test was used to analyze texture differences between grade II and grade III samples. False discovery rate (FDR) correction was applied to correct for multiple comparisons. Receiver operating characteristic curves evaluated the diagnostic value of textural analysis for grading gliomas. Correlation between MRI textures and histopathology was examined by Spearman correlation test.

RESULTS

Texture features, including max intensity, 95th quantile, range, variance, standard deviation, sum variance, and cluster prominence were higher in grade III glioma targets than grade IIs, grade II gliomas showed increased uniformity and short run low gray-level emphasis values (P and qFDRcorr < 0.05). Area under the curve was 0.887 (95% confidence interval, 0.805-0.969; P < 0.001) with combined textures in glioma grading. The listed first-order and gray-level cooccurrence matrix textures were correlated with Ki-67 labeling index. Gray-level cooccurrence matrix and gray-level run length matrix textures were correlated with isocitrate dehydrogenase 1 mutation.

CONCLUSIONS

Textures on T1-weighted brain volume with gadolinium contrast enhancement images differ between grade III and II gliomas and are correlated with Ki-67 labeling index and isocitrate dehydrogenase 1 mutation.

CT Texture Analysis for Differentiating Bronchiolar Adenoma, Adenocarcinoma In Situ, and Minimally Invasive Adenocarcinoma of the Lung

Purpose: This study aimed to investigate the potential of computed tomography (CT) imaging features and texture analysis to distinguish bronchiolar adenoma (BA) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA).

Materials and Methods: Fifteen patients with BA, 38 patients with AIS, and 36 patients with MIA were included in this study. Clinical data and CT imaging features of the three lesions were evaluated. Texture features were extracted from the thin-section unenhanced CT images using Artificial Intelligence Kit software. Then, multivariate logistic regression analysis based on selected texture features was employed to distinguish BA from AIS/MIA. Receiver operating characteristics curves were performed to determine the diagnostic performance of the features.

Results: By comparison with AIS/MIA, significantly different CT imaging features of BA included nodule type, tumor size, and pseudo-cavitation sign. Among them, pseudo-cavitation sign had a moderate diagnostic value for distinguishing BA and AIS/MIA (AUC: 0.741 and 0.708, respectively). Further, a total of 396 quantitative texture features were extracted. After comparation, the top six texture features showing the most significant difference between BA and AIS or MIA were chosen. The ROC results showed that these key texture features had a high diagnostic value for differentiating BA from AIS or MIA, among which the value of a comprehensive model with six selected texture features was the highest (AUC: 0.977 or 0.976, respectively) for BA and AIS or MIA. These results indicated that texture analyses can effectively improve the efficacy of thin-section unenhanced CT for discriminating BA from AIS/MIA.

Conclusion: CT texture analysis can effectively improve the efficacy of thin-section unenhanced CT for discriminating BA from AIS/MIA, which has a potential clinical value and helps pathologist and clinicians to make diagnostic and therapeutic strategies.

Texture Analysis in Brain Tumor MR Imaging

Texture analysis, as well as its broader category radiomics, describes a variety of techniques for image analysis that quantify the variation in surface intensity or patterns, including some that are imperceptible to the human visual system. Cerebral gliomas have been most rigorously studied in brain tumors using MR-based texture analysis (MRTA) to determine the correlation of various clinical measures with MRTA features. Promising results in cerebral gliomas have been shown in the previous MRTA studies in terms of the correlation with the World Health Organization grades, risk stratification in gliomas, and the differentiation of gliomas from other brain tumors. Multiple MRTA studies in gliomas have repeatedly shown high performance of entropy, a measure of the randomness in image intensity values, of either histogram- or gray-level co-occurrence matrix parameters. Similarly, researchers have applied MRTA to other brain tumors, including meningiomas and pediatric posterior fossa tumors.

However, the value of MRTA in the clinical use remains undetermined, probably because previous studies have shown only limited reproducibility of the result in the real world. The low-to-modest generalizability may be attributed to variations in MRTA methods, sampling bias that originates from single-institution studies, and overfitting problems to a limited number of samples.

To enhance the reliability and reproducibility of MRTA studies, researchers have realized the importance of standardizing methods in the field of radiomics. Another advancement is the recent development of a comprehensive assessment system to ensure the quality of a radiomics study. These two-way approaches will secure the validity of upcoming MRTA studies. The clinical use of texture analysis in brain MRI will be accelerated by these continuous efforts.

Evaluation of microvascular permeability of skeletal muscle and texture analysis based on DCE-MRI in alloxan-induced diabetic rabbits

OBJECTIVES

To estimate the microvascular permeability and perfusion of skeletal muscle by using quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and explore the feasibility of using texture analysis (TA) to evaluate subtle structural changes of diabetic muscles.

METHODS

Twenty-four rabbits were randomly divided into diabetic (n = 14) and control (n = 10) groups, and underwent axial DCE-MRI of the multifidus muscle (0, 4, 8, 12, and 16 weeks after alloxan injection). The pharmacokinetic model was used to calculate the permeability parameters; texture parameters were extracted from volume transfer constant (K^trans) map. The two-sample t test/Mann-Whitney U test, repeated measures analysis of variance/Friedman test, and Pearson correlations were used for data analysis.

RESULTS

In the diabetic group, K^trans and rate constant (K_ep) increased significantly at week 8 and then showed a decreasing trend. Extravascular extracellular space volume fraction (V_e) increased and plasma volume fraction (V_p) decreased significantly from the 8th week. Skewness began to decrease at the 4th week. Median K^trans and entropy increased significantly, while inverse difference moment decreased from the 8th week. Energy decreased while contrast increased only at week 8. Muscle fibre cross-sectional area was negatively correlated with V_e. The capillary-to-fibre ratio was positively correlated with V_p (p < 0.05, all).

CONCLUSIONS

Quantitative DCE-MRI can be used to evaluate microvascular permeability and perfusion in diabetic skeletal muscle at an early stage; TA based on K^trans map can identify microarchitectural modifications in diabetic muscles.

KEY POINTS

• Four quantitative parameters of DCE-MRI can be used to evaluate microvascular permeability and perfusion of skeletal muscle in diabetic models at early stages. • Texture analysis based on K^trans map can identify subtle structural changes in diabetic muscles.

Texture analysis of apparent diffusion coefficient (ADC) map for glioma grading: Analysis of whole tumoral and peri-tumoral tissue

PURPOSE

To prospectively investigate the capabilities of texture analysis (TA) based on apparent diffusion coefficient (ADC) map of the entire tumor volume and the whole volume of peri-tumoral edema, in discriminating between high-grade glioma (HGG) and low-grade glioma (LGG).

MATERIALS AND METHODS

A total of 33 patients with histopathological proven glioma were prospectively included. There were 20 men and 13 women with a mean age of 54.5±14.7 (standard deviation [SD]) years (range: 34-75years). TA parameters of whole tumor and peri-tumoral edema were extracted from the ADC map obtained with diffusion-weighted spin-echo echo-planar magnetic resonance imaging at 1.5-T. TA variables of HGG were compared to those of LGG. The optimum cut-off values of TA variables and their corresponding sensitivity, specificity and accuracy for differentiating between LGG and HGG were calculated using receiver operating characteristic curve analysis.

RESULTS

Mean and median tumoral ADC of HGG were significantly lower than those of LGG, at 1.23×10^-3 mm²/s and 1.21×10^-3 mm²/s cut-off values, yielding 70% sensitivity each (95% CI: 59-82% and 61-80%, respectively), 80% (95% CI: 79-98%) and 90% (95% CI: 82-97%) specificity, and 73% (95% CI: 66-91%) and 76% (95% CI: 72-90%) accuracy, respectively. Significant differences in tumoral and peri-tumoral kurtosis were found between HGG and LGG at 1.60 and 0.314 cut-off values yielding sensitivities of 74% (95% CI: 58-83%) and 70% (95% CI: 59-84%), specificities of 90% (95% CI: 80-95%) and 70% (95% CI: 64-83%) and accuracies of 79% (95% CI: 69-89%) and 70% (95% CI: 64-77%), respectively.

CONCLUSION

Measurements of whole tumoral and peri-tumoral TA, based on ADC maps, provide useful information that helps distinguish between HGG and LGG.

Improved Glioma Grading Using Deep Convolutional Neural Networks

BACKGROUND AND PURPOSE

Accurate determination of glioma grade leads to improved treatment planning. The criterion standard for glioma grading is invasive tissue sampling. Recently, radiomic features have shown excellent potential in glioma-grade prediction. These features may not fully exploit the underlying information in MR images. The objective of this study was to investigate the performance of features learned by a convolutional neural network compared with standard radiomic features for grade prediction.

MATERIALS AND METHODS

A total of 237 patients with gliomas were included in this study. All images were resampled, registered, skull-stripped, and segmented to extract the tumors. The learned features from the trained convolutional neural network were used for grade prediction. The performance of the proposed method was compared with standard machine learning approaches, support vector machine, random forests, and gradient boosting trained with radiomic features.

RESULTS

The experimental results demonstrate that using learned features extracted from the convolutional neural network achieves an average accuracy of 87%, outperforming the methods considering radiomic features alone. The top-performing machine learning model is gradient boosting with an average accuracy of 64%. Thus, there is a 23% improvement in accuracy, and it is an efficient technique for grade prediction.

CONCLUSIONS

Convolutional neural networks are able to learn discriminating features automatically, and these features provide added value for grading gliomas. The proposed framework may provide substantial improvement in glioma-grade prediction; however, further validation is needed.

Non-invasive monitoring of the kinetic infiltration and therapeutic efficacy of nanoparticle-labeled chimeric antigen receptor T cells in glioblastoma via 7.0-Tesla magnetic resonance imaging

BACKGROUND AIMS

Chimeric antigen receptor (CAR) T-cell therapy is a promising treatment strategy in solid tumors. In vivo cell tracking techniques can help us better understand the infiltration, persistence and therapeutic efficacy of CAR T cells. In this field, magnetic resonance imaging (MRI) can achieve high-resolution images of cells by using cellular imaging probes. MRI can also provide various biological information on solid tumors.

METHODS

The authors adopted the amino alcohol derivatives of glucose-coated nanoparticles, ultra-small superparamagnetic particles of iron oxide (USPIOs), to label CAR T cells for non-invasive monitoring of kinetic infiltration and persistence in glioblastoma (GBM). The specific targeting CARs included anti-human epidermal growth factor receptor variant III and IL13 receptor subunit alpha 2 CARs.

RESULTS

When using an appropriate concentration, USPIO labeling exerted no negative effects on the biological characteristics and killing efficiency of CAR T cells. Increasing hypointensity signals could be detected in GBM models by susceptibility-weighted imaging MRI ranging from 3 days to 14 days following the injection of USPIO-labeled CAR T cells. In addition, nanoparticles and CAR T cells were found on consecutive histopathological sections. Moreover, diffusion and perfusion MRI revealed significantly increased water diffusion and decreased vascular permeability on day 3 after treatment, which was simultaneously accompanied by a significant decrease in tumor cell proliferation and increase in intercellular tight junction on immunostaining sections.

CONCLUSION

These results establish an effective imaging technique that can track CAR T cells in GBM models and validate their early therapeutic effects, which may guide the evaluation of CAR T-cell therapies in solid tumors.

Preoperative vascular heterogeneity and aggressiveness assessment of pituitary macroadenoma based on dynamic contrast-enhanced MRI texture analysis

PURPOSE

To assess the vascular heterogeneity and aggressiveness of pituitary macroadenomas (PM) using texture analysis based on Dynamic Contrast-Enhanced MRI (DCE-MRI).

METHOD

Fifty patients with pathologically confirmed PM, including 32 patients with aggressive PM (aggressive group) and 18 patients with non-aggressive PM (non-aggressive group), were included in this study. The preoperative DCE-MRI and clinical data were collected from all patients. The features based on Ktrans, Ve, and Kep were generated using Omni-Kinetics software. Independent-samples t-test and Mann-Whitney U test were used for comparison between two groups. Logistic regression analysis was used to determine the optimal model for distinguishing aggressive and non-aggressive PM.

RESULTS

Six features related to tumor morphology, 24 features in Ktrans, 20 features in Ve, and 3 features in Kep were significantly different between the aggressive and non-aggressive groups. Volume count, gray-level non-uniformity in Ktrans, voxel value sum in Ve and run-length non-uniformity in Kep (AUC = 0.816, 0.903, 0.785, 0.813) were considered the best feature for tumor diagnosis. After modeling, the diagnosis efficiency of mean model and total model was desirable (AUC = 0.859 and 0.957), and the diagnostic efficiency of morphological, Ktrans, Ve and Kep features model was improved (AUC = 0.845, 0.951, 0.847, 0.804).

CONCLUSIONS

Texture analysis based on DCE-MRI elucidates the vascular heterogeneity and aggressiveness of pituitary adenoma. The total model could be used as a new noninvasive method for predicting the aggressiveness of pituitary macroadenoma.

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Accuracy of glioma grading is fundamental for the diagnosis, treatment planning and prognosis of patients. The purpose of this work was to develop a low-cost and easy-to-implement classification model which distinguishes low-grade gliomas (LGGs) from high-grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. Different combinations of MRI contrasts (T1Gd and T2) and one segmented glioma region (necrotic and non-enhancing tumor core, NCR/NET) were studied. Texture features obtained from the gray level size zone matrix (GLSZM) were calculated. An under-sampling method was proposed to divide the data into different training subsets and subsequently extract complementary information for the creation of distinct classification models. The sensitivity, specificity and accuracy of the models were calculated, and the best model explicitly reported. The best model included only three texture features and reached a sensitivity, specificity and accuracy of 94.12%, 88.24% and 91.18%, respectively. According to the features of the model, when the NCR/NET region was studied, HGGs had a more heterogeneous texture than LGGs in the T1Gd images, and LGGs had a more heterogeneous texture than HGGs in the T2 images. These novel results partially contrast with results from the literature. The best model proved to be useful for the classification of gliomas. Complementary results showed that the heterogeneity of gliomas depended on the MRI contrast studied. The chosen model stands out as a simple, low-cost, easy-to-implement, reproducible and highly accurate glioma classifier. Importantly, it should be accessible to populations with reduced economic and scientific resources.

Grading of Glioma: combined diagnostic value of amide proton transfer weighted, arterial spin labeling and diffusion weighted magnetic resonance imaging

BACKGROUND

To investigate the ability of amide proton transfer (APT) weighted magnetic resonance imaging (MRI), arterial spin labeling (ASL), diffusion weighted imaging (DWI) and the combination for differentiating high-grade gliomas (HGGs) from low-grade gliomas (LGGs).

METHODS

Twenty-seven patients including nine LGGs and eighteen HGGs underwent conventional, APT, ASL and DWI MRI with a 3.0-T MR scanner. Histogram analyses was performed and quantitative parameters including mean apparent diffusion coefficient (ADC mean), 20th-percentile ADC (ADC 20th), mean APT (APT mean), 90th-percentile APT (APT 90th), relative mean cerebral blood flow (rCBF mean) and relative 90th-percentile CBF (rCBF 90th) were compared between HGGs and LGGs. The diagnostic performance was evaluated with receiver operating characteristic (ROC) analysis of each parameter and their combination. Correlations were analyzed among the MRI parameters and Ki-67.

RESULTS

The APT values were significantly higher in the HGGs compared to the LGGs (p <  0.005), whereas ADC values were significantly lower in HGGs than LGGs (P <  0.0001). The ADC 20th and APT mean had higher discrimination abilities compared with other single parameters, with the area under the ROC curve (AUC) of 0.877 and 0.840. Adding ADC parameter, the discrimination ability of APT and rCBF significantly improved. The ADC was negatively correlated with the APT and rCBF value, respectively, while APT value was positively correlated with rCBF value. Significant correlations between ADC values and Ki-67 were also observed.

CONCLUSIONS

APT and DWI are valuable in differentiating HGGs from LGGs. The combination of APT, DWI and ASL imaging could improve the ability for discriminating HGGs from LGGs.

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Diffuse low-grade gliomas (LGG) have been reclassified based on molecular mutations, which require invasive tumor tissue sampling. Tissue sampling by biopsy may be limited by sampling error, whereas non-invasive imaging can evaluate the entirety of a tumor. This study presents a non-invasive analysis of low-grade gliomas using imaging features based on the updated classification. We introduce molecular (MGMT methylation, IDH mutation, 1p/19q co-deletion, ATRX mutation, and TERT mutations) prediction methods of low-grade gliomas with imaging. Imaging features are extracted from magnetic resonance imaging data and include texture features, fractal and multi-resolution fractal texture features, and volumetric features. Training models include nested leave-one-out cross-validation to select features, train the model, and estimate model performance. The prediction models of MGMT methylation, IDH mutations, 1p/19q co-deletion, ATRX mutation, and TERT mutations achieve a test performance AUC of 0.83 ± 0.04, 0.84 ± 0.03, 0.80 ± 0.04, 0.70 ± 0.09, and 0.82 ± 0.04, respectively. Furthermore, our analysis shows that the fractal features have a significant effect on the predictive performance of MGMT methylation IDH mutations, 1p/19q co-deletion, and ATRX mutations. The performance of our prediction methods indicates the potential of correlating computed imaging features with LGG molecular mutations types and identifies candidates that may be considered potential predictive biomarkers of LGG molecular classification.

Ability of Radiomics in Differentiation of Anaplastic Oligodendroglioma From Atypical Low-Grade Oligodendroglioma Using Machine-Learning Approach

Objectives: To investigate the ability of radiomics features from MRI in differentiating anaplastic oligodendroglioma (AO) from atypical low-grade oligodendroglioma using machine-learning algorithms.

Methods: A total number of 101 qualified patients (50 participants with AO and 51 with atypical low-grade oligodendroglioma) were enrolled in this retrospective, single-center study. Forty radiomics features of tumor images derived from six matrices were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images. Three selection methods were performed to select the optimal features for classifiers, including distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT). Then three machine-learning classifiers were adopted to generate discriminative models, including linear discriminant analysis, support vector machine, and random forest (RF). Receiver operating characteristic analysis was conducted to evaluate the discriminative performance of each model.

Results: Nine predictive models were established based on radiomics features from T1C images and FLAIR images. All of the classifiers represented feasible ability in differentiation, with AUC more than 0.840 when combined with suitable selection method. For models based on T1C images, the combination of LASSO and RF classifier represented the highest AUC of 0.904 in the validation group. For models based on FLAIR images, the combination of GBDT and RF classifier showed the highest AUC of 0.861 in the validation group.

Conclusion: Radiomics-based machine-learning approach could potentially serve as a feasible method in distinguishing AO from atypical low-grade oligodendroglioma.

Differentiation Between Benign and Nonbenign Meningiomas by Using Texture Analysis From Multiparametric MRI

BACKGROUND

It is difficult to prospectively differentiate between benign (World Health Organization [WHO] I) and nonbenign (WHO II and III) meningiomas.

PURPOSE

To evaluate the feasibility of preoperative differentiation between benign and nonbenign meningiomas by using texture analysis from multiparametric MR data.

STUDY TYPE

Retrospective.

SUBJECTS

In all, 184 patients with meningioma (139 benign and 45 nonbenign) were included as the training cohort and 79 patients with meningioma (60 benign and 19 nonbenign) were included as the external validation cohort.

FIELD STRENGTH/SEQUENCE

T₁ -weighted, T₂ -weighted, and contrast-enhanced T₁ -weighted imaging were performed on 1.5 or 3.0T MR systems from two centers.

ASSESSMENT

Tumor segmentation and radiological characteristic (RC) evaluation were performed by experienced radiologists. The texture features were extracted from preprocessed images and combined with RCs, and then the combined features were reduced by using a two-step feature selection. Three single-sequence models and a multiparametric MRI (the combination of single sequences) model were constructed and then evaluated with the external validation cohort.

STATISTICAL TESTS

Area under receiver operating characteristic curve (AUC), accuracy (Acc), f1-score (F1), sensitivity (Sen), and specificity (Spec), were calculated to quantify the performance of the models.

RESULTS

Among the four texture models, the multiparametric MRI model demonstrated the best performance for differentiating between benign and nonbenign meningiomas in both the training and external validation cohorts (AUC 0.91, Acc 89%, F1 0.88, Sen 0.93, and Spec 0.87 in the training cohort; AUC 0.83, Acc 80%, F1 0.77, Sen 0.84, and Spec 0.78 in the validation cohort).

DATA CONCLUSION

Nonbenign meningiomas might be preoperatively differentiated from benign meningiomas by using texture analysis from multiparametric MR data.

LEVEL OF EVIDENCE

3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;51:1810-1820.

Texture Analysis Based on Preoperative Magnetic Resonance Imaging (MRI) and Conventional MRI Features for Predicting the Early Recurrence of Single Hepatocellular Carcinoma after Hepatectomy

RATIONALE AND OBJECTIVES

To investigate the value of texture analysis and conventional magnetic resonance imaging (MRI) features for predicting the early recurrence (ER) of single hepatocellular carcinoma (HCC) after hepatectomy.

MATERIALS AND METHODS

A total of 100 HCC patients were first divided into group A (tumor diameter ≤3 cm) and group B (tumor diameter >3 cm) and then classified into two subgroups with ER or nonearly recurrence. Textural parameters (skewness, kurtosis, uniformity, energy, entropy, and correlation) based on MR images and conventional MRI features were compared between the ER and nonearly recurrence subgroups. Predictive factors for ER were further assessed with multivariate logistic regression analysis. Receiver operating characteristic curve was performed to assess the predictive power.

RESULTS

There were 53 patients in group A and 47 patients in group B. On arterial phase analysis, tumors with ER displayed significantly lower uniformity and higher entropy in group A, and higher skewness and entropy in group B. On portal venous phase analysis, tumors with ER had significantly lower kurtosis and energy in group A, and higher entropy in group B. Irregular margin in groups A and B, and arterial peritumoral enhancement and capsule presence in group B were associated with ER. In multivariate logistic regression analysis, uniformity and entropy based on arterial phase images and irregular margin in group A, and skewness and entropy based on arterial phase images and arterial peritumoral enhancement in group B were independent predictors for ER. Entropy displayed higher predictive power for ER.

CONCLUSION

Texture analysis based on preoperative MRI are potential quantitative predictors of ER in HCC patients after hepatectomy, and may provide more information for preoperative treatment decision-making and follow up.

Texture Analysis in Cerebral Gliomas: A Review of the Literature

Texture analysis is a continuously evolving, noninvasive radiomics technique to quantify macroscopic tissue heterogeneity indirectly linked to microscopic tissue heterogeneity beyond human visual perception. In recent years, systemic oncologic applications of texture analysis have been increasingly explored. Here we discuss the basic concepts and methodologies of texture analysis, along with a review of various MR imaging texture analysis applications in glioma imaging. We also discuss MR imaging texture analysis limitations and the technical challenges that impede its widespread clinical implementation. With continued advancement in computational processing, MR imaging texture analysis could potentially develop into a valuable clinical tool in routine oncologic imaging.

Intergrating conventional MRI, texture analysis of dynamic contrast-enhanced MRI, and susceptibility weighted imaging for glioma grading

BACKGROUND

The application of conventional magnetic resonance imaging (MRI) in glioma grading is limited and non-specific.

PURPOSE

To investigate the application values of MRI, texture analysis (TA) of dynamic contrast-enhanced MRI (DCE-MRI) and intratumoral susceptibility signal (ITSS) on susceptibility weighted imaging (SWI), alone and in combination, for glioma grading.

MATERIAL AND METHODS

Fifty-two patients with pathologically confirmed gliomas who underwent DCE-MRI and SWI were enrolled in this retrospective study. Conventional MRIs were evaluated by the VASARI scoring system. TA of DCE-MRI-derived parameters and the degree of ITSS were compared between low-grade gliomas (LGGs) and high-grade gliomas (HGGs). The diagnostic ability of each parameter and their combination for glioma grading were analyzed.

RESULTS

Significant statistical differences in VASARI features were observed between LGGs and HGGs ( P < 0.05), of which the enhancement quality had the highest area under the curve (AUC) (0.873) with 93.3% sensitivity and 80% specificity. The TA of DCE-MRI derived parameters were significantly different between LGGs and HGGs ( P < 0.05), of which the uniformity of K^trans had the highest AUC (0.917) with 93.3% sensitivity and 90% specificity. The degree of ITSS was significantly different between LGGs and HGGs ( P < 0.001). The AUC of the ITSS was 0.925 with 93.3% sensitivity and 90% specificity. The best discriminative power was obtained from a combination of enhancement quality, K^trans- uniformity, and ITSS, resulting in 96.7% sensitivity, 100.0% specificity, and AUC of 0.993.

CONCLUSION

Combining conventional MRI, TA of DCE-MRI, and ITSS on SWI may help to improve the differentiation between LGGs and HGGs.

Dynamic Contrast-Enhanced T1-Weighted Perfusion Magnetic Resonance Imaging Identifies Glioblastoma Immunohistochemical Biomarkers via Tumoral and Peritumoral Approach: A Pilot Study

OBJECTIVE

We aimed to evaluate the usefulness of dynamic contrast-enhanced T1-weighted perfusion magnetic resonance imaging (DCE-pMRI) to predict certain immunohistochemical (IHC) biomarkers of glioblastoma (GB) in this pilot study.

METHODS

We retrospectively reviewed 36 patients (male/female, 25:11; mean age, 53 years; age range, 29-85 years) who had pretreatment DCE-pMRI with IHC analysis of their excised GBs. Regions of interest of the enhancing tumor (ER) and nonenhancing peritumoral region (NER) were used to calculate DCE-pMRI parameters of volume transfer constant, back flux constant, volume of the extravascular extracellular space, initial area under enhancement curve, and maximum slope. IHC biomarkers including Ki-67 labeling index, epidermal growth factor receptor (EGFR), oligodendrocyte transcription factor 2 (OLIG2), isocitrate dehydrogenase 1 (IDH1), and p53 mutation status were determined. The imaging metrics of GB with IHC markers were compared using the Kruskal-Wallis test and Spearman correlation analysis.

RESULTS

Among 30 patients with available IDH1 status, 14 patients (46.6%) had IDH1 mutation. EGFR amplification was present in 24/36 (66.6%) patients. Mean Ki-67 labeling index was 29% (range, 1.5%-80%). p53 mutation was present in 20/36 GBs (55%), whereas OLIG2 expression was positive in 29/36 GBs (80.5%). Various DCE-pMRI parameters gathered from the ER and NER were significantly correlated with IDH1 mutation, EGFR amplification, and OLIG2 expression (P < 0.05). Ki-67 labeling index showed a strong positive correlation with initial area under enhancement curve (r = 0.619; P < 0.001).

CONCLUSIONS

DCE-pMRI could determine surrogate IHC biomarkers in GB via tumoral and peritumoral approach, potential targets for individualized treatment protocols.

Texture analysis on conventional MRI images accurately predicts early malignant transformation of low-grade gliomas

OBJECTIVES

Texture analysis performed on MRI images can provide additional quantitative information that is invisible to human assessment. This study aimed to evaluate the feasibility of texture analysis on preoperative conventional MRI images in predicting early malignant transformation from low- to high-grade glioma and compare its utility to histogram analysis alone.

METHODS

A total of 68 patients with low-grade glioma (LGG) were included in this study, 15 of which showed malignant transformation. Patients were randomly divided into training (60%) and testing (40%) sets. Texture analyses were performed to obtain the most discriminant factor (MDF) values for both training and testing data. Receiver operating characteristic (ROC) curve analyses were performed on MDF values and 9 histogram parameters in the training data to obtain cutoff values for determining the correct rates of discrimination between two groups in the testing data.

RESULTS

The ROC analyses on MDF values resulted in an area under the curve (AUC) of 0.90 (sensitivity 85%, specificity 84%) for T2w FLAIR, 0.92 (86%, 94%) for ADC, 0.96 (97%, 84%) for T1w, and 0.82 (78%, 75%) for T1w + Gd and correctly discriminated between the two groups in 93%, 100%, 93%, and 92% of cases in testing data, respectively. In the astrocytoma subgroup, AUCs were 0.92 (88%, 83%) for T2w FLAIR and 0.90 (92%, 74%) for T1w + Gd and correctly discriminated two groups in 100% and 92% of cases. The MDF outperformed all 9 of the histogram parameters.

CONCLUSION

Texture analysis on conventional preoperative MRI images can accurately predict early malignant transformation of LGGs, which may guide therapeutic planning.

KEY POINTS

• Texture analysis performed on MRI images can provide additional quantitative information that is invisible to human assessment. • Texture analysis based on conventional preoperative MR images can accurately predict early malignant transformation from low- to high-grade glioma. • Texture analysis is a clinically feasible technique that may provide an alternative and effective way of determining the likelihood of early malignant transformation and help guide therapeutic decisions.

MRI based texture analysis to classify low grade gliomas into astrocytoma and 1p/19q codeleted oligodendroglioma

PURPOSE

Texture analysis performed on MR images can detect quantitative features that are imperceptible to human visual assessment. The purpose of this study was to evaluate the feasibility of texture analysis on preoperative conventional MRI to discriminate between histological subtypes in low-grade gliomas (LGGs), and to determine the utility of texture analysis compared to histogram analysis alone.

METHODS

A total of 41 patients with LGG, 21 astrocytoma and 20 1p/19q codeleted oligodendroglioma were included in this study. Patients were randomly divided into training (60%) and testing (40%) sets. Texture analysis was performed on conventional MRI sequences to obtain the most discriminant factor (MDF) values for both the training and testing data. Receiver operating characteristic (ROC) curve analyses were then performed using the MDF values and 9 histogram parameters in the training data to obtain cut-off values for determining the correct rate of discriminating between astrocytoma and oligodendroglioma in the testing data.

RESULTS

The ROC analyses using MDF values resulted in an area under the curve (AUC) of 0.91 (sensitivity 86%, specificity 87%) for T2w FLAIR, 0.94 (87%, 89%) for ADC, 0.98 (93%, 95%) for T1w, and 0.88 (78%, 86%) for T1w + Gd sequences. Using the best cut-off values, MDF correctly discriminated between the two groups in 94%, 82%, 100%, and 88% of cases in the testing data, respectively. The MDF outperformed all 9 of the histogram parameters.

CONCLUSION

Texture analysis performed on conventional preoperative MRI images can accurately predict histological subtype of LGGs, which would have an impact on clinical management.

Intra-tumoural heterogeneity characterization through texture and colour analysis for differentiation of non-small cell lung carcinoma subtypes

Radiomics has shown potential in disease diagnosis, but its feasibility for non-small cell lung carcinoma (NSCLC) subtype classification is unclear. This study aims to explore the diagnosis value of texture and colour features from positron emission tomography computed tomography (PET-CT) images in differentiation of NSCLC subtypes: adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). Two patient cohorts were retrospectively collected into a dataset of 341 ¹⁸F-labeled 2-deoxy-2fluoro-d-glucose ([¹⁸F] FDG) PET-CT images of NSCLC tumours (125 ADC, 174 SqCC, and 42 cases with unknown subtype). Quantification of texture and colour features was performed using freehand regions of interest. The relation between extracted features and commonly used parameters such as age, gender, tumour size, and standard uptake value (SUVmax) was explored. To classify NSCLC subtypes, support vector machine algorithm was applied on these features and the classification performance was evaluated by receiver operating characteristic curve analysis. There was a significant difference between ADC and SqCC subtypes in texture and colour features (P  <  0.05); this showed that imaging features were significantly correlated to both SUVmax and tumour diameter (P  <  0.05). When evaluating classification performance, features combining texture and colour showed an AUC of 0.89 (95% CI, 0.78-1.00), colour features showed an AUC of 0.85 (95% CI, 0.71-0.99), and texture features showed an AUC of 0.68 (95% CI, 0.48-0.88). DeLong's test showed that AUC was higher for features combining texture and colour than that for texture features only (P  =  0.010), but not significantly different from that for colour features only (P  =  0.328). HSV colour features showed a similar performance to RGB colour features (P  =  0.473). The colour features are promising in the refinement of NSCLC subtype differentiation, and features combining texture and colour of PET-CT images could result in better classification performance.