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

Identifying IDH-mutant and 1p/19q noncodeleted astrocytomas from nonenhancing gliomas: Manual recognition followed by artificial intelligence recognition

Background

The T2-FLAIR mismatch sign (T2FM) has nearly 100% specificity for predicting IDH-mutant and 1p/19q noncodeleted astrocytomas (astrocytomas). However, only 18.2%-56.0% of astrocytomas demonstrate a positive T2FM. Methods must be considered for distinguishing astrocytomas from negative T2FM gliomas. In this study, positive T2FM gliomas were manually distinguished from nonenhancing gliomas, and then a support vector machine (SVM) classification model was used to distinguish astrocytomas from negative T2FM gliomas.

Methods

Nonenhancing gliomas (regardless of pathological type or grade) diagnosed between January 2022 and October 2022 (N = 300) and November 2022 and March 2023 (N = 196) will comprise the training and validation sets, respectively. Our method for distinguishing astrocytomas from nonenhancing gliomas was examined and validated using the training set and validation set.

Results

The specificity of T2FM for predicting astrocytomas was 100% in both the training and validation sets, while the sensitivity was 42.75% and 67.22%, respectively. Using a classification model of SVM based on radiomics features, among negative T2FM gliomas, the accuracy was above 85% when the prediction score was greater than 0.70 in identifying astrocytomas and above 95% when the prediction score was less than 0.30 in identifying nonastrocytomas.

Conclusions

Manual screening of positive T2FM gliomas, followed by the SVM classification model to differentiate astrocytomas from negative T2FM gliomas, may be a more effective method for identifying astrocytomas in nonenhancing gliomas.

SWI by 7T MR Imaging for the Microscopic Imaging Diagnosis of Astrocytic and Oligodendroglial Tumors

BACKGROUND AND PURPOSE

Despite advances in molecular imaging, preoperative diagnosis of astrocytomas and oligodendrogliomas can be challenging. In the present study, we assessed whether 7T SWI can be used to distinguish astrocytomas and oligodendrogliomas and whether malignant grading of gliomas is possible.

MATERIALS AND METHODS

7T SWI was performed on 21 patients with gliomas before surgery with optimization for sharp visualization of the corticomedullary junction. Scoring for cortical thickening and displacement of medullary vessels, characteristic of oligodendroglial tumors, and cortical tapering, characteristic of astrocytic tumors, was performed. Additionally, characteristics of malignancy, including thickening of the medullary veins, the presence of microbleeds, and/or necrosis were scored.

RESULTS

Scoring for oligodendroglial (highest possible score, +3) and astrocytic (lowest score possible, -3) characteristics yielded a significant difference between astrocytomas and oligodendrogliomas (mean, -1.93 versus +1.71, P < .01). Scoring for malignancy was significantly different among the World Health Organization grade II (n = 10), grade III (n = 4), and grade IV (n = 7) tumors (mean, 0.20 versus 1.38 versus 2.79). Cortical thickening was observed significantly more frequently in oligodendrogliomas (P < .02), with a sensitivity of 71.4% and specificity of 85.7%; observation of tapering of the cortex was higher in astrocytomas (P < .01) with a sensitivity of 85.7% and specificity of 100%.

CONCLUSIONS

Visualization of the corticomedullary junction by 7T SWI was useful in distinguishing astrocytomas and oligodendrogliomas. Observation of tapering of the cortex was most sensitive and specific for diagnosing astrocytomas. Reliably predicting malignant grade was also possible by 7T SWI.

A Combination Analysis of IVIM-DWI Biomarkers and T2WI-Based Texture Features for Tumor Differentiation Grade of Cervical Squamous Cell Carcinoma

Purpose

To explore the value of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) and texture analysis on T2-weighted imaging (T2WI) for evaluating pathological differentiation of cervical squamous cell carcinoma.

Method

This retrospective study included a total of 138 patients with pathologically confirmed poor/moderate/well-differentiated (71/49/18) who underwent conventional MRI and IVIM-DWI scans. The values of ADC, D, D^∗, and f and 58 T2WI-based texture features (18 histogram features, 24 gray-level co-occurrence matrix features, and 16 gray-level run length matrix features) were obtained. Multiple comparison, correlation, and regression analyses were used.

Results

For IVIM-DWI, the ADC, D, D^∗, and f were significantly different among the three groups (p < 0.05). ADC, D, and D^∗ were positively correlated with pathological differentiation (r = 0.262, 0.401, 0.401; p < 0.05), while the correlation was negative for f (r = −0.221; p < 0.05). The comparison of 52 parameters of texture analysis on T2WI reached statistically significant levels (p < 0.05). Multivariate logistic regression analysis incorporated significant IVIM-DWI, and texture features on T2WI showed good diagnostic performance both in the four differentiation groups (poorly vs. moderately, area under the curve(AUC) = 0.797; moderately vs. well, AUC = 0.954; poorly vs. moderately and well, AUC = 0.795; and well vs. moderately and poorly, AUC = 0.952). The AUCs of each parameters alone were smaller than that of each regression model (0.503∼0.684, 0.547∼0.805, 0.511∼0.712, and 0.636∼0.792, respectively; pairwise comparison of ROC curves between regression model and individual variables, p < 0.05).

Conclusions

IVIM-DWI biomarkers and T2WI-based texture features had potential to evaluate the pathological differentiation of cervical squamous cell carcinoma. The combination of IVIM-DWI with texture analysis improved the predictive performance.

Deep cross-view co-regularized representation learning for glioma subtype identification

The new subtypes of diffuse gliomas are recognized by the World Health Organization (WHO) on the basis of genotypes, e.g., isocitrate dehydrogenase and chromosome arms 1p/19q, in addition to the histologic phenotype. Glioma subtype identification can provide valid guidances for both risk-benefit assessment and clinical decision. The feature representations of gliomas in magnetic resonance imaging (MRI) have been prevalent for revealing underlying subtype status. However, since gliomas are highly heterogeneous tumors with quite variable imaging phenotypes, learning discriminative feature representations in MRI for gliomas remains challenging. In this paper, we propose a deep cross-view co-regularized representation learning framework for glioma subtype identification, in which view representation learning and multiple constraints are integrated into a unified paradigm. Specifically, we first learn latent view-specific representations based on cross-view images generated from MRI via a bi-directional mapping connecting original imaging space and latent space, and view-correlated regularizer and output-consistent regularizer in the latent space are employed to explore view correlation and derive view consistency, respectively. We further learn view-sharable representations which can explore complementary information of multiple views by projecting the view-specific representations into a holistically shared space and enhancing via adversary learning strategy. Finally, the view-specific and view-sharable representations are incorporated for identifying glioma subtype. Experimental results on multi-site datasets demonstrate the proposed method outperforms several state-of-the-art methods in detection of glioma subtype status.

Development and external validation of a non-invasive molecular status predictor of chromosome 1p/19q co-deletion based on MRI radiomics analysis of Low Grade Glioma patients

PURPOSE

The 1p/19q co-deletion status has been demonstrated to be a prognostic biomarker in lower grade glioma (LGG). The objective of this study was to build a magnetic resonance (MRI)-derived radiomics model to predict the 1p/19q co-deletion status.

METHOD

209 pathology-confirmed LGG patients from 2 different datasets from The Cancer Imaging Archive were retrospectively reviewed; one dataset with 159 patients as the training and discovery dataset and the other one with 50 patients as validation dataset. Radiomics features were extracted from T2- and T1-weighted post-contrast MRI resampled data using linear and cubic interpolation methods. For each of the voxel resampling methods a three-step approach was used for feature selection and a random forest (RF) classifier was trained on the training dataset. Model performance was evaluated on training and validation datasets and clinical utility indexes (CUIs) were computed. The distributions and intercorrelation for selected features were analyzed.

RESULTS

Seven radiomics features were selected from the cubic interpolated features and five from the linear interpolated features on the training dataset. The RF classifier showed similar performance for cubic and linear interpolation methods in the training dataset with accuracies of 0.81 (0.75-0.86) and 0.76 (0.71-0.82) respectively; in the validation dataset the accuracy dropped to 0.72 (0.6-0.82) using cubic interpolation and 0.72 (0.6-0.84) using linear resampling. CUIs showed the model achieved satisfactory negative values (0.605 using cubic interpolation and 0.569 for linear interpolation).

CONCLUSIONS

MRI has the potential for predicting the 1p/19q status in LGGs. Both cubic and linear interpolation methods showed similar performance in external validation.

Multi-institutional noninvasive in vivo characterization of IDH, 1p/19q, and EGFRvIII in glioma using neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk)

Background

Gliomas represent a biologically heterogeneous group of primary brain tumors with uncontrolled cellular proliferation and diffuse infiltration that renders them almost incurable, thereby leading to a grim prognosis. Recent comprehensive genomic profiling has greatly elucidated the molecular hallmarks of gliomas, including the mutations in isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2), loss of chromosomes 1p and 19q (1p/19q), and epidermal growth factor receptor variant III (EGFRvIII). Detection of these molecular alterations is based on ex vivo analysis of surgically resected tissue specimen that sometimes is not adequate for testing and/or does not capture the spatial tumor heterogeneity of the neoplasm.

Methods

We developed a method for noninvasive detection of radiogenomic markers of IDH both in lower-grade gliomas (WHO grade II and III tumors) and glioblastoma (WHO grade IV), 1p/19q in IDH-mutant lower-grade gliomas, and EGFRvIII in glioblastoma. Preoperative MRIs of 473 glioma patients from 3 of the studies participating in the ReSPOND consortium (collection I: Hospital of the University of Pennsylvania [HUP: n = 248], collection II: The Cancer Imaging Archive [TCIA; n = 192], and collection III: Ohio Brain Tumor Study [OBTS, n = 33]) were collected. Neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk), a modular platform available for cancer imaging analytics and machine learning, was leveraged to extract histogram, shape, anatomical, and texture features from delineated tumor subregions and to integrate these features using support vector machine to generate models predictive of IDH, 1p/19q, and EGFRvIII. The models were validated using 3 configurations: (1) 70-30% training-testing splits or 10-fold cross-validation within individual collections, (2) 70-30% training-testing splits within merged collections, and (3) training on one collection and testing on another.

Results

These models achieved a classification accuracy of 86.74% (HUP), 85.45% (TCIA), and 75.15% (TCIA) in identifying EGFRvIII, IDH, and 1p/19q, respectively, in configuration I. The model, when applied on combined data in configuration II, yielded a classification success rate of 82.50% in predicting IDH mutation (HUP + TCIA + OBTS). The model when trained on TCIA dataset yielded classification accuracy of 84.88% in predicting IDH in HUP dataset.

Conclusions

Using machine learning algorithms, high accuracy was achieved in the prediction of IDH, 1p/19q, and EGFRvIII mutation. Neuro-CaPTk encompasses all the pipelines required to replicate these analyses in multi-institutional settings and could also be used for other radio(geno)mic analyses.

MRI texture analysis in acromegaly and its role in predicting response to somatostatin receptor ligands

PURPOSE

Given the paucity of reliable predictors of tumor recurrence, progression, or response to somatostatin receptor ligand (SRL) therapy in acromegaly, we attempted to determine whether preoperative MR image texture was predictive of these clinical outcomes. We also determined whether image texture could differentiate somatotroph adenomas from non-functioning pituitary adenomas (NFPAs).

METHODS

We performed a retrospective study of patients with acromegaly due to a macroadenoma who underwent transsphenoidal surgery at our institution between 2007 and 2015. Clinical data were extracted from electronic medical records. MRI texture analysis was performed on preoperative non-enhanced T1-weighted images using ImageJ (NIH). Logistic and Cox models were used to determine if image texture parameters predicted outcomes.

RESULTS

Eighty-nine patients had texture parameters measured, which were compared to that of NFPAs, while 64 of these patients had follow-up and were included in the remainder of analyses. Minimum pixel intensity, skewness, and kurtosis were significantly different in somatotroph adenomas versus NFPAs (area under the receiver operating characteristic curve, 0.7771, for kurtosis). Furthermore, those with a maximum pixel intensity above the median had an increased odds of IGF-I normalization on SRL therapy (OR 5.96, 95% CI 1.33-26.66), which persisted after adjusting for several potential predictors of response. Image texture did not predict tumor recurrence or progression.

CONCLUSION

Our data suggest that MRI texture analysis can distinguish NFPAs from somatotroph macroadenomas with good diagnostic accuracy and can predict normalization of IGF-I with SRL therapy.