Glioma grading prediction using multiparametric magnetic resonance imaging‐based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging

Abstract

Purpose To evaluate the efficacy of three‐dimensional (3D) segmentation‐based radiomics analysis of multiparametric MRI combined with proton magnetic resonance spectroscopy (1H‐MRS) and diffusion tensor imaging (DTI) in glioma grading. Method A total of 100 patients with histologically confirmed gliomas (grade II–IV) were examined using conventional MRI, 1H‐MRS, and DTI. Tumor segmentations of T1‐weighted imaging (T1WI), contrast‐enhanced T1WI (T1WI+C), T2‐weighted imaging (T2WI), apparent diffusion coefficient (ADC) mapping, and fractional anisotropy (FA) mapping were performed. In total, 396 radiomics features were extracted and reduced using basic tests and least absolute shrinkage and selection operator (LASSO) regression. The selected features of each sequence were combined, and logistic regression with ten‐fold cross‐validation was applied to develop the grading model. Sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were compared. The model developed from the training set was applied to the test set to measure accuracy. One optimal grading quantitative parameter was selected for each 1H‐MRS and DTI analysis. A radiomics nomogram model including radiomics signature, quantitative parameters, and clinical features was developed. Results T1WI+C exhibited the highest grading efficacy among single sequences (AUC, 0.92; sensitivity, 0.89; specificity, 0.85), but the efficacy of the combined model was higher (AUC, 0.97; sensitivity, 0.94; specificity, 0.91). The AUCs of all models exhibited high accuracy, and no significant differences were observed in AUCs between the training and test sets. The visualized nomogram was developed based on the combined radiomics signature and choline (Cho)/N‐acetyl aspartate (NAA) from 1H‐MRS. Conclusion Multiparametric MRI can be used to predict the pathological grading of high‐grade gliomas (HGGs) and low‐grade gliomas (LGGs) by combining radiomics features with quantitative parameters. The visualized nomogram may provide an intuitive assessment tool in clinical practice. Clinical trial registration This trial was not registered, as it was a retrospective study and was approved by the local institutional review board.

Artificial intelligence in multiparametric magnetic resonance imaging: A review

“…In early studies, limited features were calculated from mpMRI data, and classifiers were learned to determine the grades (e.g., LGG (grades I and II) or high‐grade glioma (HGG, grades III and IV), Figure 4). 138,139,143 Hand‐crafted radiomics‐based methods have then been developed, with which abundant image features from tumor regions are extracted and more accurate glioma grading performance is achieved 144,149,161,168 . The introduction of DL to glioma grading could be considered a milestone in the field.…”

“…138,139,143 Handcrafted radiomics-based methods have then been developed, with which abundant image features from tumor regions are extracted and more accurate glioma grading performance is achieved. 144,149,161,168 The introduction of DL to glioma grading could be considered a milestone in the field. DL was first utilized to replace the classifier in hand-crafted radiomics-based methods.…”

An automated approach for predicting glioma grade and survival of LGG patients using CNN and radiomics

“…CNN and radiomics analysis are representative quantitative methods for image analysis, which can extract high-dimensional and abstract numeric information beyond what is perceivable via the visual assessment of a given image (15). Multiple studies have focused on the grading and survival analysis of glioma on preoperative multimodal images using radiomics or deep learning methods (29,(52)(53)(54)(55)(56)(57). Although related studies using CNN or radiomics methods have shown admirable performance, both two methods have encountered many difficulties when it comes to clinical practice.…”

CSF-Glioma: A Causal Segmentation Framework for Accurate Grading and Subregion Identification of Gliomas

“…The gray-level co-occurrence matrix (GLCM) is considered an effective feature for capturing the spatial relationship of pixels [ 13 ]. Discriminant models used in traditional approaches include the SVM [ 14 ], decision tree [ 15 ], LASSO [ 16 ], and various other methods. These traditional processes rely on hand-designed features, which can ensure model stability.…”