IDH glioma radiogenomics in the era of deep learning

Diffusion-weighted MRI precisely predicts telomerase reverse transcriptase promoter mutation status in World Health Organization grade IV gliomas using a residual convolutional neural network

OBJECTIVES

Telomerase reverse transcriptase promoter (pTERT) mutation status plays a key role in making decisions and predicting prognoses for patients with World Health Organization (WHO) grade IV glioma. This study was conducted to assess the value of diffusion-weighted imaging (DWI) for predicting pTERT mutation status in WHO grade IV glioma.

METHODS

MRI data and molecular information were obtained for 266 patients with WHO grade IV glioma at the hospital and divided into training and validation sets. The ratio of training to validation set was approximately 10:3. We trained the same residual convolutional neural network (ResNet) for each MR modality, including structural MRIs (T1-weighted, T2-weighted, and contrast-enhanced T1-weighted) and DWI*, to compare the predictive capacities between DWI and conventional structural MRI. We also explored the effects of different regions of interest on pTERT mutation status prediction outcomes.

RESULTS

Structural MRI modalities poorly predicted the pTERT mutation status (accuracy = 51%-54%; area under the curve [AUC]=0.545-0.571), whereas DWI combined with its apparent diffusive coefficient maps yielded the best predictive performance (accuracy = 85.2%, AUC = 0.934). Including the radiological and clinical characteristics did not further improve the performance for predicting pTERT mutation status. The entire tumour volume yielded the best prediction performance.

CONCLUSIONS

DWI technology shows promising potential for predicting pTERT mutations in WHO grade IV glioma and should be included in the MRI protocol for WHO grade IV glioma in clinical practice.

ADVANCES IN KNOWLEDGE

This is the first large-scale model study to validate the predictive value of DWI for pTERT in WHO grade IV glioma.

Clinical management and survival outcomes of patients with different molecular subtypes of diffuse gliomas in China (2011-2017): a multicenter retrospective study from CGGA

OBJECTIVE

We aimed to summarize the clinicopathological characteristics and prognostic features of various molecular subtypes of diffuse gliomas (DGs) in the Chinese population.

METHODS

In total, 1,418 patients diagnosed with DG between 2011 and 2017 were classified into 5 molecular subtypes according to the 2016 WHO classification of central nervous system tumors. The IDH mutation status was determined by immunohistochemistry and/or DNA sequencing, and 1p/19q codeletion was detected with fluorescence in situ hybridization. The median clinical follow-up time was 1,076 days. T-tests and chi-square tests were used to compare clinicopathological characteristics. Kaplan-Meier and Cox regression methods were used to evaluate prognostic factors.

RESULTS

Our cohort included 15.5% lower-grade gliomas, IDH-mutant and 1p/19q-codeleted (LGG-IDHm-1p/19q); 18.1% lower-grade gliomas, IDH-mutant (LGG-IDHm); 13.1% lower-grade gliomas, IDH-wildtype (LGG-IDHwt); 36.1% glioblastoma, IDH-wildtype (GBM-IDHwt); and 17.2% glioblastoma, IDH-mutant (GBM-IDHm). Approximately 63.3% of the enrolled primary gliomas, and the median overall survival times for LGG-IDHm, LGG-IDHwt, GBM-IDHwt, and GBM-IDHm subtypes were 75.97, 34.47, 11.57, and 15.17 months, respectively. The 5-year survival rate of LGG-IDHm-1p/19q was 76.54%. We observed a significant association between high resection rate and favorable survival outcomes across all subtypes of primary tumors. We also observed a significant role of chemotherapy in prolonging overall survival for GBM-IDHwt and GBM-IDHm, and in prolonging post-relapse survival for the 2 recurrent GBM subtypes.

CONCLUSIONS

By controlling for molecular subtypes, we found that resection rate and chemotherapy were 2 prognostic factors associated with survival outcomes in a Chinese cohort with DG.

Swin Transformer Improves the IDH Mutation Status Prediction of Gliomas Free of MRI-Based Tumor Segmentation

Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH mutation status free of refined tumor segmentation. Methods: A total of 493 glioma patients were recruited from two independent institutions for model development (TCIA; N = 259) and external test (AHXZ; N = 234). IDH mutation status was predicted directly from T2 images with a Swin Transformer and conventional ResNet. Furthermore, to investigate the necessity of refined tumor segmentation, seven strategies for the model input image were explored: (i) whole tumor slice; (ii-iii) tumor mask and/or not edema; (iv-vii) tumor bounding box of 0.8, 1.0, 1.2, 1.5 times. Performance comparison was made among the networks of different architectures along with different image input strategies, using area under the curve (AUC) and accuracy (ACC). Finally, to further boost the performance, a hybrid model was built by incorporating the images with clinical features. Results: With the seven proposed input strategies, seven Swin Transformer models and seven ResNet models were built, respectively. Based on the seven Swin Transformer models, an averaged AUC of 0.965 (internal test) and 0.842 (external test) were achieved, outperforming 0.922 and 0.805 resulting from the seven ResNet models, respectively. When a bounding box of 1.0 times was used, Swin Transformer (AUC = 0.868, ACC = 80.7%), achieved the best results against the one that used tumor segmentation (Tumor + Edema, AUC = 0.862, ACC = 78.5%). The hybrid model that integrated age and location features into images yielded improved performance (AUC = 0.878, Accuracy = 82.0%) over the model that used images only. Conclusions: Swin Transformer outperforms the CNN-based ResNet in IDH prediction. Using bounding box input images benefits the DL networks in IDH prediction and makes the IDH prediction free of refined glioma segmentation feasible.

Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine

Simple Summary

Recently, radiogenomics has played a significant role and offered a new understanding of cancer’s biology and behavior in response to standard therapy. It also provides a more precise prognosis, investigation, and analysis of the patient’s cancer. Over the years, Artificial Intelligence (AI) has provided a significant strength in radiogenomics. In this paper, we offer computational and oncological prospects of the role of AI in radiogenomics, as well as its offers, achievements, opportunities, and limitations in the current clinical practices.

Abstract

Radiogenomics, a combination of “Radiomics” and “Genomics,” using Artificial Intelligence (AI) has recently emerged as the state-of-the-art science in precision medicine, especially in oncology care. Radiogenomics syndicates large-scale quantifiable data extracted from radiological medical images enveloped with personalized genomic phenotypes. It fabricates a prediction model through various AI methods to stratify the risk of patients, monitor therapeutic approaches, and assess clinical outcomes. It has recently shown tremendous achievements in prognosis, treatment planning, survival prediction, heterogeneity analysis, reoccurrence, and progression-free survival for human cancer study. Although AI has shown immense performance in oncology care in various clinical aspects, it has several challenges and limitations. The proposed review provides an overview of radiogenomics with the viewpoints on the role of AI in terms of its promises for computational as well as oncological aspects and offers achievements and opportunities in the era of precision medicine. The review also presents various recommendations to diminish these obstacles.

Automated Machine-Learning Framework Integrating Histopathological and Radiological Information for Predicting IDH1 Mutation Status in Glioma

Diffuse gliomas are the most common malignant primary brain tumors. Identification of isocitrate dehydrogenase 1 (IDH1) mutations aids the diagnostic classification of these tumors and the prediction of their clinical outcomes. While histology continues to play a key role in frozen section diagnosis, as a diagnostic reference and as a method for monitoring disease progression, recent research has demonstrated the ability of multi-parametric magnetic resonance imaging (MRI) sequences for predicting IDH genotypes. In this paper, we aim to improve the prediction accuracy of IDH1 genotypes by integrating multi-modal imaging information from digitized histopathological data derived from routine histological slide scans and the MRI sequences including T1-contrast (T1) and Fluid-attenuated inversion recovery imaging (T2-FLAIR). In this research, we have established an automated framework to process, analyze and integrate the histopathological and radiological information from high-resolution pathology slides and multi-sequence MRI scans. Our machine-learning framework comprehensively computed multi-level information including molecular level, cellular level, and texture level information to reflect predictive IDH genotypes. Firstly, an automated pre-processing was developed to select the regions of interest (ROIs) from pathology slides. Secondly, to interactively fuse the multimodal complementary information, comprehensive feature information was extracted from the pathology ROIs and segmented tumor regions (enhanced tumor, edema and non-enhanced tumor) from MRI sequences. Thirdly, a Random Forest (RF)-based algorithm was employed to identify and quantitatively characterize histopathological and radiological imaging origins, respectively. Finally, we integrated multi-modal imaging features with a machine-learning algorithm and tested the performance of the framework for IDH1 genotyping, we also provided visual and statistical explanation to support the understanding on prediction outcomes. The training and testing experiments on 217 pathologically verified IDH1 genotyped glioma cases from multi-resource validated that our fully automated machine-learning model predicted IDH1 genotypes with greater accuracy and reliability than models that were based on radiological imaging data only. The accuracy of IDH1 genotype prediction was 0.90 compared to 0.82 for radiomic result. Thus, the integration of multi-parametric imaging features for automated analysis of cross-modal biomedical data improved the prediction accuracy of glioma IDH1 genotypes.