Artificial intelligence in the radiomic analysis of glioblastomas: A review, taxonomy, and perspective

Abstract

Radiological imaging techniques, including magnetic resonance imaging (MRI) and positron emission tomography (PET), are the standard-of-care non-invasive diagnostic approaches widely applied in neuro-oncology. Unfortunately, accurate interpretation of radiological imaging data is constantly challenged by the indistinguishable radiological image features shared by different pathological changes associated with tumor progression and/or various therapeutic interventions. In recent years, machine learning (ML)-based artificial intelligence (AI) technology has been widely applied in medical image processing and bioinformatics due to its advantages in implicit image feature extraction and integrative data analysis. Despite its recent rapid development, ML technology still faces many hurdles for its broader applications in neuro-oncological radiomic analysis, such as lack of large accessible standardized real patient radiomic brain tumor data of all kinds and reliable predictions on tumor response upon various treatments. Therefore, understanding ML-based AI technologies is critically important to help us address the skyrocketing demands of neuro-oncology clinical deployments. Here, we provide an overview on the latest advancements in ML techniques for brain tumor radiomic analysis, emphasizing proprietary and public dataset preparation and state-of-the-art ML models for brain tumor diagnosis, classifications (e.g., primary and secondary tumors), discriminations between treatment effects (pseudoprogression, radiation necrosis) and true progression, survival prediction, inflammation, and identification of brain tumor biomarkers. We also compare the key features of ML models in the realm of neuroradiology with ML models employed in other medical imaging fields and discuss open research challenges and directions for future work in this nascent precision medicine area.

Keywords: artificial intelligence; brain tumor; immunotherapy; machine learning; radiogenomics; radiomics; survival prediction; tumor classification.

Figure 1

AI/ML in GBM radiomic analysis: (A) Overall workflow of AI-assisted GBM analysis: 1) Data Acquisition. Raw radiological image data are acquired by MRI scanning of GBM patients. Images are collected into public or private data sets. Before analysis, images are preprocessed (e.g., data cleaning, co-registration, normalization) and standardized (e.g., format, resolutions, voxel sizes). Then, radiologists annotate the images, color-coding different parts of the tumor habitat. 2) Data Augmentation and Preprocessing for ML Models. Imaging dataset and its annotations from step 1 are further “augmented” via geometric transformations, photometric transformation, and/or synthetic data (e.g., GAN) to improve the data generalizability, followed by the optional preprocessing for ML modeling, a process that includes feature extraction to filter out “useless” data and extract explicit features (e.g., biological and/or geometry) in the images. 3) ML modeling and training. Augmented and preprocessed data are fed into various ML models (e.g., SVM, RF, CNN) for GBM radiomic analysis training and validation. Advanced techniques such as transfer learning and multimodal data fusion (e.g., clinical and genomic data) can be employed to improve the training accuracy as well as generality. 4) AI-Assisted Clinical Diagnosis/Deployment. Predictions from the ML models for various medical demands, such as differential diagnosis and survival estimation. (B) Current major challenges (left panel: 1, 2, 3) and perspectives for corresponding solutions (right panel: 1*, 2*, 3*) in AI/ML-assisted GBM radiomic analysis: 1→1* Current GBM radiological image datasets are limited in low numbers, insufficient annotations, and poor organization. Enrichment and standardization of current GBM radiological datasets are urgently needed, while incorporation of clinical and/or genomic data (red circle) can further enhance the performance of ML prediction models; 2→2* develop more comprehensive ML models to further improve the prediction accuracy and address the relatively low generalizability of current models; 3→3* further strengthen collaborations among clinicians, biomedical researchers, and computer scientists to overcome the lack of efficient communications between these parties for the highly multidisciplinary research.