Description

In the proposed retrospective study, images (MRI, CT, or PET) undertaken as part of standard of care (pre-treatment, post-operative, response assessment, and surveillance) will be analyzed. The DMG database maintaining records of patients registered in TMC neuro-oncology DMG will be screened to identify the patients eligible for the study. With approximately 500-600 gliomas seen annually and approximately 80-100 patients/year having pre-treatment imaging, we expect a ceiling of 1000 patients during 2010-2022, which will be the maximum number of patients used for the analysis. All the images will be downloaded from the PACS applying anonymization filters, with clinical records extracted by review of electronic medical records and radiation plans. Imaging pre-processing will be done, which will include skull stripping and registration across different modalities (e.g., MRI and CT) or different sequences (e.g., T1C, T2W, ADC) will be done using rigid or deformable algorithms as suited best for the modality. Image segmentation to classify the region of interest will be done and verified individually by a neuro-radiologist or nuclear medicine physician as appropriate. The segmentations will be done to identify T1-contrast enhancing region (CE), non-enhancing regions (NE), and necrosis (NEC) guided by T1-C, T2W, and T2-FLAIR areas. The contours and the images will be resampled to a uniform resolution for different sequences or modalities (e.g., T2W/ ADC/ PET) to match either with the 3D sequence (e.g., FSPGR sequence) or available images with the least slice thickness. Subsequently, normalization techniques (e.g., histogram normalization/ Z-score normalization) will be undertaken within the individual images and across the entire dataset to account or image heterogeneity, including field strength for MRI and different image acquisition parameters. For auto segmentation, both supervised and unsupervised machine learning algorithms will be applied. For the supervised model, the entire database will be split into training and test cohorts for the model and application development, respectively. The effectiveness of the automated model will be tested using the dice similarity coefficient between manually segmentation regions and AI-based segments. For prognostication of gliomas, the next step will include feature extraction, which will consist of first-order (including shape, histogram), second-order or higher-order (e.g., different texture features like GLCM, GLDM, GLSZM, etc.), or deep learning techniques will be employed. Delta-radiomics will include temporal changes in the radiomic features from different time points for the same patient within the entire volume and individual regions. Subsequently, feature reduction and selection techniques like LASSO, recursive feature elimination will be used to shortlist the number of features depending on the sample size. The outputs will be decided based on the modeling defined for specific class problems (e.g., tumor vs. edema, recurrence vs. pseudo progression, outcomes, tumor region of interest vs. non-tumoral area) as obtained from the clinical information. Any class imbalance will be addressed using methods like random subset sampling or SMOTE analysis for data augmentation of the minority class. Machine learning algorithms like LDA, k-NN, SVM, random forest, AdaBoost, etc., will be applied singularly or in combination as an ensembled classifier to find the model with best performance. Deep learning classifiers will be used along with feature-based modeling and compared to test the classifier's applicability. Validation techniques like leave-one-out validation, k-fold validation, and split (into training and test cohort) will be used to assess the stability of the machine learning model. Radiomic analysis will be done by data scientist/ study investigators with expertise in data analytics. All segmentations will be done on open-source software like ITK snap (itksnap.org) or 3D Slicer (slicer.org). Feature extraction and modeling will be done using open-source software like Python (python.org). With continuous advancements in computational science, available newer analytical techniques and platforms will be applied as appropriate by collaborators from Indian Statistical Institute, Kolkata, Machine Intelligence Unit by sharing of the anonymized data.