Primary Intracranial Germ Cell Tumors: A Study with an Integrated Clinicopathological Approach.

Background and Objective: Primary intracranial germ cell tumors (ICGCTs) are rare and are histologically classified as germinomas and non-germinomatous with distinctive prognostic and therapeutic implications. ICGCTs, essentially due to the inherent difficulty of surgical access, pose different challenges and management connotations than their extracranial counterparts. This is a retrospective analysis of histologically verified ICGCTs, which was undertaken to evaluate various clinicopathological features and their implications on patient management. Materials and Methods: Eighty-eight histologically diagnosed cases (over 14 years) of ICGCT at our institute formed the study cohort and were classified into germinoma and non-germinomatous germ cell tumors (NGGCTs). Additionally, germinomas were further subdivided on the basis of 1) tumor marker (TM) levels, as germinoma with normal TM, mildly elevated TM, and markedly elevated TM and 2) radiology features, as germinomas with typical radiology and atypical radiological features. Results: ICGCT with age ≤6 years (P = 0.049), elevated TM (P = 0.047), and NGGCT histology (P < 0.001) showed significantly worse outcomes. Furthermore, germinomas with markedly elevated TM and certain atypical radiological features showed prognosis akin to NGGCT. Conclusions: Analysis of our largest single cancer center Indian patient cohort of ICGCT shows that inclusion of age ≤6 years, raised TM, and certain radiological features may assist clinicians in overcoming the limitations of surgical sampling, with better prognostication of histologically diagnosed germinomas.

Machine-Learning-Based Radiomics for Classifying Glioma Grade from Magnetic Resonance Images of the Brain.

Grading of gliomas is a piece of critical information related to prognosis and survival. Classifying glioma grade by semantic radiological features is subjective, requires multiple MRI sequences, is quite complex and clinically demanding, and can very often result in erroneous radiological diagnosis. We used a radiomics approach with machine learning classifiers to determine the grade of gliomas. Eighty-three patients with histopathologically proven gliomas underwent MRI of the brain. Whenever available, immunohistochemistry was additionally used to augment the histopathological diagnosis. Segmentation was performed manually on the T2W MR sequence using the TexRad texture analysis softwareTM, Version 3.10. Forty-two radiomics features, which included first-order features and shape features, were derived and compared between high-grade and low-grade gliomas. Features were selected by recursive feature elimination using a random forest algorithm method. The classification performance of the models was measured using accuracy, precision, recall, f1 score, and area under the curve (AUC) of the receiver operating characteristic curve. A 10-fold cross-validation was adopted to separate the training and the test data. The selected features were used to build five classifier models: support vector machine, random forest, gradient boost, naive Bayes, and AdaBoost classifiers. The random forest model performed the best, achieving an AUC of 0.81, an accuracy of 0.83, f1 score of 0.88, a recall of 0.93, and a precision of 0.85 for the test cohort. The results suggest that machine-learning-based radiomics features extracted from multiparametric MRI images can provide a non-invasive method for predicting glioma grades preoperatively. In the present study, we extracted the radiomics features from a single cross-sectional image of the T2W MRI sequence and utilized these features to build a fairly robust model to classify low-grade gliomas from high-grade gliomas (grade 4 gliomas).