Background: Central nervous system (CNS) tumors are the second most frequent type of neoplasm in childhood and adolescence, after leukemia. Despite the incorporation of molecular classification and improvement of protocols combining chemotherapy, surgery, and radiotherapy, CNS tumors are still the most lethal neoplasm in this age group. Mass spectrometry imaging (MSI) is a powerful tool to map the distribution of molecular species in tissue sections. Among MSI techniques, desorption electrospray ionization (DESI-MSI) has been demonstrated to enable reliable agreement with the pathological evaluation of different adult cancer types, along with an acceptable time scale for intraoperative use. Methods: In the present work, we aimed to investigate the chemical profile obtained by DESI-MSI as an intraoperative surgical management tool by profiling 162 pediatric brain biopsies and reporting the results according to the histopathology and molecular profile of the tumors. Results: The 2D chemical images obtained by DESI-MSI allowed us to distinguish tumor-transformed tissue from non-tumor tissue with an accuracy of 96.8% in the training set and 94.3% in the validation set after statistical modeling of our data using Lasso. In addition, high-grade and low-grade tumors also displayed a distinct chemical profile when analyzed by DESI-MSI. We also provided evidence that the chemical profile of brain tumors obtained by DESI-MSI correlates with methylation-based molecular classes and specific immunophenotypes found in brain biopsies. Conclusions: The results presented herein support the incorporation of DESI-MSI analysis as an intraoperative assistive tool in prospective clinical trials for pediatric brain tumors management in the near future.
Background: The major current challenge in Alzheimer’s disease (AD) is the identification of individuals likely to develop dementia. Non‐invasive imaging techniques that reflect the integrity of the brain’s white matter are potential parameters to study the pathogenesis of AD. Diffusion tensor imaging (DTI) provides tools to analyze AD‐related brain changes despite the large amount of data generated. To process large amounts of data, computational methods capable of finding relationships among large and complex data sets are needed. In this context, machine learning (ML) techniques have been extended to address this issue. This study aimed to evaluate whether DTI features could predict future AD in non‐AD patients using ML techniques.Method: Sixty‐two subjects, with mild cognitive impairment and healthy controls, were enrolled and followed for approximately eleven months. At the first assessment, MRI, neuropsychological tests, and cerebrospinal fluid analysis were performed. At the second assessment, ten had progressed to Alzheimer’s dementia. The clinical diagnosis was used to train the ML classification models. Five data sets were generated with different missing data strategies. Feature selection strategies measured by information gain were implemented and compared. Twenty ML algorithms distributed over several mathematical approaches were used in model training. A deep learning model was also implemented for comparison with ML results.Result: The best model for predicting AD by DTI was Random Forest with kNN missing data imputation and features selected by information gain. This model achieved a test accuracy of 88.72%. The most relevant DTI tract that contributed to the prediction of the model was the fractional anisotropy (FA) of the cingulum ‐ hippocampus . When other categories of data, such as neuropsychological tests, were included in the model, the accuracy hardly changed (90.26%), suggesting that DTI alone is a good predictor of Alzheimer’s disease. When the deep learning model was run, the constructed neural network achieved 92.31% accuracy.Conclusion: Our results suggest that DTI measures analyzed by ML models, such as Random Forest, may predict AD in non‐AD patients. Furthermore, DTI measure of cingulum ‐ hippocampus tract may be a sensitive marker of early AD pathology.