RESUMEN
Background Oligodendrogliomas, rare brain tumors in the frontal lobe's white matter, are reshaped by molecular markers like isocitrate dehydrogenase mutations and 1p/19q co-deletion, influencing treatment outcomes. Despite the initial indolence, these tumors pose a significant risk, with a median survival of 10-12 years. Non-invasive alternatives, such as magnetic resonance imaging (MRI) for assessing T2-fluid-attenuated inversion recovery (FLAIR) mismatch and calcifications, provide insights into molecular subtypes and aid prognosis. Our study explored these features to predict the oligodendroglioma status and refine patient management to improve outcomes. Methods In this retrospective study, patient data identified patients with suspected central nervous system tumors undergoing MRI, revealing low-grade gliomas. Surgical biopsy and 1p/19q fluorescence in situ hybridization confirmed the co-deletion status. MRI was used to assess various morphological features. Statistical analyses included x2 tests, Fisher's exact tests, Kruskal-Wallis tests, and binary logistic regression models, with significance set at p < 0.05. Results Seventy-three patients (median age, 37 years) were stratified according to 1p/19q co-deletion. Most (61.6%) were 18-40 years old and mostly male (67.1%). Co-deletion cases, primarily frontal lobe lesions (67.6%), were unilateral (88.2%), with 55.9% non-circumscribed margins and 58.8% ill-defined contours. Smooth contrast enhancement and no necrosis were observed in 48.1% of 1p/19q co-deletion cases. Logistic regression analysis showed a significant association between ill-defined/irregular contours and 1p/19q co-deletion. Fisher's exact test confirmed this but raised concerns about the small sample size influencing the conclusions. Conclusions This study established a significant link between glioma tumor contour characteristics, particularly irregular and ill-defined contours, and the likelihood of 1p/19q co-deletion. Our findings underscore the clinical relevance of using tumor contours in treatment decisions and prognosis assessments.
RESUMEN
BACKGROUND: Central nervous system (CNS) tumours, especially glioma, are a complex disease and many challenges are encountered in their treatment. Artificial intelligence (AI) has made a colossal impact in many walks of life at a low cost. However, this avenue still needs to be explored in healthcare settings, demanding investment of resources towards growth in this area. We aim to develop machine learning (ML) algorithms to facilitate the accurate diagnosis and precise mapping of the brain tumour. METHODS: We queried the data from 2019 to 2022 and brain magnetic resonance imaging (MRI) of glioma patients were extracted. Images that had both T1-contrast and T2-fluid-attenuated inversion recovery (T2-FLAIR) volume sequences available were included. MRI images were annotated by a team supervised by a neuroradiologist. The extracted MRIs thus obtained were then fed to the preprocessing pipeline to extract brains using SynthStrip. They were further fed to the deep learning-based semantic segmentation pipelines using UNet-based architecture with convolutional neural network (CNN) at its backbone. Subsequently, the algorithm was tested to assess the efficacy in the pixel-wise diagnosis of tumours. RESULTS: In total, 69 samples of low-grade glioma (LGG) were used out of which 62 were used for fine-tuning a pre-trained model trained on brain tumor segmentation (BraTS) 2020 and 7 were used for testing. For the evaluation of the model, the Dice coefficient was used as the metric. The average Dice coefficient on the 7 test samples was 0.94. CONCLUSIONS: With the advent of technology, AI continues to modify our lifestyles. It is critical to adapt this technology in healthcare with the aim of improving the provision of patient care. We present our preliminary data for the use of ML algorithms in the diagnosis and segmentation of glioma. The promising result with comparable accuracy highlights the importance of early adaptation of this nascent technology.