Deep learning-based detection of pediatric brain tumor presence on MRI.
Authors
Affiliations (5)
Affiliations (5)
- Department of Physics, Universidad Autónoma Metropolitana-Iztapalapa, Mexico City, Mexico (E.R.S., S.H.T.).
- Department of Imageonology, Hospital Infantil de México Federico Gómez, Mexico City, Mexico.
- Department of Neurosurgery, Hospital Centro Médico Nacional "20 de Noviembre", Mexico City, Mexico (J.V.E.).
- Faculty of Physical and Mathematical Sciences, Benemérita Universidad Autónoma de Puebla, Puebla, México.
- Department of Neurosurgery, Hospital Infantil de México Federico Gómez, Mexico City, Mexico.
Abstract
Pediatric cancer imposes a significant global burden, with ∼400 000 new cases annually. Magnetic resonance imaging (MRI) is a fundamental technique for timely diagnosis; however, interpretation can be subjective. In this context, convolutional neural networks (CNNs) have emerged as a promising tool for early and accurate detection of brain tumors in pediatric patients. To develop and validate a CNN model for tumor detection tasks (tumor vs nontumor) of pediatric brain MRI images using T1-weighted imaging. T1-weighted brain MRI images from 285 pediatric patients were included (140 with confirmed tumors and 145 controls). A CNN architecture with convolutional layers, max-pooling, and dropout regularization was implemented. The model was trained and evaluated using cross-validation, employing the following metrics: accuracy, precision, recall, and F1-score. Model performance was compared across training configurations of 10-50 and 100 epochs to determine the optimal setup. The model trained for 40 epochs achieved the best overall performance, with a precision of 99%, a recall of 100%, and an F1-score of 99%. These metrics demonstrate excellent tumor detection while eliminating false negatives, a crucial aspect in pediatric oncology. The CNN demonstrates strong potential as a diagnostic aid for detection brain tumors using pediatric MRI images. Its integration into clinical environments could contribute to more objective interpretation, optimize diagnostic workflows, and provide imaging follow-up before and after treatment.