Deep Learning for Pediatric Posterior Fossa Tumor Detection and Classification: A Multi-Institutional Study
Jennifer L. Quon, Wasif Bala, L.C. Chen, Jason N. Wright, Lily H. Kim, Michelle Han, Katie Shpanskaya, Edward H. Lee, Elizabeth Tong, Michael Iv, Jayne Seekins, Matthew P. Lungren, Kristina R. M. Braun, Tina Young Poussaint, Suzanne Laughlin, Michael D. Taylor, Robert M. Lober, Hannes Vogel, Paul G. Fisher, Gerald A. Grant, Vijay Ramaswamy, Nicholas A. Vitanza, Chang Yueh Ho, Michael S. B. Edwards, Samuel Cheshier, Kristen W. Yeom
Abstract
BACKGROUND AND PURPOSE: Posterior fossa tumors are the most common pediatric brain tumors. MR imaging is key to tumor detection, diagnosis, and therapy guidance. We sought to develop an MR imaging-based deep learning model for posterior fossa tumor detection and tumor pathology classification. MATERIALS AND METHODS: = 88). There were 199 controls. Tumor histology served as ground truth except for diffuse midline glioma of the pons, which was primarily diagnosed by MR imaging. A modified ResNeXt-50-32x4d architecture served as the backbone for a multitask classifier model, using T2-weighted MRIs as input to detect the presence of tumor and predict tumor class. Deep learning model performance was compared against that of 4 radiologists. RESULTS: score were higher than those of 2 of the 4 radiologists. CONCLUSIONS: We present a multi-institutional deep learning model for pediatric posterior fossa tumor detection and classification with the potential to augment and improve the accuracy of radiologic diagnosis.