RT Journal Article
SR Electronic
T1 Deep Learning for Pediatric Posterior Fossa Tumor Detection and Classification: A Multi-Institutional Study
JF American Journal of Neuroradiology
JO Am. J. Neuroradiol.
FD American Society of Neuroradiology
SP 1718
OP 1725
DO 10.3174/ajnr.A6704
VO 41
IS 9
A1 J.L. Quon
A1 W. Bala
A1 L.C. Chen
A1 J. Wright
A1 L.H. Kim
A1 M. Han
A1 K. Shpanskaya
A1 E.H. Lee
A1 E. Tong
A1 M. Iv
A1 J. Seekins
A1 M.P. Lungren
A1 K.R.M. Braun
A1 T.Y. Poussaint
A1 S. Laughlin
A1 M.D. Taylor
A1 R.M. Lober
A1 H. Vogel
A1 P.G. Fisher
A1 G.A. Grant
A1 V. Ramaswamy
A1 N.A. Vitanza
A1 C.Y. Ho
A1 M.S.B. Edwards
A1 S.H. Cheshier
A1 K.W. Yeom
YR 2020
UL http://www.ajnr.org/content/41/9/1718.abstract
AB 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: The study cohort comprised 617 children (median age, 92 months; 56% males) from 5 pediatric institutions with posterior fossa tumors: diffuse midline glioma of the pons (n = 122), medulloblastoma (n = 272), pilocytic astrocytoma (n = 135), and ependymoma (n = 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: Model tumor detection accuracy exceeded an AUROC of 0.99 and was similar to that of 4 radiologists. Model tumor classification accuracy was 92% with an F1 score of 0.80. The model was most accurate at predicting diffuse midline glioma of the pons, followed by pilocytic astrocytoma and medulloblastoma. Ependymoma prediction was the least accurate. Tumor type classification accuracy and F1 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.PFposterior fossaEVDexternal ventricular drainCAMsclass activation mapsDMGdiffuse midline glioma of the ponsEPependymomaMBmedulloblastomaPApilocytic astrocytomaPFposterior fossaROCreceiver operating characteristict-SNEt-distributed stochastic neighbor embedding