0602

View Abstract / View Presentation

Classification of Pediatric Posterior Fossa Tumors using Convolutional Neural Network and Tabular Data

Moran Artzi^1,2,3, Erez Redmard³, Oron Tzemach³, Jonathan Zeltser³, Omri Gropper⁴, Jonathan Roth^2,5,6, Ben Shofty^2,5,7, Danil A. Kozyrev^5,7, Shlomi Constantini^2,5,7, and Liat Ben-Sira^2,8
¹Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel, ²Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel, ³Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel, ⁴The Iby and Aladar Fleischman Faculty of Engineering, Tel Aviv University, Tel Aviv, Israel, ⁵Department of Pediatric Neurosurgery, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel, ⁶The Gilbert Israeli Neurofibromatosis Center, Tel Aviv University, Tel Aviv, Israel, ⁷The Gilbert Israeli Neurofibromatosis Center, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel, ⁸Division of Radiology, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel

A fused architecture comprised of ResNet-50 CNN and tabular network is proposed for the classification of posterior fossa tumors. The model was tested given T1WI+C, FLAIR, diffusion MRI, and tabular data (age), achieving accuracy of 0.87 for the test dataset based on diffusion MRI and age

Figure 2: Illustration of the fused CNN and tabular data architecture

Figure 3: Model interpretation based on Gradient-weighted Class Activation Mapping (Grad-CAM).