HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Me-NDT: Neural-backed Decision Tree for visual Explainability of deep Medical models

Abstract : Despite the progress of deep learning on medical imaging, there is still not a true understanding of what networks learn and of how decisions are reached. Here, we address this by proposing a Visualized Neural-backed Decision Tree for Medical image analysis, Me-NDT. It is a CNN with a tree-based structure template that allows for both classification and visualization of firing neurons, thus offering interpretability. We also introduce node and path losses that allow Me-NDT to consider the entire path instead of isolated nodes. Our experiments on brain CT and chest radiographs outperform all baselines. Overall, Me-NDT is a lighter, comprehensively explanatory model, of great value for clinical practice.
Complete list of metadata

Contributor : Vicky Kalogeiton Connect in order to contact the contributor
Submitted on : Friday, September 24, 2021 - 10:42:54 AM
Last modification on : Wednesday, February 2, 2022 - 11:32:03 AM


Publisher files allowed on an open archive


  • HAL Id : hal-03353559, version 1


Guanghui Fu, Ruiqian Wang, Jianqiang Li, Maria Vakalopoulou, Vicky Kalogeiton. Me-NDT: Neural-backed Decision Tree for visual Explainability of deep Medical models. Medical Imaging with Deep Learning 2021, Jul 2021, Lübeck (virtual), Germany. ⟨hal-03353559⟩



Record views


Files downloads