Spfilm improves brain region labeling on pre and post contrast mri scans
Spatial Feature-wise Linear Modulation (SpFiLM) for Contrast Agent-Aware Brain Parcellation
Computer Vision and Pattern RecognitionMachine Learning
Summary
Different types of MRI scans of the brain can look quite different, especially before and after a contrast dye is used. Models trained on one type may not work well on the other. The authors created a new technique called Spatial FiLM that helps a single model adjust its understanding at each location in the brain depending on the scan type. This approach improved the accuracy of identifying brain regions on both types of scans.
What this means in practice
- •For medical imaging engineers: Create MRI brain segmentation tools that perform equally well on scans taken before and after contrast dye injection.
- •For hospital data teams: Integrate a single brain parcellation model into clinical workflows that include both pre- and post-contrast MRI scans for improved consistency.
Authors
Pushpendra Singh, Joshua R. Astley, Roman Rodionov, John Duncan, Tom Vercauteren, Rachel Sparks
Abstract
Most automated brain parcellation tools are developed and validated on T1-weighted (T1w) MRI. Yet, some clinical workflows for which parcellation is relevant only use contrast-enhanced T1w (T1ce) MRI, on which T1w-trained models are less accurate. We present a unified network that parcellates both pre- and post-contrast agent T1w MRI reliably, trained on a combination of the two with conditioning that spatially modulates its response differently for each. Feature-wise Linear Modulation (FiLM) is a known approach for input-based modulation in networks. It applies a per-channel scale and shift uniformly across the input. However, the appearance change between pre- and post-contrast varies locally across the brain, making FiLM suboptimal for our use case. In this work, we introduce Spatial FiLM (SpFiLM), a conditioning layer whose modulation varies spatially, assembling a voxel-wise scale and shift from image-derived spatial patterns. Using a cohort of 134 patients with paired T1w and T1ce MRI parcellated into 106 classes, the addition of SpFiLM layers in a UNet increased the mean Dice on the test set of 25 patients from 80.2% to 84.1%, a 4.9% relative improvement. Adding SpFiLM layers led to the best performance on both pre- and post-contrast MRI, even when controlling for network parameter counts.