Brain scan software improves accuracy on different MRI images
Spatial Feature-wise Linear Modulation (SpFiLM) for Contrast Agent-Aware Brain Parcellation
Computer Vision and Pattern RecognitionMachine Learning
Summary
Brain scans use different types of MRI images, some taken before and some after a contrast agent is used to highlight areas in the brain. Software that divides the brain into regions usually works best on images taken before the contrast is added, but less well on images after. The authors created a new method called Spatial FiLM that adjusts the software’s response differently for each type of image and even varies this adjustment in different parts of the brain. This new method improved the accuracy of brain region identification in both kinds of images. It worked better than previous methods, even when the size of the software was kept the same.
brain parcellationT1-weighted MRIcontrast agentT1ce MRIFeature-wise Linear Modulation (FiLM)Spatial FiLM (SpFiLM)UNetDice scorevoxel-wise modulationimage segmentation
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.