Benefits of Linear Conditioning for Segmentation using Metadata

02/18/2021
by   Andréanne Lemay, et al.
0

Medical images are often accompanied by metadata describing the image (vendor, acquisition parameters) and the patient (disease type or severity, demographics, genomics). This metadata is usually disregarded by image segmentation methods. In this work, we adapt a linear conditioning method called FiLM (Feature-wise Linear Modulation) for image segmentation tasks. This FiLM adaptation enables integrating metadata into segmentation models for better performance. We observed an average Dice score increase of 5.1 spinal cord tumor segmentation when incorporating the tumor type with FiLM. The metadata modulates the segmentation process through low-cost affine transformations applied on feature maps which can be included in any neural network's architecture. Additionally, we assess the relevance of segmentation FiLM layers for tackling common challenges in medical imaging: training with limited or unbalanced number of annotated data, multi-class training with missing segmentations, and model adaptation to multiple tasks. Our results demonstrated the following benefits of FiLM for segmentation: FiLMed U-Net was robust to missing labels and reached higher Dice scores with few labels (up to 16.7 www.ivadomed.org.

READ FULL TEXT

page 3

page 12

research
06/05/2023

Dual self-distillation of U-shaped networks for 3D medical image segmentation

U-shaped networks and its variants have demonstrated exceptional results...
research
03/09/2020

Automatic segmentation of spinal multiple sclerosis lesions: How to generalize across MRI contrasts?

Despite recent improvements in medical image segmentation, the ability t...
research
04/05/2023

FMG-Net and W-Net: Multigrid Inspired Deep Learning Architectures For Medical Imaging Segmentation

Accurate medical imaging segmentation is critical for precise and effect...
research
03/22/2021

Spatially Dependent U-Nets: Highly Accurate Architectures for Medical Imaging Segmentation

In clinical practice, regions of interest in medical imaging often need ...
research
08/18/2023

Metadata Improves Segmentation Through Multitasking Elicitation

Metainformation is a common companion to biomedical images. However, thi...
research
09/17/2023

Image-level supervision and self-training for transformer-based cross-modality tumor segmentation

Deep neural networks are commonly used for automated medical image segme...
research
07/19/2022

The Dice loss in the context of missing or empty labels: Introducing Φ and ε

Albeit the Dice loss is one of the dominant loss functions in medical im...

Please sign up or login with your details

Forgot password? Click here to reset