Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data

by   Guanghui Fu, et al.

One often lacks sufficient annotated samples for training deep segmentation models. This is in particular the case for less common imaging modalities such as Quantitative Susceptibility Mapping (QSM). It has been shown that deep models tend to fit the target function from low to high frequencies. One may hypothesize that such property can be leveraged for better training of deep learning models. In this paper, we exploit this property to propose a new training method based on frequency-domain disentanglement. It consists of two main steps: i) disentangling the image into high- and low-frequency parts and feature learning; ii) frequency-domain fusion to complete the task. The approach can be used with any backbone segmentation network. We apply the approach to the segmentation of the red and dentate nuclei from QSM data which is particularly relevant for the study of parkinsonian syndromes. We demonstrate that the proposed method provides considerable performance improvements for these tasks. We further applied it to three public datasets from the Medical Segmentation Decathlon (MSD) challenge. For two MSD tasks, it provided smaller but still substantial improvements (up to 7 points of Dice), especially under small training set situations.


Fourier Disentangled Multimodal Prior Knowledge Fusion for Red Nucleus Segmentation in Brain MRI

Early and accurate diagnosis of parkinsonian syndromes is critical to pr...

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

Deep neural networks are commonly used for automated medical image segme...

Shape-Aware Organ Segmentation by Predicting Signed Distance Maps

In this work, we propose to resolve the issue existing in current deep l...

Frequency Dropout: Feature-Level Regularization via Randomized Filtering

Deep convolutional neural networks have shown remarkable performance on ...

MaskIt: Masking for efficient utilization of incomplete public datasets for training deep learning models

A major challenge in training deep learning models is the lack of high q...

Adaptive Neural Layer for Globally Filtered Segmentation

This study is motivated by typical images taken during ultrasonic examin...

Please sign up or login with your details

Forgot password? Click here to reset