Automated segmentation of multiple sclerosis (MS) lesions from MRI scans is important to quantify disease progression. In recent years, convolutional neural networks (CNNs) have shown top performance for this task when a large amount of labeled data is available. However, the accuracy of CNNs suffers when dealing with few and/or sparsely labeled datasets. A potential solution is to leverage the information available in large public datasets in conjunction with a target dataset which only has limited labeled data. In this paper, we propose a training framework, SSL2 (self-supervised-semi-supervised), for multi-modality MS lesion segmentation with limited supervision. We adopt self-supervised learning to leverage the knowledge from large public 3T datasets to tackle the limitations of a small 7T target dataset. To leverage the information from unlabeled 7T data, we also evaluate state-of-the-art semi-supervised methods for other limited annotation settings, such as small labeled training size and sparse annotations. We use the shifted-window (Swin) transformer1 as our backbone network. The effectiveness of self-supervised and semi-supervised training strategies is evaluated in our in-house 7T MRI dataset. The results indicate that each strategy improves lesion segmentation for both limited training data size and for sparse labeling scenarios. The combined overall framework further improves the performance substantially compared to either of its components alone. Our proposed framework thus provides a promising solution for future data/label-hungry 7T MS studies.
Spinal cord (SC) tissue loss is known to occur in some patients with multiple sclerosis (MS), resulting in SC atrophy.
Currently, no measurement tools exist to determine the magnitude of SC atrophy from Magnetic Resonance Images
(MRI). We have developed and implemented a novel semi-automatic method for quantifying the cervical SC volume
(CSCV) from Magnetic Resonance Images (MRI) based on level sets. The image dataset consisted of SC MRI exams
obtained at 1.5 Tesla from 12 MS patients (10 relapsing-remitting and 2 secondary progressive) and 12 age- and gender-matched
healthy volunteers (HVs). 3D high resolution image data were acquired using an IR-FSPGR sequence acquired
in the sagittal plane. The mid-sagittal slice (MSS) was automatically located based on the entropy calculation for each of
the consecutive sagittal slices. The image data were then pre-processed by 3D anisotropic diffusion filtering for noise
reduction and edge enhancement before segmentation with a level set formulation which did not require re-initialization.
The developed method was tested against manual segmentation (considered ground truth) and intra-observer and inter-observer
variability were evaluated.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.