Deep learning (DL) has led to significant improvements in medical image synthesis, enabling advanced image-toimage translation to generate synthetic images. However, DL methods face challenges such as domain shift and high demands for training data, limiting their generalizability and applicability. Historically, image synthesis was also carried out using deformable image registration (DIR), a method that warps moving images of a desired modality to match the anatomy of a fixed image. However, concerns about its speed and accuracy led to its decline in popularity. With the recent advances of DL-based DIR, we now revisit and reinvigorate this line of research. In this paper, we propose a fast and accurate synthesis method based on DIR. We use the task of synthesizing a rare magnetic resonance (MR) sequence, white matter nulled (WMn) T1-weighted (T1-w) images, to demonstrate the potential of our approach. During training, our method learns a DIR model based on the widely available MPRAGE sequence, which is a cerebrospinal fluid nulled (CSFn) T1-w inversion recovery gradient echo pulse sequence. During testing, the trained DIR model is first applied to estimate the deformation between moving and fixed CSFn images. Subsequently, this estimated deformation is applied to align the paired WMn counterpart of the moving CSFn image, yielding a synthetic WMn image for the fixed CSFn image. Our experiments demonstrate promising results for unsupervised image synthesis using DIR. These findings highlight the potential of our technique in contexts where supervised synthesis methods are constrained by limited training data.
Deep learning algorithms using Magnetic Resonance (MR) images have demonstrated state-of-the-art performance in the automated segmentation of Multiple Sclerosis (MS) lesions. Despite their success, these algorithms may fail to generalize across sites or scanners, leading to domain generalization errors. Few-shot or one-shot domain adaptation is an option to reduce the generalization error using limited labeled data from the target domain. However, this approach may not yield satisfactory performance due to the limited data available for adaptation. In this paper, we aim to address this issue by integrating one-shot adaptation data with harmonized training data that includes labels. Our method synthesizes new training data with a contrast similar to that of the test domain, through a process referred to as “contrast harmonization” in MRI. Our experiments show that combining one-shot adaptation data with harmonized training data outperformed the use of either one of the data sources alone. Domain adaptation using only harmonized training data achieved comparable or even better performance compared to one-shot adaptation. In addition, all adaptations only required light fine-tuning of two to five epochs for convergence.
The development of automatic whole brain segmentation algorithms has greatly facilitated large-scale multi cohort magnetic resonance (MR) image analyses in recent years. However, the performance of these segmentation algorithms is often affected by image contrast due to the variations in pulse sequences, acquisitions parameters, and manufacturers. Quantitatively evaluating segmentation algorithms on different image contrasts is challenging because manual delineations of the human brain are usually limited. In this study, we tackle the problem by synthesizing new contrast MR images from a small set of images with manual delineations. We quantitatively evaluate the current state-of-the-art whole brain segmentation algorithm, SLANT, on various MR image contrasts. Based on 50 manually delineated T1-weighted MR images acquired from a single site, we synthesize new contrast images using a deep learning-based harmonization algorithm. Two types of contrast synthesis were conducted to simulate both intra- and inter-site contrast variability in MR imaging. SLANT performance is measured using the Dice similarity coefficient (DSC). Experiments show that the average DSC of SLANT varies with image contrast. We also demonstrate the preferred and the least preferred contrast of SLANT based on 11 real MR imaging sites.
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.