Individual assessment of chronic brain tissue changes in MRI – the role of focal lesions for brain atrophy development. A Voxel-Guided Morphometry study

Kraemer, Matthias; Schormann, Thorsten; Dabringhaus, Andreas; Hirsch, Jochen G.; Stephan, KM; Hömberg, V.; Kappos, Ludwig; Gass, Achim

doi:10.1055/s-2008-1072980

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To illustrate the application of VGM, we provide an example case comprising a baseline image, a follow-up image, and the resulting VGM map in Figure 1 . Initially designed for stroke data analysis (Schormann and Kraemer, 2003 ; Kraemer et al, 2004 ), recent research has demonstrated its efficacy in the context of multiple sclerosis (MS) (Kraemer et al, 2008 ; Fox et al, 2016 ; Weber et al, 2021 , 2022 ). However, it is important to note that the clinical utilization of VGM is currently impeded by the relatively long computation time of ~11 min per case.…”

Section: Methodsmentioning

confidence: 99%

A generalizable deep voxel-guided morphometry algorithm for the detection of subtle lesion dynamics in multiple sclerosis

Raj,

Gass,

Eisele

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionMultiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in the central nervous system. Accurate detection and monitoring of MS-related changes in brain structures are crucial for disease management and treatment evaluation. We propose a deep learning algorithm for creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI brain volumes for analyzing MS disease activity. Our approach focuses on developing a generalizable model that can effectively be applied to unseen datasets.MethodsLongitudinal MS patient high-resolution 3D T1-weighted follow-up imaging from three different MRI systems were analyzed. We employed a 3D residual U-Net architecture with attention mechanisms. The U-Net serves as the backbone, enabling spatial feature extraction from MRI volumes. Attention mechanisms are integrated to enhance the model's ability to capture relevant information and highlight salient regions. Furthermore, we incorporate image normalization by histogram matching and resampling techniques to improve the networks' ability to generalize to unseen datasets from different MRI systems across imaging centers. This ensures robust performance across diverse data sources.ResultsNumerous experiments were conducted using a dataset of 71 longitudinal MRI brain volumes of MS patients. Our approach demonstrated a significant improvement of 4.3% in mean absolute error (MAE) against the state-of-the-art (SOTA) method. Furthermore, the algorithm's generalizability was evaluated on two unseen datasets (n = 116) with an average improvement of 4.2% in MAE over the SOTA approach.DiscussionResults confirm that the proposed approach is fast and robust and has the potential for broader clinical applicability.

show abstract