Author name cluster

Martin Bauer

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

YNICL Journal 2026 Journal Article

Microstructure-informed deep learning improves thalamic atrophy segmentation and clinical associations in multiple sclerosis and related neuroimmunological diseases

Omar Angelo Ibrahim
Henri Trang
Qianlan Chen
Lara Zimmermann
Alexander U. Brandt
Tatiana Usnich
Stefano Magon
Muhamed Barakovic

Thalamic atrophy is a sensitive imaging marker of neurodegeneration in multiple sclerosis (MS) and related disorders, though thalamus segmentation remains method-dependent. Quantitative magnetic resonance imaging (qMRI) may enhance thalamic boundary contrast, particularly in the context of deep learning. We benchmarked thalamic segmentations from two atlas-constrained algorithms, FreeSurfer and FIRST, and two deep learning algorithms, DBSegment and MindGlide (an MS-trained model), against ground truth (GT) labels, tested whether quantitative R1 maps improve performance, and evaluated clinical validity cross-sectionally and longitudinally. We generated thalamus masks using each algorithm from T1-weighted data in a single-scanner cohort (baseline n = 321; 1-year follow-up n = 234) including patients with MS/related disorders and healthy controls. Using MindGlide, we also produced FLAIR- and R1-based masks and ensembles. Manual GT labels were obtained for 50 MS patients using T1w and FLAIR scans. For voxel-wise GT agreement, DBSegment yielded the highest Dice-similarity coefficient; atlas-constrained methods showed the highest sensitivity but lowest precision, while MindGlide balanced both. Volumetrically, MindGlide showed the most accurate estimates; DBSegment and FreeSurfer showed proportional bias, and both atlas-constrained methods overestimated thalamic volumes. Adding R1 input to MindGlide produced modest or no gains in GT agreement. Additionally, MindGlide volumes were most consistently associated with disability and cognitive scores cross-sectionally, and longitudinally showed the largest effects between thalamic volume change and EDSS worsening. Incorporating R1 maps offered no cross-sectional benefit but strengthened longitudinal associations. Higher-resolution qMRI and multi-contrast deep learning architectures may further enhance thalamic segmentation and monitoring in neuroinflammatory diseases.

Details DOI

JMLR Journal 2025 Journal Article

The Z-Gromov-Wasserstein Distance

Martin Bauer
Facundo Mémoli
Tom Needham
Mao Nishino

The Gromov-Wasserstein (GW) distance is a powerful tool for comparing metric measure spaces which has found broad applications in data science and machine learning. Driven by the need to analyze data sets whose objects have increasingly complex structure (such as node and edge-attributed graphs), several variants of GW distance have been introduced in the recent literature. With a view toward establishing a general framework for the theory of GW-like distances, this paper considers a vast generalization of the notion of a metric measure space: for an arbitrary metric space $Z$, we define a $Z$-network to be a measure space endowed with a kernel valued in $Z$. We introduce a method for comparing $Z$-networks by defining a generalization of GW distance, which we refer to as $Z$-Gromov-Wasserstein ($Z$-GW) distance. This construction subsumes many previously known metrics and offers a unified approach to understanding their shared properties. This paper demonstrates that the $Z$-GW distance defines a metric on the space of $Z$-networks which retains desirable properties of $Z$, such as separability, completeness, and geodesicity. Many of these properties were unknown for existing variants of GW distance that fall under our framework. Our focus is on foundational theory, but our results also include computable lower bounds and approximations of the distance which will be useful for practical applications. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

YNIMG Journal 2020 Journal Article

Association of dopamine D2/3 receptor binding potential measured using PET and [11C]-(+)-PHNO with post-mortem DRD2/3 gene expression in the human brain

Arkadiusz Komorowski
Ana Weidenauer
Matej Murgaš
Ulrich Sauerzopf
Wolfgang Wadsak
Markus Mitterhauser
Martin Bauer
Marcus Hacker

Open access post-mortem transcriptome atlases such as the Allen Human Brain Atlas (AHBA) can inform us about mRNA expression of numerous proteins of interest across the whole brain, while in vivo protein binding in the human brain can be quantified by means of neuroreceptor positron emission tomography (PET). By combining both modalities, the association between regional gene expression and receptor distribution in the living brain can be approximated. Here, we compare the characteristics of D2 and D3 dopamine receptor distribution by applying the dopamine D2/3 receptor agonist radioligand [11C]-(+)-PHNO and human gene expression data. Since [11C]-(+)-PHNO has a higher affinity for D3 compared to D2 receptors, we hypothesized that there is a stronger relationship between D2/3 non-displaceable binding potentials (BPND) and D3 mRNA expression. To investigate the relationship between D2/3 BPND and mRNA expression of DRD2 and DRD3 we performed [11C]-(+)-PHNO PET scans in 27 healthy subjects (12 females) and extracted gene expression data from the AHBA. We also calculated D2/D3 mRNA expression ratios to imitate the mixed D2/3 signal of [11C]-(+)-PHNO. In accordance with our a priori hypothesis, a strong correlation between [11C]-(+)-PHNO and DRD3 expression was found. However, there was no significant correlation with DRD2 expression. Calculated D2/D3 mRNA expression ratios also showed a positive correlation with [11C]-(+)-PHNO binding, reflecting the mixed D2/3 signal of the radioligand. Our study supports the usefulness of combining gene expression data from open access brain atlases with in vivo imaging data in order to gain more detailed knowledge on neurotransmitter signaling.

Details DOI