About

Laurent Younes is a professor in the Department of Applied Mathematics and Statistics at Johns Hopkins University and a member of the JHU Center for Imaging Science. His research focuses on the statistical properties of image analysis, deformation analysis, and shape recognition, with particular emphasis on Markov Random Fields as a mathematical tool for modeling and making inferences about image data. His pioneering shape analysis algorithms enable researchers and clinicians to better interpret medical imaging data, advancing the detection and treatment of diseases such as Parkinson’s disease, Alzheimer’s disease, cardiac disease, and mental illness. Younes leads research teams studying the statistical properties of image analysis and shape recognition, and his work is central to the field of computational anatomy, especially in analyzing how diseases affect organ shapes. He has contributed significantly to understanding early-stage brain disease, network neurodegeneration during Alzheimer’s, and the creation of algorithms to examine cortical atrophy in mild cognitive impairment. Younes authored the book 'Shapes and Diffeomorphisms,' published by Springer, which is considered a definitive text on the mathematical analysis of shapes and their transformations. He has received recognition for his contributions, including being named a Fellow of the Institute for Mathematical Statistics in 2015 and a Fellow of the Society for Industrial and Applied Mathematics in 2023. Younes is actively involved in the academic community through organizing workshops, giving invited presentations, and serving as an associate editor for prominent journals.

Research topics

• Medicine
• Pathology
• Psychology
• Internal medicine
• Psychiatry
• Artificial Intelligence
• Endocrinology
• Computer Science
• Neuroscience
• Mathematics
• Algorithm
• Biology
• Biochemistry
• Computer vision

Selected publications

• Rostral Associations of MRI Atrophy of the Amygdala and Entorhinal Cortex Across the AD Spectrum

  medRxiv · 2026-01-30

  articleOpen access

  Abstract This paper examines associations of atrophy in the amygdala, entorhinal cortex and hippocampus based on magnetic resonance imaging (MRI) and Positron Emission Tomography (PET) scans from two independent cohorts: Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD) study. The amygdala and entorhinal cortex (ERC) are shown to change earlier in the disease than the hippocampus based on atrophy of laminar thickness of the ERC and amygdala volumes. Over four hundred laminar reconstructions showed that ERC volume loss is linked to cortical thinning, as a more specific measure historically linked to the layer specific pattern of tau pathology deposition. Additionally, high field atlasing with delineations of amygdala subregions shows predominant volume loss in medial subregions including basomedial, basolateral, and corticocentromedial compared with the lateral subregion. In the context of earlier work linking MRI-based atrophy with hyperphospho-rylated tau deposition in the ERC and amygdala, the atrophy rate marker is shown to be strongly associated with tau deposition as measured by tau positron emission tomography imaging and co-localization of the atrophy marker to the spatial distribution of tau deposition. Highlights Structural MRI analyses across ADNI and BIOCARD cohorts reveal significantly greater early atrophy in amygdala and entorhinal cortex (ERC), marking them as sensitive indicators of preclinical Alzheimer’s disease. ERC volume loss is shown to correspond to cortical laminar thinning by surface-based diffeomorphic reconstructions, confirming MRI volume atrophy as a biologically valid marker of early neuronal degeneration. Predominant atrophy in medial amygdala subregions (basomedial, basolateral, corticocentromedial) are identified compared to the lateral amygdala using high-field (11T) atlases, mirroring known histopathological tau distribution. MRI volume atrophy correlates with tau burden measured by tau PET imaging, demonstrating region-specific correspondence between structural atrophy and molecular pathology.

  PublisherDOI

• Plasma biomarker trajectories across Alzheimer’s clinical onset: a 17-year prospective study

  Alzheimer s Research & Therapy · 2026-04-22

  articleOpen access

  Long-term trajectories of plasma biomarkers relative to clinical symptom onset in Alzheimer’s disease (AD) remain scarce. We analyzed 17-year longitudinal data from 195 initially cognitively unimpaired participants in the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD) study. Plasma biomarker trajectories were modeled as a function of years from estimated mild cognitive impairment (MCI) symptom onset using generalized additive mixed models. In participants who progressed to amyloid-positive MCI, plasma p-tau181/Aβ42 and GFAP diverged from stable controls earliest (about 13 and 12 years before symptom onset, respectively), followed by Aβ42/Aβ40, p-tau181, and NfL, all of which became abnormal before symptom onset. Individuals who developed amyloid-negative MCI showed abnormalities only in GFAP (about 11 years before onset) and YKL-40 (around the time of symptom onset). This study establishes a clinically anchored temporal map of plasma AD biomarkers. Plasma markers detect AD-related pathological changes more than a decade before symptom onset, offering a scalable, non-invasive approach for defining the preclinical phase and identifying at-risk individuals for early intervention.

  PublisherDOI

• A Continuous Scale Space of Diffeomorphisms

  SIAM Journal on Imaging Sciences · 2026-01-06

  articleSenior author
  PublisherDOI

• CellCover Defines Marker Gene Panels Capturing Developmental Progression in Neocortical Neural Stem Cell Identity

  eLife · 2025-10-21

  preprintOpen access

  Definition of cell classes across the tissues of living organisms is central in the analysis of growing atlases of single-cell RNA sequencing (scRNA-seq) data across biomedicine. Marker genes for cell classes are most often defined by differential expression (DE) methods that serially assess individual genes across landscapes of diverse cells. This serial approach has been extremely useful, but is limited because it ignores possible redundancy or complementarity across genes that can only be captured by analyzing multiple genes simultaneously. Interrogating binarized expression data, we aim to identify discriminating panels of genes that are specific to, not only enriched in, individual cell types. To efficiently explore the vast space of possible marker panels, leverage the large number of cells often sequenced, and overcome zero-inflation in scRNA-seq data, we propose viewing marker gene panel selection as a variation of the “minimal set-covering problem” in combinatorial optimization. Using scRNA-seq data from blood and brain tissue, we show that this new method, CellCover, performs as good or better than DE and other methods in defining cell-type discriminating gene panels, while reducing gene redundancy and capturing cell-class-specific signals that are distinct from those defined by DE methods. Transfer learning experiments across mouse, primate, and human data demonstrate that CellCover identifies markers of conserved cell classes in neocortical neurogenesis, as well as developmental progression in both progenitors and neurons. Exploring markers of human outer radial glia (oRG, or basal RG) across mammals, we show that transcriptomic elements of this key cell type in the expansion of the human cortex likely appeared in gliogenic precursors of the rodent before the full program emerged in neurogenic cells of the primate lineage. We have assembled the public datasets we use in this report within the NeMO Analytics multi-omic data exploration environment [1], where the expression of individual genes (NeMO: Individual genes in cortex and NeMO: Individual genes in blood) and marker gene panels (NeMO: Telley 3 CellCover Panels, NeMO: Telley 12 CellCover Panels, NeMO: Sorted Brain Cell CellCover Panels, and NeMO: Blood 34 CellCover Panels) can be freely explored without coding expertise. CellCover is available in CellCover R and CellCover Python.

  PublisherDOI

• The xIV-LDDMM toolkit of image-varifold based technologies for mapping 3D images and spatial-omics across scales

  Communications Biology · 2025-09-30

  articleOpen access

  Advancements in imaging and molecular techniques enable the collection of subcellular-scale data. Diversity in measured features, resolution, and physical scope of capture across technologies and experimental protocols pose numerous challenges to integrating data with reference coordinate systems and across scales. This paper describes a collection of technologies that we have developed for mapping data across scales and modalities, such as genes to tissues, specifically in a 3D setting. Our collection of technologies include (i) an explicit censored data representation for the partial matching problem mapping whole brains to subsampled subvolumes, (ii) a multi, scale-space optimization technology for generating resampling grids optimized to represent spatial geometry at fixed complexities, and (iii) mutual-information based functional feature selection. We integrate these technologies with our cross-modality mapping algorithm through the use of image-varifold measure norms to represent universally data across scales and imaging modalities. Collectively, these methods afford efficient representations of peta-scale imagery providing the algorithms for mapping from the nano to millimeter scales, which we term cross-modality image-varifold LDDMM (xIV-LDDMM).

  PublisherOA PDFDOI

• Mapping spatial gradients in spatial transcriptomics data with score matching

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-11-27 · 1 citations

  preprintOpen accessSenior author

  Abstract Spatial transcriptomics (ST) technologies measure gene expression at thousands of locations within a two-dimensional tissue slice, enabling the study of spatial gene expression patterns. Spatial variation in gene expression is characterized by spatial gradients , or the collection of vector fields describing the direction and magnitude in which the expression of each gene increases. However, the few existing methods that learn spatial gradients from ST data either make restrictive and unrealistic assumptions on the structure of the spatial gradients or do not accurately model discrete transcript locations/counts. We introduce SLOPER (for Score-based Learning Of Poisson-modeled Expression Rates), a generative model for learning spatial gradients (vector fields) from ST data. SLOPER models the spatial distribution of mRNA transcripts with an inhomogeneous Poisson point process (IPPP) and uses score matching to learn spatial gradients for each gene. SLOPER utilizes the learned spatial gradients in a novel diffusion-based sampling approach to enhance the spatial coherence and specificity of the observed gene expression measurements. We demonstrate that the spatial gradients and enhanced gene expression representations learned by SLOPER leads to more accurate identification of tissue organization, spatially variable gene modules, and continuous axes of spatial variation (isodepth) compared to existing methods. Software availability SLOPER is available at https://github.com/chitra-lab/SLOPER .

  PublisherDOI

• A continuous scale space of diffeomorphisms

  arXiv (Cornell University) · 2025-01-01

  preprintOpen accessSenior author

  In this paper, we define and study a nested family of reproducing kernel Hilbert spaces of vector fields that is indexed by a range of scales, from which we construct a reproducing kernel Hilbert space of scale-dependent vector fields. We provide a characterization of the reproducing kernel of that space, with numerical approximations ensuring quick evaluations when this kernel does not have a closed form. We then introduce a multiscale version of the large deformation diffeomorphic metric mapping (LDDMM) problem and prove the existence of solutions. Finally, we provide numerical experiments performing landmark matching using multiscale LDDMM.

  PublisherOA PDFDOI

• Author response: CellCover Defines Marker Gene Panels Capturing Developmental Progression in Neocortical Neural Stem Cell Identity

  2025-10-21

  peer-reviewOpen access

  Definition of cell classes across the tissues of living organisms is central in the analysis of growing atlases of single-cell RNA sequencing (scRNA-seq) data across biomedicine. Marker genes for cell classes are most often defined by differential expression (DE) methods that serially assess individual genes across landscapes of diverse cells. This serial approach has been extremely useful, but is limited because it ignores possible redundancy or complementarity across genes that can only be captured by analyzing multiple genes simultaneously. Interrogating binarized expression data, we aim to identify discriminating panels of genes that are specific to, not only enriched in, individual cell types. To efficiently explore the vast space of possible marker panels, leverage the large number of cells often sequenced, and overcome zero-inflation in scRNA-seq data, we propose viewing marker gene panel selection as a variation of the “minimal set-covering problem” in combinatorial optimization. Using scRNA-seq data from blood and brain tissue, we show that this new method, CellCover, performs as good or better than DE and other methods in defining cell-type discriminating gene panels, while reducing gene redundancy and capturing cell-class-specific signals that are distinct from those defined by DE methods. Transfer learning experiments across mouse, primate, and human data demonstrate that CellCover identifies markers of conserved cell classes in neocortical neurogenesis, as well as developmental progression in both progenitors and neurons. Exploring markers of human outer radial glia (oRG, or basal RG) across mammals, we show that transcriptomic elements of this key cell type in the expansion of the human cortex likely appeared in gliogenic precursors of the rodent before the full program emerged in neurogenic cells of the primate lineage. We have assembled the public datasets we use in this report within the NeMO Analytics multi-omic data exploration environment [], where the expression of individual genes ( and ) and marker gene panels (, , , and ) can be freely explored without coding expertise. CellCover is available in and .

  PublisherOA PDFDOI

• Label-free selection of marker genes in single-cell and spatial transcriptomics with geneCover

  Genome Research · 2025-11-12 · 2 citations

  preprintSenior author

  The selection of marker gene panels is critical for capturing the cellular and spatial heterogeneity in the expanding atlases of single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics data. Most current approaches to marker gene selection operate in a label-based framework, which is inherently limited by its dependency on predefined cell type labels or clustering results. In contrast, existing label-free methods often struggle to identify genes that characterize rare cell types or subtle spatial patterns, and they frequently fail to scale efficiently with large data sets. Here, we introduce geneCover, a label-free combinatorial method that selects an optimal panel of minimally redundant marker genes based on gene-gene correlations. Our method demonstrates excellent scalability to large data sets and identifies marker gene panels that capture distinct correlation structures across the transcriptome. This allows geneCover to distinguish cell states in various tissues of living organisms effectively, including those associated with rare or otherwise difficult-to-identify cell types. We evaluate the performance of geneCover across various scRNA-seq and spatial transcriptomics data sets, comparing it to other label-free algorithms to highlight its utility and potential in diverse biological contexts.

  PublisherDOI

• Shape Alignment via Allen-Cahn Nonlinear-Convection

  ArXiv.org · 2025-04-22

  preprintOpen access

  This paper demonstrates the impact of a phase field method on shape registration to align shapes of possibly different topology. It yields new insights into the building of discrepancy measures between shapes regardless of topology, which would have applications in fields of image data analysis such as computational anatomy. A soft end-point optimal control problem is introduced whose minimum measures the minimal control norm required to align an initial shape to a final shape, up to a small error term. The initial data is spatially integrable, the paths in control spaces are integrable and the evolution equation is a generalized convective Allen-Cahn. Binary images are used to represent shapes for the initial data. Inspired by level-set methods and large diffeomorphic deformation metric mapping, the controls spaces are integrable scalar functions to serve as a normal velocity and smooth reproducing kernel Hilbert spaces to serve as velocity vector fields. The existence of mild solutions to the evolution equation is proved, the minimums of the time discretized optimal control problem are characterized, and numerical simulations of minimums to the fully discretized optimal control problem are displayed. The numerical implementation enforces the maximum-bounded principle, although it is not proved for these mild solutions. This research offers a novel discrepancy measure that provides valuable ways to analyze diverse image data sets. Future work involves proving the existence of minimums, existence and uniqueness of strong solutions and the maximum bounded principle.

  PublisherOA PDFDOI

Recent grants

• Numerical Computation of Geodesics in the Framework of Metamorphosis

  NSF · $275k · 2010–2013

• FRG: The Geometry, Mechanics and Statistics of the Infinite-dimensional Manifold of Shapes

  NSF · $800k · 2005–2009

Frequent coauthors

• Michael I. Miller

  Discovery Institute

  112 shared

• Alain Trouvé

  École Normale Supérieure Paris-Saclay

  53 shared

• J. Tilak Ratnanather

  Johns Hopkins University

  31 shared

• Donald Geman

  Johns Hopkins University

  31 shared

• Susumu Mori

  Johns Hopkins University

  29 shared

• Sylvain Arguillère

  29 shared

• Nicolas Charon

  University of Houston

  21 shared

• Luigi Marchionni

  21 shared

Awards & honors

• Fellow of the Institute for Mathematical Statistics (2015)
• Fellow of the Society for Industrial and Applied Mathematics…