Matthew B. Smith
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Matthew B. Smith has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Agathe Chaigne
Cell Biology, Neurobiology and Biophysics, Department of Biology, Faculty of Science, Utrecht University, Padualaan, Utrecht 3584 CH, the Netherlands
1 shared publication - Anne F. J. Janssen
Department of Pharmacology, University of Cambridge, Tennis Court Road, Cambridge, CB2 1PD, United Kingdom
1 shared publication - Axel Behrens
Adult Stem Cell Laboratory, The Francis Crick Institute, London, UK
1 shared publication - Bram M. Bosch
University Medical Centre Utrecht
1 shared publication - Caspar T. H. Jonker
Genmab B.V.
1 shared publication Chris Dunsby
Photonics Group, Department of Physics, Imperial College London
1 shared publication
Latest Publications
- Open Access
UDIST: unsupervised disentanglement of shape and texture for multi-scale phenotypic profiling in 2D microscopy
Microscopy-based phenotypic profiling relies increasingly on autonomous, unsupervised feature extraction, yet no existing method explicitly separates shape from texture into dedicated and independent latent subspaces by architectural design. Therefore texture, encoding critical biological information such as protein distribution and intracellular organisation, remains inaccessible as an independent feature domain in standard unsupervised approaches. This represents a fundamental limitation that prevents unbiased phenotypic analysis across biological scales. Here we introduce UDIST (Unsupervised Disentanglement of Shape and Texture), a sequential dual variational autoencoder (VAE) framework that tackles this fundamental limitation by explicitly decoupling shape from texture into independent, non-overlapping latent subspaces at the single-object level. By training two VICReg-regularised VAEs on principal-axis-aligned objects, UDIST separates binary shape from continuous texture information into rotation-invariant feature spaces, enabling separate downstream analysis of both domains. We validated UDIST across biological scales, from nuclei and single cells to patient-derived intestinal organoids, using both fluorescence and brightfield imaging, revealing phenotypic differences previously hidden by morphological variation and enabling the independent analysis of shape and texture in downstream analyses including clustering and similarity measurements. UDIST provides a versatile, label-free, and unsupervised tool for multi-scale phenotypic profiling in high-content microscopy and screening.
Open AccessUDIST: unsupervised disentanglement of shape and texture for multi-scale phenotypic profiling in 2D microscopy
Microscopy-based phenotypic profiling relies increasingly on autonomous, unsupervised feature extraction, yet no existing method explicitly separates shape from texture into dedicated and independent latent subspaces by architectural design. Therefore texture, encoding critical biological information such as protein distribution and intracellular organisation, remains inaccessible as an independent feature domain in standard unsupervised approaches. This represents a fundamental limitation that prevents unbiased phenotypic analysis across biological scales. Here we introduce UDIST (Unsupervised Disentanglement of Shape and Texture), a sequential dual variational autoencoder (VAE) framework that tackles this fundamental limitation by explicitly decoupling shape from texture into independent, non-overlapping latent subspaces at the single-object level. By training two VICReg-regularised VAEs on principal-axis-aligned objects, UDIST separates binary shape from continuous texture information into rotation-invariant feature spaces, enabling separate downstream analysis of both domains. We validated UDIST across biological scales, from nuclei and single cells to patient-derived intestinal organoids, using both fluorescence and brightfield imaging, revealing phenotypic differences previously hidden by morphological variation and enabling the independent analysis of shape and texture in downstream analyses including clustering and similarity measurements. UDIST provides a versatile, label-free, and unsupervised tool for multi-scale phenotypic profiling in high-content microscopy and screening.
- Open Access
Active mesh and neural network pipeline for cell aggregate segmentation
Segmenting cells within cellular aggregates in 3D is a growing challenge in cell biology, due to improvements in capacity and accuracy of microscopy techniques. Here we describe a pipeline to segment images of cell aggregates in 3D. The pipeline combines neural network segmentations with active meshes. We apply our segmentation method to cultured mouse mammary duct organoids imaged over 24 hours with oblique plane microscopy, a high-throughput light-sheet fluorescence microscopy technique. We show that our method can also be applied to images of mouse embryonic stem cells imaged with a spinning disc microscope. We segment individual cells based on nuclei and cell membrane fluorescent markers, and track cells over time. We describe metrics to quantify the quality of the automated segmentation. Our segmentation pipeline involves a Fiji plugin which implement active meshes deformation and allows a user to create training data, automatically obtain segmentation meshes from original image data or neural network prediction, and manually curate segmentation data to identify and correct mistakes. Our active meshes-based approach facilitates segmentation postprocessing, correction, and integration with neural network prediction. Statement of significance In vitro culture of organ-like structures derived from stem cells, so-called organoids, allows to image tissue morphogenetic processes with high temporal and spatial resolution. Three-dimensional segmentation of cell shape in timelapse movies of these developing organoids is however a significant challenge. In this work, we propose an image analysis pipeline for cell aggregates that combines deep learning with active contour segmentations. This combination offers a flexible and efficient way to segment three-dimensional cell images, which we illustrate with by segmenting datasets of growing mammary gland organoids and mouse embryonic stem cells.
Open AccessActive mesh and neural network pipeline for cell aggregate segmentation
Segmenting cells within cellular aggregates in 3D is a growing challenge in cell biology, due to improvements in capacity and accuracy of microscopy techniques. Here we describe a pipeline to segment images of cell aggregates in 3D. The pipeline combines neural network segmentations with active meshes. We apply our segmentation method to cultured mouse mammary duct organoids imaged over 24 hours with oblique plane microscopy, a high-throughput light-sheet fluorescence microscopy technique. We show that our method can also be applied to images of mouse embryonic stem cells imaged with a spinning disc microscope. We segment individual cells based on nuclei and cell membrane fluorescent markers, and track cells over time. We describe metrics to quantify the quality of the automated segmentation. Our segmentation pipeline involves a Fiji plugin which implement active meshes deformation and allows a user to create training data, automatically obtain segmentation meshes from original image data or neural network prediction, and manually curate segmentation data to identify and correct mistakes. Our active meshes-based approach facilitates segmentation postprocessing, correction, and integration with neural network prediction. Statement of significance In vitro culture of organ-like structures derived from stem cells, so-called organoids, allows to image tissue morphogenetic processes with high temporal and spatial resolution. Three-dimensional segmentation of cell shape in timelapse movies of these developing organoids is however a significant challenge. In this work, we propose an image analysis pipeline for cell aggregates that combines deep learning with active contour segmentations. This combination offers a flexible and efficient way to segment three-dimensional cell images, which we illustrate with by segmenting datasets of growing mammary gland organoids and mouse embryonic stem cells.