Charles Kervrann
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
Charles Kervrann has a total of 151 co-authors. Here are the top co-authors by number of shared publications:
- Cesar Augusto Valades-Cruz
Institute of Hydrobiology Chinese Academy of Sciences Wuhan China
9 shared publications - Jean Salamero
CNRS, Institut Curie, UMR 144, 12 rue Lhomond, 75005 Paris, France
8 shared publications Ludovic Leconte
Institute of Human Genetics, CNRS UMR9002 National Infrastructure France‐BioImaging Montpellier France
8 shared publicationsJean Salamero
Institut Pasteur de Montevideo Montevideo Uruguay
6 shared publications- Anaïs Badoual
Inria Center at University of Rennes, France, SAIRPICO Team, U1339 INSERM, Institut Curie Chemical Biology of Cancer Unit, Paris, France
5 shared publications Emmanuel Moebel
SAIRPICO Project‐Team, Inria Center at University of Rennes, Institut Curie, Cellular and Chemical Biology Unit (U1339 INSERM, UMR3666 CNRS) PSL Research University Rennes France
5 shared publications
Latest Publications
- Open Access
Deep Learning-Meets-Active Surfaces: A Unified Framework for Multi-Object Segmentation and Shape Analysis in 3D Fluorescence Microscopy
In this paper, we introduce Nagini3D, a 3D biological image segmentation method that hybridizes two high-performing yet highly complementary segmentation paradigms: deep learning-based approaches and snake-based methods. Our approach leverages both the high efficiency of data-driven techniques and the convenient shape representation provided by active surfaces, which proves highly practical for incorporating a priori knowledge as well as for the post-analysis of segmented objects. By considering a complete 3D volume, our method ensures segmentation consistency across all three dimensions, unlike many approaches that handle volumes in a slice-by-slice manner. Additionally, it theoretically enables the representation of any object with spherical topology, overcoming the limitations of common 3D methods that rely on object convexity assumptions. Furthermore, the continuous representation of objects allows for a resolution-independent description, facilitating the extraction of various geometric features of interest (e.g., local curvature, principal deformations). We demonstrate both the quality of the segmentation produced by our method and the richness of the accessible geometric features through an extensive set of experiments conducted on multiple real and simulated datasets, including objects with challenging geometries.
Open AccessDeep Learning-Meets-Active Surfaces: A Unified Framework for Multi-Object Segmentation and Shape Analysis in 3D Fluorescence Microscopy
In this paper, we introduce Nagini3D, a 3D biological image segmentation method that hybridizes two high-performing yet highly complementary segmentation paradigms: deep learning-based approaches and snake-based methods. Our approach leverages both the high efficiency of data-driven techniques and the convenient shape representation provided by active surfaces, which proves highly practical for incorporating a priori knowledge as well as for the post-analysis of segmented objects. By considering a complete 3D volume, our method ensures segmentation consistency across all three dimensions, unlike many approaches that handle volumes in a slice-by-slice manner. Additionally, it theoretically enables the representation of any object with spherical topology, overcoming the limitations of common 3D methods that rely on object convexity assumptions. Furthermore, the continuous representation of objects allows for a resolution-independent description, facilitating the extraction of various geometric features of interest (e.g., local curvature, principal deformations). We demonstrate both the quality of the segmentation produced by our method and the richness of the accessible geometric features through an extensive set of experiments conducted on multiple real and simulated datasets, including objects with challenging geometries.
- 6 July 2026
- Published by Wiley in Journal of Microscopy
BioImageIT: A novel python‐based architecture for reproducible bio‐image workflows
Recent advances in light microscopy have transformed the scale and complexity of biological imaging data, creating an urgent need for sophisticated computational pipelines capable of extracting meaningful biological insights. However, the current software ecosystem for bio‐image analysis remains highly fragmented, with researchers needing to integrate tools written in disparate programming languages and architectural paradigms. This fragmentation gives rise to ‘dependency hell’ and creates significant technical barriers for life scientists. We present the novel and flexible architecture of BioImageIT, a lightweight open‐source workflow management system designed to bridge the gap between advanced computational tools and end‐user bio‐image analysts. Built upon Python, BioImageIT has evolved into a dual interface architecture: a node‐based visual programming GUI alongside a comprehensive Python Application Programming Interface (API). The system features the Wetlands environment management system for automatic dependency resolution, and adopts pandas DataFrames as the universal data structure for inter‐node communication. BioImageIT enforces adherence to FAIR principles (Findable, Accessible, Interoperable, Reusable) throughout the analysis lifecycle, automatically capturing comprehensive metadata for every processing step. The architecture abstracts the underlying computational infrastructure, laying the groundwork for seamless scaling from local workstations to high‐performance computing (HPC) clusters—a capability currently under active development.
- 6 July 2026
- Published by Wiley in Journal of Microscopy
BioImageIT: A novel python‐based architecture for reproducible bio‐image workflows
Recent advances in light microscopy have transformed the scale and complexity of biological imaging data, creating an urgent need for sophisticated computational pipelines capable of extracting meaningful biological insights. However, the current software ecosystem for bio‐image analysis remains highly fragmented, with researchers needing to integrate tools written in disparate programming languages and architectural paradigms. This fragmentation gives rise to ‘dependency hell’ and creates significant technical barriers for life scientists. We present the novel and flexible architecture of BioImageIT, a lightweight open‐source workflow management system designed to bridge the gap between advanced computational tools and end‐user bio‐image analysts. Built upon Python, BioImageIT has evolved into a dual interface architecture: a node‐based visual programming GUI alongside a comprehensive Python Application Programming Interface (API). The system features the Wetlands environment management system for automatic dependency resolution, and adopts pandas DataFrames as the universal data structure for inter‐node communication. BioImageIT enforces adherence to FAIR principles (Findable, Accessible, Interoperable, Reusable) throughout the analysis lifecycle, automatically capturing comprehensive metadata for every processing step. The architecture abstracts the underlying computational infrastructure, laying the groundwork for seamless scaling from local workstations to high‐performance computing (HPC) clusters—a capability currently under active development.
- 16 June 2026
- Published by Wiley in Cytometry Part A
- Vol. 109 (7) , 485-499
Ensembling Unets for Rare Chromosomal Aberration Detection in Metaphase Images, Uncertainty Quantification, and Ionizing Radiation Dose Estimation
In biological dosimetry a radiation dose is estimated using the average number of chromosomal aberrations per peripheral blood lymphocytes. This analysis is still manually performed on 2D metaphase images depicting the 23 pairs of chromosomes because the false discovery rate of current automated detection systems is too high and variable because of sensitivity to small variations in image quality (chromosome spread, illumination variations …). Therefore, the current systems are only used to assist human experts. Designing more performant automatic and reliable chromosomal aberration detection systems has become of paramount importance to improve diagnosis speed and reduce human expertise time. Here, we propose a novel deep‐learning method for automatic rare chromosomal aberration detection and uncertainty quantification. We formulate the problem as a unique regression problem requiring the minimization of a sparsity‐promoting loss to reduce the false alarm rate. Furthermore, we select checkpoints at the end of each epoch during training to form a model ensemble. The resulting artificial experts are further analyzed to derive a consensus voting, similar to an agreement of human annotator rating, to provide trustworthy aberration detections and confidence intervals. A radiation dose curve is finally derived from deep learning‐assisted counting of dicentrics and fragments in metaphase images, in high agreement with the reference hand‐crafted curve in biological dosimetry with a promising dose estimation validation.
- 16 June 2026
- Published by Wiley in Cytometry Part A
- Vol. 109 (7) , 485-499
Ensembling Unets for Rare Chromosomal Aberration Detection in Metaphase Images, Uncertainty Quantification, and Ionizing Radiation Dose Estimation
In biological dosimetry a radiation dose is estimated using the average number of chromosomal aberrations per peripheral blood lymphocytes. This analysis is still manually performed on 2D metaphase images depicting the 23 pairs of chromosomes because the false discovery rate of current automated detection systems is too high and variable because of sensitivity to small variations in image quality (chromosome spread, illumination variations …). Therefore, the current systems are only used to assist human experts. Designing more performant automatic and reliable chromosomal aberration detection systems has become of paramount importance to improve diagnosis speed and reduce human expertise time. Here, we propose a novel deep‐learning method for automatic rare chromosomal aberration detection and uncertainty quantification. We formulate the problem as a unique regression problem requiring the minimization of a sparsity‐promoting loss to reduce the false alarm rate. Furthermore, we select checkpoints at the end of each epoch during training to form a model ensemble. The resulting artificial experts are further analyzed to derive a consensus voting, similar to an agreement of human annotator rating, to provide trustworthy aberration detections and confidence intervals. A radiation dose curve is finally derived from deep learning‐assisted counting of dicentrics and fragments in metaphase images, in high agreement with the reference hand‐crafted curve in biological dosimetry with a promising dose estimation validation.
- Open Access
- 14 October 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (10) , e1013556
Deep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy
Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-Net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescence Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 12000 events in 60 cells. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of our deep learning model. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep learning guided analysis of dynamic processes in live-cell imaging.
- 14 October 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (10) , e1013556
Open AccessDeep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy
Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-Net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescence Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 12000 events in 60 cells. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of our deep learning model. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep learning guided analysis of dynamic processes in live-cell imaging.
- Open Access
- 3 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Template Learning: Deep learning with domain randomization for particle picking in cryo-electron tomography
Cryo-electron tomography (cryo-ET) enables three-dimensional visualization of biomolecules and cellular components in their near-native state. A key challenge in cryo-ET data analysis is particle picking, often performed by template matching, which relies on cross-correlating tomograms with known structural templates. Current deep learning-based methods improve accuracy but require labor-intensive annotated datasets for supervised training. Here, we present Template Learning, a technique that combines deep learning accuracy with the convenience of training on biomolecular templates via domain randomization. Template Learning automates synthetic dataset generation, modeling molecular crowding, structural variability, and data acquisition variation, thereby reducing or eliminating the need for annotated experimental data. We show that models trained using Template Learning, and optionally fine-tuned with experimental data, outperform those trained solely on annotations. Furthermore, Template Learning provides higher precision and more uniform orientation detection than template matching, particularly for small non-spherical particles. Template Learning software is open-source, Python-based, and GPU/CPU parallelized.
- 3 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Open AccessTemplate Learning: Deep learning with domain randomization for particle picking in cryo-electron tomography
Cryo-electron tomography (cryo-ET) enables three-dimensional visualization of biomolecules and cellular components in their near-native state. A key challenge in cryo-ET data analysis is particle picking, often performed by template matching, which relies on cross-correlating tomograms with known structural templates. Current deep learning-based methods improve accuracy but require labor-intensive annotated datasets for supervised training. Here, we present Template Learning, a technique that combines deep learning accuracy with the convenience of training on biomolecular templates via domain randomization. Template Learning automates synthetic dataset generation, modeling molecular crowding, structural variability, and data acquisition variation, thereby reducing or eliminating the need for annotated experimental data. We show that models trained using Template Learning, and optionally fine-tuned with experimental data, outperform those trained solely on annotations. Furthermore, Template Learning provides higher precision and more uniform orientation detection than template matching, particularly for small non-spherical particles. Template Learning software is open-source, Python-based, and GPU/CPU parallelized.
- 17 May 2025
- Published by Springer Nature
- p. 255-268
Prediction of Parametric Surfaces for Multi-object Segmentation in 3D Biological Imaging
- 17 May 2025
- Published by Springer Nature
- p. 255-268
Prediction of Parametric Surfaces for Multi-object Segmentation in 3D Biological Imaging
- Open Access
- 26 February 2025
- Published by Springer Nature in Communications Biology
- Vol. 8 (1) , 1-17
DeepCristae, a CNN for the restoration of mitochondria cristae in live microscopy images
Mitochondria play an essential role in the life cycle of eukaryotic cells. However, we still don’t know how their ultrastructure, like the cristae of the inner membrane, dynamically evolves to regulate these fundamental functions, in response to external conditions or during interaction with other cell components. Although high-resolution fluorescent microscopy coupled with recently developed innovative probes can reveal this structural organization, their long-term, fast and live 3D imaging remains challenging. To address this problem, we have developed a CNN, called DeepCristae, to restore mitochondria cristae in low spatial resolution microscopy images. Our network is trained from 2D STED images using a novel loss specifically designed for cristae restoration. To efficiently increase the size of the training set, we also developed a random image patch sampling centered on mitochondrial areas. To evaluate DeepCristae, quantitative assessments are carried out using metrics we derived by focusing on the mitochondria and cristae pixels rather than on the whole image as usual. Depending on the conditions of use indicated, DeepCristae works well on broad microscopy modalities (Stimulated Emission Depletion (STED), Live-SR, AiryScan and LLSM). It is ultimately applied in the context of mitochondrial network dynamics during interaction with endo/lysosome membranes.
- 26 February 2025
- Published by Springer Nature in Communications Biology
- Vol. 8 (1) , 1-17
Open AccessDeepCristae, a CNN for the restoration of mitochondria cristae in live microscopy images
Mitochondria play an essential role in the life cycle of eukaryotic cells. However, we still don’t know how their ultrastructure, like the cristae of the inner membrane, dynamically evolves to regulate these fundamental functions, in response to external conditions or during interaction with other cell components. Although high-resolution fluorescent microscopy coupled with recently developed innovative probes can reveal this structural organization, their long-term, fast and live 3D imaging remains challenging. To address this problem, we have developed a CNN, called DeepCristae, to restore mitochondria cristae in low spatial resolution microscopy images. Our network is trained from 2D STED images using a novel loss specifically designed for cristae restoration. To efficiently increase the size of the training set, we also developed a random image patch sampling centered on mitochondrial areas. To evaluate DeepCristae, quantitative assessments are carried out using metrics we derived by focusing on the mitochondria and cristae pixels rather than on the whole image as usual. Depending on the conditions of use indicated, DeepCristae works well on broad microscopy modalities (Stimulated Emission Depletion (STED), Live-SR, AiryScan and LLSM). It is ultimately applied in the context of mitochondrial network dynamics during interaction with endo/lysosome membranes.
- Open Access
Deep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy
Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescent Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 60 cells/∼12000 events. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of ExoDeepFinder. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep-learning guided analysis of dynamic processes in live-cell imaging.
Open AccessDeep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy
Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescent Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 60 cells/∼12000 events. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of ExoDeepFinder. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep-learning guided analysis of dynamic processes in live-cell imaging.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 4600-4613
Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image ( a.k.a ., self-supervised or zero-shot) methods perform denoising solely based the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network-based techniques, while being much faster and fully interpretable.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 4600-4613
Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image ( a.k.a ., self-supervised or zero-shot) methods perform denoising solely based the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network-based techniques, while being much faster and fully interpretable.
- Open Access
Template Learning: Deep Learning with Domain Randomization for Particle Picking in Cryo-Electron Tomography
Cryo-electron tomography (cryo-ET) enables the three-dimensional visualization of biomolecules and cellular components in their near-native state. Particle picking, a crucial step in cryo-ET data analysis, is traditionally performed by template matching—a method utilizing cross-correlations with available biomolecular templates. Despite the effectiveness of recent deep learning-based particle picking approaches, their dependence on initial data annotation datasets for supervised training remains a significant limitation. Here, we propose a technique that combines the accuracy of deep learning particle identification with the convenience of the model training on biomolecular templates enabled through a tailored domain randomization approach. Our technique, named Template Learning, automates the simulation of training datasets, incorporating considerations for molecular crowding, structural variabilities, and data acquisition variations. This reduces or even eliminates the dependence of supervised deep learning on annotated experimental datasets. We demonstrate that models trained on simulated datasets, optionally fine-tuned on experimental datasets, outperform those exclusively trained on experimental datasets. Also, we illustrate that Template Learning used as an alternative to template matching, can offer higher precision and better orientational isotropy, especially for picking small non-spherical particles. Template Learning software is open-source, Python-based, and GPU and CPU parallelized.
Open AccessTemplate Learning: Deep Learning with Domain Randomization for Particle Picking in Cryo-Electron Tomography
Cryo-electron tomography (cryo-ET) enables the three-dimensional visualization of biomolecules and cellular components in their near-native state. Particle picking, a crucial step in cryo-ET data analysis, is traditionally performed by template matching—a method utilizing cross-correlations with available biomolecular templates. Despite the effectiveness of recent deep learning-based particle picking approaches, their dependence on initial data annotation datasets for supervised training remains a significant limitation. Here, we propose a technique that combines the accuracy of deep learning particle identification with the convenience of the model training on biomolecular templates enabled through a tailored domain randomization approach. Our technique, named Template Learning, automates the simulation of training datasets, incorporating considerations for molecular crowding, structural variabilities, and data acquisition variations. This reduces or even eliminates the dependence of supervised deep learning on annotated experimental datasets. We demonstrate that models trained on simulated datasets, optionally fine-tuned on experimental datasets, outperform those exclusively trained on experimental datasets. Also, we illustrate that Template Learning used as an alternative to template matching, can offer higher precision and better orientational isotropy, especially for picking small non-spherical particles. Template Learning software is open-source, Python-based, and GPU and CPU parallelized.