1
|
Wiesner D, Suk J, Dummer S, Nečasová T, Ulman V, Svoboda D, Wolterink JM. Generative modeling of living cells with SO(3)-equivariant implicit neural representations. Med Image Anal 2024; 91:102991. [PMID: 37839341 DOI: 10.1016/j.media.2023.102991] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 08/20/2023] [Accepted: 10/02/2023] [Indexed: 10/17/2023]
Abstract
Data-driven cell tracking and segmentation methods in biomedical imaging require diverse and information-rich training data. In cases where the number of training samples is limited, synthetic computer-generated data sets can be used to improve these methods. This requires the synthesis of cell shapes as well as corresponding microscopy images using generative models. To synthesize realistic living cell shapes, the shape representation used by the generative model should be able to accurately represent fine details and changes in topology, which are common in cells. These requirements are not met by 3D voxel masks, which are restricted in resolution, and polygon meshes, which do not easily model processes like cell growth and mitosis. In this work, we propose to represent living cell shapes as level sets of signed distance functions (SDFs) which are estimated by neural networks. We optimize a fully-connected neural network to provide an implicit representation of the SDF value at any point in a 3D+time domain, conditioned on a learned latent code that is disentangled from the rotation of the cell shape. We demonstrate the effectiveness of this approach on cells that exhibit rapid deformations (Platynereis dumerilii), cells that grow and divide (C. elegans), and cells that have growing and branching filopodial protrusions (A549 human lung carcinoma cells). A quantitative evaluation using shape features and Dice similarity coefficients of real and synthetic cell shapes shows that our model can generate topologically plausible complex cell shapes in 3D+time with high similarity to real living cell shapes. Finally, we show how microscopy images of living cells that correspond to our generated cell shapes can be synthesized using an image-to-image model.
Collapse
Affiliation(s)
- David Wiesner
- Centre for Biomedical Image Analysis, Masaryk University, Brno, Czech Republic.
| | - Julian Suk
- Department of Applied Mathematics & Technical Medical Centre, University of Twente, Enschede, The Netherlands
| | - Sven Dummer
- Department of Applied Mathematics & Technical Medical Centre, University of Twente, Enschede, The Netherlands
| | - Tereza Nečasová
- Centre for Biomedical Image Analysis, Masaryk University, Brno, Czech Republic
| | - Vladimír Ulman
- IT4Innovations, VSB - Technical University of Ostrava, Ostrava, Czech Republic
| | - David Svoboda
- Centre for Biomedical Image Analysis, Masaryk University, Brno, Czech Republic
| | - Jelmer M Wolterink
- Department of Applied Mathematics & Technical Medical Centre, University of Twente, Enschede, The Netherlands.
| |
Collapse
|
2
|
Shetab Boushehri S, Essig K, Chlis NK, Herter S, Bacac M, Theis FJ, Glasmacher E, Marr C, Schmich F. Explainable machine learning for profiling the immunological synapse and functional characterization of therapeutic antibodies. Nat Commun 2023; 14:7888. [PMID: 38036503 PMCID: PMC10689847 DOI: 10.1038/s41467-023-43429-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 11/09/2023] [Indexed: 12/02/2023] Open
Abstract
Therapeutic antibodies are widely used to treat severe diseases. Most of them alter immune cells and act within the immunological synapse; an essential cell-to-cell interaction to direct the humoral immune response. Although many antibody designs are generated and evaluated, a high-throughput tool for systematic antibody characterization and prediction of function is lacking. Here, we introduce the first comprehensive open-source framework, scifAI (single-cell imaging flow cytometry AI), for preprocessing, feature engineering, and explainable, predictive machine learning on imaging flow cytometry (IFC) data. Additionally, we generate the largest publicly available IFC dataset of the human immunological synapse containing over 2.8 million images. Using scifAI, we analyze class frequency and morphological changes under different immune stimulation. T cell cytokine production across multiple donors and therapeutic antibodies is quantitatively predicted in vitro, linking morphological features with function and demonstrating the potential to significantly impact antibody design. scifAI is universally applicable to IFC data. Given its modular architecture, it is straightforward to incorporate into existing workflows and analysis pipelines, e.g., for rapid antibody screening and functional characterization.
Collapse
Affiliation(s)
- Sayedali Shetab Boushehri
- Institute of AI for Health, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany
- Institute of Computational Biology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany
- Technical University of Munich, Department of Mathematics, Munich, Germany
- Data & Analytics (D&A), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Munich, Germany
| | - Katharina Essig
- Large Molecule Research (LMR), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Munich, Germany
| | - Nikolaos-Kosmas Chlis
- Large Molecule Research (LMR), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Munich, Germany
| | - Sylvia Herter
- Roche Innovation Center Zurich, Roche Pharma Research and Early Development (pRED), Zurich, Switzerland
| | - Marina Bacac
- Roche Innovation Center Zurich, Roche Pharma Research and Early Development (pRED), Zurich, Switzerland
| | - Fabian J Theis
- Institute of Computational Biology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany
- Technical University of Munich, Department of Mathematics, Munich, Germany
| | - Elke Glasmacher
- Research and Early Development (RED), Roche Diagnostics Solutions, Roche Innovation Center Munich, Munich, Germany.
| | - Carsten Marr
- Institute of AI for Health, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany.
- Institute of Computational Biology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany.
| | - Fabian Schmich
- Data & Analytics (D&A), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Munich, Germany.
| |
Collapse
|
3
|
Hou W, Wei Y. Evaluating the resolution of conventional optical microscopes through point spread function measurement. iScience 2023; 26:107976. [PMID: 37822495 PMCID: PMC10562796 DOI: 10.1016/j.isci.2023.107976] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/13/2023] Open
Abstract
In the imaging process of conventional optical microscopy, the primary factor hindering microscope resolution is the energy diffusion of incident light, most directly described by the point spread function (PSF). Therefore, accurate calculation and measurement of PSF are essential for evaluating and enhancing imaging resolution. Currently, there are various methods to obtain PSFs, each with different advantages and disadvantages suitable for different scenarios. To provide a comprehensive analysis of PSF-obtaining methods, this study classifies them into four categories based on different acquisition principles and analyzes their advantages and disadvantages, starting from the propagation property of light in optical physics. Finally, two PSF-obtaining methods are proposed based on mathematical modeling and deep learning, demonstrating their effectiveness through experimental results. This study compares and analyzes these results, highlighting the practical applications of image deblurring.
Collapse
Affiliation(s)
- Weihan Hou
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China
| | - Yangjie Wei
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, College of Computer Science and Engineering, Northeastern University, Wenhua Street 3, Shenyang 110819, China
| |
Collapse
|
4
|
Cudic M, Diamond JS, Noble JA. Unpaired mesh-to-image translation for 3D fluorescent microscopy images of neurons. Med Image Anal 2023; 86:102768. [PMID: 36857945 DOI: 10.1016/j.media.2023.102768] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2022] [Revised: 01/18/2023] [Accepted: 02/08/2023] [Indexed: 02/12/2023]
Abstract
While Generative Adversarial Networks (GANs) can now reliably produce realistic images in a multitude of imaging domains, they are ill-equipped to model thin, stochastic textures present in many large 3D fluorescent microscopy (FM) images acquired in biological research. This is especially problematic in neuroscience where the lack of ground truth data impedes the development of automated image analysis algorithms for neurons and neural populations. We therefore propose an unpaired mesh-to-image translation methodology for generating volumetric FM images of neurons from paired ground truths. We start by learning unique FM styles efficiently through a Gramian-based discriminator. Then, we stylize 3D voxelized meshes of previously reconstructed neurons by successively generating slices. As a result, we effectively create a synthetic microscope and can acquire realistic FM images of neurons with control over the image content and imaging configurations. We demonstrate the feasibility of our architecture and its superior performance compared to state-of-the-art image translation architectures through a variety of texture-based metrics, unsupervised segmentation accuracy, and an expert opinion test. In this study, we use 2 synthetic FM datasets and 2 newly acquired FM datasets of retinal neurons.
Collapse
Affiliation(s)
- Mihael Cudic
- National Institutes of Health Oxford-Cambridge Scholars Program, USA; National Institutes of Neurological Diseases and Disorders, Bethesda, MD 20814, USA; Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK
| | - Jeffrey S Diamond
- National Institutes of Neurological Diseases and Disorders, Bethesda, MD 20814, USA
| | - J Alison Noble
- Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UK.
| |
Collapse
|
5
|
Jiao Y, Gu L, Jiang Y, Weng M, Yang M. Digitally predicting protein localization and manipulating protein activity in fluorescence images using 4D reslicing GAN. Bioinformatics 2023; 39:6827288. [PMID: 36373962 PMCID: PMC9805574 DOI: 10.1093/bioinformatics/btac719] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2022] [Revised: 09/28/2022] [Accepted: 11/13/2022] [Indexed: 11/16/2022] Open
Abstract
MOTIVATION While multi-channel fluorescence microscopy is a vital imaging method in biological studies, the number of channels that can be imaged simultaneously is limited by technical and hardware limitations such as emission spectra cross-talk. One solution is using deep neural networks to model the localization relationship between two proteins so that the localization of one protein can be digitally predicted. Furthermore, the input and predicted localization implicitly reflect the modeled relationship. Accordingly, observing the response of the prediction via manipulating input localization could provide an informative way to analyze the modeled relationships between the input and the predicted proteins. RESULTS We propose a protein localization prediction (PLP) method using a cGAN named 4D Reslicing Generative Adversarial Network (4DR-GAN) to digitally generate additional channels. 4DR-GAN models the joint probability distribution of input and output proteins by simultaneously incorporating the protein localization signals in four dimensions including space and time. Because protein localization often correlates with protein activation state, based on accurate PLP, we further propose two novel tools: digital activation (DA) and digital inactivation (DI) to digitally activate and inactivate a protein, in order to observing the response of the predicted protein localization. Compared with genetic approaches, these tools allow precise spatial and temporal control. A comprehensive experiment on six pairs of proteins shows that 4DR-GAN achieves higher-quality PLP than Pix2Pix, and the DA and DI responses are consistent with the known protein functions. The proposed PLP method helps simultaneously visualize additional proteins, and the developed DA and DI tools provide guidance to study localization-based protein functions. AVAILABILITY AND IMPLEMENTATION The open-source code is available at https://github.com/YangJiaoUSA/4DR-GAN. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Yang Jiao
- Department of Electrical and Computer Engineering, University of Nevada, Las Vegas, NV 89154, USA
| | - Lingkun Gu
- School of Life Sciences, University of Nevada, Las Vegas, NV 89154, USA
| | - Yingtao Jiang
- Department of Electrical and Computer Engineering, University of Nevada, Las Vegas, NV 89154, USA
| | - Mo Weng
- To whom correspondence should be addressed. or
| | - Mei Yang
- To whom correspondence should be addressed. or
| |
Collapse
|
6
|
Jenner AL, Smalley M, Goldman D, Goins WF, Cobbs CS, Puchalski RB, Chiocca EA, Lawler S, Macklin P, Goldman A, Craig M. Agent-based computational modeling of glioblastoma predicts that stromal density is central to oncolytic virus efficacy. iScience 2022; 25:104395. [PMID: 35637733 PMCID: PMC9142563 DOI: 10.1016/j.isci.2022.104395] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2021] [Revised: 03/18/2022] [Accepted: 04/08/2022] [Indexed: 11/26/2022] Open
Abstract
Oncolytic viruses (OVs) are emerging cancer immunotherapy. Despite notable successes in the treatment of some tumors, OV therapy for central nervous system cancers has failed to show efficacy. We used an ex vivo tumor model developed from human glioblastoma tissue to evaluate the infiltration of herpes simplex OV rQNestin (oHSV-1) into glioblastoma tumors. We next leveraged our data to develop a computational, model of glioblastoma dynamics that accounts for cellular interactions within the tumor. Using our computational model, we found that low stromal density was highly predictive of oHSV-1 therapeutic success, suggesting that the efficacy of oHSV-1 in glioblastoma may be determined by stromal-to-tumor cell regional density. We validated these findings in heterogenous patient samples from brain metastatic adenocarcinoma. Our integrated modeling strategy can be applied to suggest mechanisms of therapeutic responses for central nervous system cancers and to facilitate the successful translation of OVs into the clinic.
Collapse
Affiliation(s)
- Adrianne L. Jenner
- Department of Mathematics and Statistics, Université de Montréal, Montréal, QC, Canada
- Sainte-Justine University Hospital Research Centre, Montréal, QC, Canada
| | - Munisha Smalley
- Division of Engineering in Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | | | - William F. Goins
- Department of Microbiology and Molecular Genetics, University of Pittsburgh, Pittsburgh, PA, USA
| | - Charles S. Cobbs
- Ben and Catherine Ivy Center for Advanced Brain Tumor Treatment, Swedish Neuroscience Institute, Seattle, WA, USA
| | - Ralph B. Puchalski
- Ben and Catherine Ivy Center for Advanced Brain Tumor Treatment, Swedish Neuroscience Institute, Seattle, WA, USA
| | - E. Antonio Chiocca
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA
| | - Sean Lawler
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA
| | - Paul Macklin
- Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA
| | - Aaron Goldman
- Division of Engineering in Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Morgan Craig
- Department of Mathematics and Statistics, Université de Montréal, Montréal, QC, Canada
- Sainte-Justine University Hospital Research Centre, Montréal, QC, Canada
| |
Collapse
|
7
|
Lutton EJ, Collier S, Bretschneider T. A Curvature-Enhanced Random Walker Segmentation Method for Detailed Capture of 3D Cell Surface Membranes. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:514-526. [PMID: 33052849 DOI: 10.1109/tmi.2020.3031029] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
High-resolution 3D microscopy is a fast advancing field and requires new techniques in image analysis to handle these new datasets. In this work, we focus on detailed 3D segmentation of Dictyostelium cells undergoing macropinocytosis captured on an iSPIM microscope. We propose a novel random walker-based method with a curvature-based enhancement term, with the aim of capturing fine protrusions, such as filopodia and deep invaginations, such as macropinocytotic cups, on the cell surface. We tested our method on both real and synthetic 3D image volumes, demonstrating that the inclusion of the curvature enhancement term can improve the segmentation of the aforementioned features. We show that our method performs better than other state of the art segmentation methods in 3D images of Dictyostelium cells, and performs competitively against CNN-based methods in two Cell Tracking Challenge datasets, demonstrating the ability to obtain accurate segmentations without the requirement of large training datasets. We also present an automated seeding method for microscopy data, which, combined with the curvature-enhanced random walker method, enables the segmentation of large time series with minimal input from the experimenter.
Collapse
|
8
|
Shaga Devan K, Walther P, von Einem J, Ropinski T, A Kestler H, Read C. Improved automatic detection of herpesvirus secondary envelopment stages in electron microscopy by augmenting training data with synthetic labelled images generated by a generative adversarial network. Cell Microbiol 2020; 23:e13280. [PMID: 33073426 DOI: 10.1111/cmi.13280] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2020] [Revised: 10/01/2020] [Accepted: 10/14/2020] [Indexed: 12/16/2022]
Abstract
Detailed analysis of secondary envelopment of the herpesvirus human cytomegalovirus (HCMV) by transmission electron microscopy (TEM) is crucial for understanding the formation of infectious virions. Here, we present a convolutional neural network (CNN) that automatically recognises cytoplasmic capsids and distinguishes between three HCMV capsid envelopment stages in TEM images. 315 TEM images containing 2,610 expert-labelled capsids of the three classes were available for CNN training. To overcome the limitation of small training datasets and thus poor CNN performance, we used a deep learning method, the generative adversarial network (GAN), to automatically increase our labelled training dataset with 500 synthetic images and thus to 9,192 labelled capsids. The synthetic TEM images were added to the ground truth dataset to train the Faster R-CNN deep learning-based object detector. Training with 315 ground truth images yielded an average precision (AP) of 53.81% for detection, whereas the addition of 500 synthetic training images increased the AP to 76.48%. This shows that generation and additional use of synthetic labelled images for detector training is an inexpensive way to improve detector performance. This work combines the gold standard of secondary envelopment research with state-of-the-art deep learning technology to speed up automatic image analysis even when large labelled training datasets are not available.
Collapse
Affiliation(s)
| | - Paul Walther
- Central Facility for Electron Microscopy, Ulm University, Ulm, Germany
| | - Jens von Einem
- Institute of Virology, Ulm University Medical Center, Ulm, Germany
| | - Timo Ropinski
- Institute of Media Informatics, Ulm University, Ulm, Germany
| | | | - Clarissa Read
- Central Facility for Electron Microscopy, Ulm University, Ulm, Germany.,Institute of Virology, Ulm University Medical Center, Ulm, Germany
| |
Collapse
|