2024Martinez-Sanchez PolNet - Revision history

Amartinez at 12:01, 8 November 2024

2024-11-08T12:01:13Z

← Older revision		Revision as of 12:01, 8 November 2024
Line 3:		Line 3:
	A. Martinez-Sanchez, L. Lamm, M. Jasnin and H. Phelippeau, "Simulating the Cellular Context in Synthetic Datasets for Cryo-Electron Tomography," in IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3742-3754, Nov. 2024, doi: 10.1109/TMI.2024.3398401		A. Martinez-Sanchez, L. Lamm, M. Jasnin and H. Phelippeau, "Simulating the Cellular Context in Synthetic Datasets for Cryo-Electron Tomography," in IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3742-3754, Nov. 2024, doi: 10.1109/TMI.2024.3398401

	== Abstract == Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane-bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.		== Abstract ==

	~~== Keywords ==~~ Cryo-electron tomography, deep learning, image ~~processing~~, ~~scientific computation~~, synthetic ~~data generation~~		Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane-bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.

			== Keywords ==

	~~== Links == https://github.com/anmartinezs/polnet~~		Cryo-electron tomography, deep learning, image processing, scientific computation, synthetic data generation

	== Related software == IMOD, nnU-Net
			== Links ==

			https://github.com/anmartinezs/polnet

			== Related software ==

			IMOD, nnU-Net

			== Comments ==

			Python package for generating synthetic datasets of the cellular context for Cryo-Electron Tomography.

Amartinez: Python package for generating synthetic datasets of the cellular context for Cryo-Electron Tomography.

2024-11-08T12:00:41Z

Python package for generating synthetic datasets of the cellular context for Cryo-Electron Tomography.

← Older revision		Revision as of 12:00, 8 November 2024
Line 1:		Line 1:
	== Citation == A. Martinez-Sanchez, L. Lamm, M. Jasnin and H. Phelippeau, "Simulating the Cellular Context in Synthetic Datasets for Cryo-Electron Tomography," in IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3742-3754, Nov. 2024, doi: 10.1109/TMI.2024.3398401		== Citation ==

			A. Martinez-Sanchez, L. Lamm, M. Jasnin and H. Phelippeau, "Simulating the Cellular Context in Synthetic Datasets for Cryo-Electron Tomography," in IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3742-3754, Nov. 2024, doi: 10.1109/TMI.2024.3398401

	== Abstract == Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane-bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.		== Abstract == Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane-bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.

Amartinez: Python package for generating synthetic datasets of the cellular context for Cryo-Electron Tomography.

2024-11-08T12:00:06Z

Python package for generating synthetic datasets of the cellular context for Cryo-Electron Tomography.

New page

== Citation == A. Martinez-Sanchez, L. Lamm, M. Jasnin and H. Phelippeau, "Simulating the Cellular Context in Synthetic Datasets for Cryo-Electron Tomography," in IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3742-3754, Nov. 2024, doi: 10.1109/TMI.2024.3398401

== Abstract == Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane-bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.

== Keywords == Cryo-electron tomography, deep learning, image processing, scientific computation, synthetic data generation

== Links == https://github.com/anmartinezs/polnet

== Related software == IMOD, nnU-Net