Multi-scale Stochastic Generation of Labelled Microscopy Images for Neuron Segmentation

Meghane Decroocq, Binbin Xu, Katherine L Thompson-Peer, Adrian Moore, Henrik Skibbe
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:352-366, 2024.

Abstract

We introduce a novel method leveraging conditional generative adversarial networks (cGANs) to generate diverse, high-resolution microscopy images for neuron tracing model training. This approach addresses the challenge of limited annotated data availability, a significant obstacle in automating neuron dendrite tracing. Our technique utilizes a multi-scale cascade process to generate synthetic images from single neuron tractograms, accurately replicating the complex characteristics of real microscopy images, encompassing imaging artifacts and background structures. In experiments, our method generates diverse images that mimic the characteristics of two distinct neuron microscopy datasets, which were successfully used as training data in the segmentation task of real neuron images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-decroocq24a, title = {Multi-scale Stochastic Generation of Labelled Microscopy Images for Neuron Segmentation}, author = {Decroocq, Meghane and Xu, Binbin and Thompson-Peer, Katherine L and Moore, Adrian and Skibbe, Henrik}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {352--366}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/decroocq24a/decroocq24a.pdf}, url = {https://proceedings.mlr.press/v250/decroocq24a.html}, abstract = {We introduce a novel method leveraging conditional generative adversarial networks (cGANs) to generate diverse, high-resolution microscopy images for neuron tracing model training. This approach addresses the challenge of limited annotated data availability, a significant obstacle in automating neuron dendrite tracing. Our technique utilizes a multi-scale cascade process to generate synthetic images from single neuron tractograms, accurately replicating the complex characteristics of real microscopy images, encompassing imaging artifacts and background structures. In experiments, our method generates diverse images that mimic the characteristics of two distinct neuron microscopy datasets, which were successfully used as training data in the segmentation task of real neuron images.} }
Endnote
%0 Conference Paper %T Multi-scale Stochastic Generation of Labelled Microscopy Images for Neuron Segmentation %A Meghane Decroocq %A Binbin Xu %A Katherine L Thompson-Peer %A Adrian Moore %A Henrik Skibbe %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-decroocq24a %I PMLR %P 352--366 %U https://proceedings.mlr.press/v250/decroocq24a.html %V 250 %X We introduce a novel method leveraging conditional generative adversarial networks (cGANs) to generate diverse, high-resolution microscopy images for neuron tracing model training. This approach addresses the challenge of limited annotated data availability, a significant obstacle in automating neuron dendrite tracing. Our technique utilizes a multi-scale cascade process to generate synthetic images from single neuron tractograms, accurately replicating the complex characteristics of real microscopy images, encompassing imaging artifacts and background structures. In experiments, our method generates diverse images that mimic the characteristics of two distinct neuron microscopy datasets, which were successfully used as training data in the segmentation task of real neuron images.
APA
Decroocq, M., Xu, B., Thompson-Peer, K.L., Moore, A. & Skibbe, H.. (2024). Multi-scale Stochastic Generation of Labelled Microscopy Images for Neuron Segmentation. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:352-366 Available from https://proceedings.mlr.press/v250/decroocq24a.html.

Related Material