Cargando…
Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images
To characterize the growth of brain organoids (BOs), cultures that replicate some early physiological or pathological developments of the human brain are usually manually extracted. Due to their novelty, only small datasets of these images are available, but segmenting the organoid shape automatical...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603975/ https://www.ncbi.nlm.nih.gov/pubmed/37893062 http://dx.doi.org/10.3390/biomedicines11102687 |
_version_ | 1785126724689723392 |
---|---|
author | Brémond Martin, Clara Simon Chane, Camille Clouchoux, Cédric Histace, Aymeric |
author_facet | Brémond Martin, Clara Simon Chane, Camille Clouchoux, Cédric Histace, Aymeric |
author_sort | Brémond Martin, Clara |
collection | PubMed |
description | To characterize the growth of brain organoids (BOs), cultures that replicate some early physiological or pathological developments of the human brain are usually manually extracted. Due to their novelty, only small datasets of these images are available, but segmenting the organoid shape automatically with deep learning (DL) tools requires a larger number of images. Light U-Net segmentation architectures, which reduce the training time while increasing the sensitivity under small input datasets, have recently emerged. We further reduce the U-Net architecture and compare the proposed architecture (MU-Net) with U-Net and UNet-Mini on bright-field images of BOs using several data augmentation strategies. In each case, we perform leave-one-out cross-validation on 40 original and 40 synthesized images with an optimized adversarial autoencoder (AAE) or on 40 transformed images. The best results are achieved with U-Net segmentation trained on optimized augmentation. However, our novel method, MU-Net, is more robust: it achieves nearly as accurate segmentation results regardless of the dataset used for training (various AAEs or a transformation augmentation). In this study, we confirm that small datasets of BOs can be segmented with a light U-Net method almost as accurately as with the original method. |
format | Online Article Text |
id | pubmed-10603975 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-106039752023-10-28 Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images Brémond Martin, Clara Simon Chane, Camille Clouchoux, Cédric Histace, Aymeric Biomedicines Article To characterize the growth of brain organoids (BOs), cultures that replicate some early physiological or pathological developments of the human brain are usually manually extracted. Due to their novelty, only small datasets of these images are available, but segmenting the organoid shape automatically with deep learning (DL) tools requires a larger number of images. Light U-Net segmentation architectures, which reduce the training time while increasing the sensitivity under small input datasets, have recently emerged. We further reduce the U-Net architecture and compare the proposed architecture (MU-Net) with U-Net and UNet-Mini on bright-field images of BOs using several data augmentation strategies. In each case, we perform leave-one-out cross-validation on 40 original and 40 synthesized images with an optimized adversarial autoencoder (AAE) or on 40 transformed images. The best results are achieved with U-Net segmentation trained on optimized augmentation. However, our novel method, MU-Net, is more robust: it achieves nearly as accurate segmentation results regardless of the dataset used for training (various AAEs or a transformation augmentation). In this study, we confirm that small datasets of BOs can be segmented with a light U-Net method almost as accurately as with the original method. MDPI 2023-09-30 /pmc/articles/PMC10603975/ /pubmed/37893062 http://dx.doi.org/10.3390/biomedicines11102687 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Brémond Martin, Clara Simon Chane, Camille Clouchoux, Cédric Histace, Aymeric Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title | Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title_full | Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title_fullStr | Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title_full_unstemmed | Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title_short | Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images |
title_sort | mu-net a light architecture for small dataset segmentation of brain organoid bright-field images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603975/ https://www.ncbi.nlm.nih.gov/pubmed/37893062 http://dx.doi.org/10.3390/biomedicines11102687 |
work_keys_str_mv | AT bremondmartinclara munetalightarchitectureforsmalldatasetsegmentationofbrainorganoidbrightfieldimages AT simonchanecamille munetalightarchitectureforsmalldatasetsegmentationofbrainorganoidbrightfieldimages AT clouchouxcedric munetalightarchitectureforsmalldatasetsegmentationofbrainorganoidbrightfieldimages AT histaceaymeric munetalightarchitectureforsmalldatasetsegmentationofbrainorganoidbrightfieldimages |