Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images

In this work, a Deep Learning-based machine vision model was devel- oped for the detection, segmentation and counting of Neural Progenitor Cell nuclei from fluorescence microscopy images. The cells were obtained from adult mice and cultivated in vitro, with cellular nuclei labeled using DAPI...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pérez, Gabriel, Russo, Claudia, Palumbo, María Laura, Moroni, Alejandro David
Formato: Documento de conferencia publishedVersion
Lenguaje:Inglés
Publicado: Springer Nature Switzerland AG 2025
Materias:
Instance segmentation
Deep Learning
Fluorescence Microscopy
Cell Nuclei
Acceso en línea:http://repositorio.unnoba.edu.ar/xmlui/handle/23601/905
Aporte de:
Re DI Repositorio Digital UNNOBA de Universidad Nacional del Noroeste de la Provincia de Buenos Aires
id I103-R405-23601-905
record_format dspace
spelling I103-R405-23601-9052025-02-05T12:08:29Z Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images Pérez, Gabriel Russo, Claudia Palumbo, María Laura Moroni, Alejandro David Instance segmentation Deep Learning Fluorescence Microscopy Cell Nuclei In this work, a Deep Learning-based machine vision model was devel- oped for the detection, segmentation and counting of Neural Progenitor Cell nuclei from fluorescence microscopy images. The cells were obtained from adult mice and cultivated in vitro, with cellular nuclei labeled using DAPI dye. Convolu- tional neural networks for instance segmentation, specifically the Mask R-CNN model with ResNet-50 and ResNet-101 backbones, were trained to recognize the nuclei, and their results were evaluated. Nuclei labeling was implemented semi- automatically, applying a Superpixel technique and then refining the segmentations from a manual process, also using a pre-trained model, which allowed to assem- ble a dataset of 66 images with 6392 labels in total. The results obtained with the Resnet-50 backbone show that there is an effectiveness of 98.6% for between the specialist count and model-predicted count, in addition to having an mAP50 of 98.0%. This approach has the potential to significantly reduce the time and effort required to analyze large image sets, which is especially useful in studies that require repetitive and detailed cellular analysis. Fil: Pérez, Gabriel. Universidad Nacional del Noroeste de la Provincia de Buenos Aires. Instituto de Investigación y Transferencia en Tecnología; Argentina. Fil: Russo, Claudia. Universidad Nacional del Noroeste de la Provincia de Buenos Aires. Instituto de Investigación y Transferencia en Tecnología; Argentina. Fil: Palumbo, María Laura. Universidad Nacional del Noroeste de la Provincia de Buenos Aires. Centro de Investigaciones Básicas y Aplicadas; Argentina. Fil: Moroni, Alejandro David. Universidad Nacional del Noroeste de la Provincia de Buenos Aires. Centro de Investigaciones Básicas y Aplicadas; Argentina. Con referato 2025-02-05T12:05:10Z 2025-02-05T12:05:10Z 2024-10-15 info:eu-repo/semantics/conferenceObject info:ar-repo/semantics/documento de conferencia info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/conferenceObject info:ar-repo/semantics/documento de conferencia info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/conferenceObject info:ar-repo/semantics/documento de conferencia info:eu-repo/semantics/publishedVersion Pérez, G., Russo, C., Palumbo, M. L., y Moroni, A. D. (2024). Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images. Cloud Computing, Big Data and Emerging Topics (JCC-BD&ET 2024) 978-3-031-70806-0 1865-0929 http://repositorio.unnoba.edu.ar/xmlui/handle/23601/905 eng https://doi.org/10.1007/978-3-031-70807-7 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-nc-nd/2.5/ar/ application/pdf application/pdf Springer Nature Switzerland AG Cloud Computing, Big Data and Emerging Topics (JCC-BD&ET 2024)
institution Universidad Nacional del Noroeste de la Provincia de Buenos Aires
institution_str I-103
repository_str R-405
collection Re DI Repositorio Digital UNNOBA
language Inglés
topic Instance segmentation
Deep Learning
Fluorescence Microscopy
Cell Nuclei
spellingShingle Instance segmentation
Deep Learning
Fluorescence Microscopy
Cell Nuclei
Pérez, Gabriel
Russo, Claudia
Palumbo, María Laura
Moroni, Alejandro David
Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
topic_facet Instance segmentation
Deep Learning
Fluorescence Microscopy
Cell Nuclei
description In this work, a Deep Learning-based machine vision model was devel- oped for the detection, segmentation and counting of Neural Progenitor Cell nuclei from fluorescence microscopy images. The cells were obtained from adult mice and cultivated in vitro, with cellular nuclei labeled using DAPI dye. Convolu- tional neural networks for instance segmentation, specifically the Mask R-CNN model with ResNet-50 and ResNet-101 backbones, were trained to recognize the nuclei, and their results were evaluated. Nuclei labeling was implemented semi- automatically, applying a Superpixel technique and then refining the segmentations from a manual process, also using a pre-trained model, which allowed to assem- ble a dataset of 66 images with 6392 labels in total. The results obtained with the Resnet-50 backbone show that there is an effectiveness of 98.6% for between the specialist count and model-predicted count, in addition to having an mAP50 of 98.0%. This approach has the potential to significantly reduce the time and effort required to analyze large image sets, which is especially useful in studies that require repetitive and detailed cellular analysis.
format Documento de conferencia
Documento de conferencia
publishedVersion
Documento de conferencia
Documento de conferencia
publishedVersion
Documento de conferencia
Documento de conferencia
publishedVersion
author Pérez, Gabriel
Russo, Claudia
Palumbo, María Laura
Moroni, Alejandro David
author_facet Pérez, Gabriel
Russo, Claudia
Palumbo, María Laura
Moroni, Alejandro David
author_sort Pérez, Gabriel
title Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
title_short Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
title_full Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
title_fullStr Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
title_full_unstemmed Deep Learning-Based Instance Segmentation of Neural Progenitor Cell Nuclei in Fluorescence Microscopy Images
title_sort deep learning-based instance segmentation of neural progenitor cell nuclei in fluorescence microscopy images
publisher Springer Nature Switzerland AG
publishDate 2025
url http://repositorio.unnoba.edu.ar/xmlui/handle/23601/905
work_keys_str_mv AT perezgabriel deeplearningbasedinstancesegmentationofneuralprogenitorcellnucleiinfluorescencemicroscopyimages
AT russoclaudia deeplearningbasedinstancesegmentationofneuralprogenitorcellnucleiinfluorescencemicroscopyimages
AT palumbomarialaura deeplearningbasedinstancesegmentationofneuralprogenitorcellnucleiinfluorescencemicroscopyimages
AT moronialejandrodavid deeplearningbasedinstancesegmentationofneuralprogenitorcellnucleiinfluorescencemicroscopyimages
_version_ 1850060797250633728

Ejemplares similares