التفاصيل البيبلوغرافية
| العنوان: |
Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation |
| المؤلفون: |
Bonte, Thomas, Philbert, Maxence, Coleno, Emeline, Bertrand, Edouard, Imbert, Arthur, Walter, Thomas |
| المساهمون: |
Centre de Bioinformatique (CBIO), Mines Paris - PSL (École nationale supérieure des mines de Paris), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL), Cancer et génome: Bioinformatique, biostatistiques et épidémiologie d'un système complexe, Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut Curie Paris -Institut National de la Santé et de la Recherche Médicale (INSERM), Institut de génétique humaine (IGH), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM) |
| المصدر: |
ECCV 2022 proceedings (Bio-image computing workshop) ; https://hal.science/hal-03935104 ; ECCV 2022 proceedings (Bio-image computing workshop), ECCV 2022 proceedings (Bio-image computing workshop), 2023 |
| بيانات النشر: |
HAL CCSD |
| سنة النشر: |
2023 |
| المجموعة: |
Université de Montpellier: HAL |
| مصطلحات موضوعية: |
Segmentation, Transfer learning, Pretext task, In Silico Labeling, Fluorescence microscopy, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] |
| الوصف: |
International audience ; Deep learning provides us with powerful methods to perform nucleus or cell segmentation with unprecedented quality. However, these methods usually require large training sets of manually annotated images, which are tedious and expensive to generate. In this paper we propose to use In Silico Labeling (ISL) as a pretraining scheme for segmentation tasks. The strategy is to acquire label-free microscopy images (such as bright-field or phase contrast) along fluorescently labeled images (such as DAPI or CellMask). We then train a model to predict the fluorescently labeled images from the label-free microscopy images. By comparing segmentation performance across several training set sizes, we show that such a scheme can dramatically reduce the number of required annotations. |
| نوع الوثيقة: |
conference object |
| اللغة: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/arxiv/2301.03914; ARXIV: 2301.03914 |
| الاتاحة: |
https://hal.science/hal-03935104 |
| Rights: |
http://creativecommons.org/licenses/by-nc-sa/ |
| رقم الانضمام: |
edsbas.98A4711B |
| قاعدة البيانات: |
BASE |