Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Few-shot microscopy image cell segmentation|
|Citation:||Lecture Notes in Artificial Intelligence, 2021 / Dong, Y., Ifrim, G., Mladenic, D., Saunders, C., VanHoecke, S. (ed./s), vol.12461, pp.139-154|
|Publisher Place:||Cham, Switzerland|
|Series/Report no.:||Lecture Notes in Computer Science; 12461|
|Conference Name:||Joint European Conference on Machine Learning and Knowledge Discover in Databases (ECML PKDD) (14 Sep 2020 - 18 Sep 2020 : virtual online)|
|Youssef Dawoud, Julia Hornauer, Gustavo Carneiro, Vasileios Belagiannis|
|Abstract:||Automatic cell segmentation in microscopy images works well with the support of deep neural networks trained with full supervision. Collecting and annotating images, though, is not a sustainable solution for every new microscopy database and cell type. Instead, we assume that we can access a plethora of annotated image data sets from different domains (sources) and a limited number of annotated image data sets from the domain of interest (target), where each domain denotes not only different image appearance but also a different type of cell segmentation problem. We pose this problem as meta-learning where the goal is to learn a generic and adaptable few-shot learning model from the available source domain data sets and cell segmentation tasks. The model can be afterwards fine-tuned on the few annotated images of the target domain that contains different image appearance and different cell type. In our meta-learning training, we propose the combination of three objective functions to segment the cells, move the segmentation results away from the classification boundary using cross-domain tasks, and learn an invariant representation between tasks of the source domains. Our experiments on five public databases show promising results from 1- to 10-shot meta-learning using standard segmentation neural network architectures.|
|Keywords:||Cell segmentation; Microscopy image; Few-shot learning|
|Rights:||© Springer Nature Switzerland AG 2021|
|Appears in Collections:||Aurora harvest 4|
Computer Science publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.