Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Zitong, Pham, Chau, Wang, Siqi, Doron, Michael, Moshkov, Nikita, Plummer, Bryan A., Caicedo, Juan C.
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2310.19224
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909074631688192
author Chen, Zitong
Pham, Chau
Wang, Siqi
Doron, Michael
Moshkov, Nikita
Plummer, Bryan A.
Caicedo, Juan C.
author_facet Chen, Zitong
Pham, Chau
Wang, Siqi
Doron, Michael
Moshkov, Nikita
Plummer, Bryan A.
Caicedo, Juan C.
contents Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset (https://doi.org/10.5281/zenodo.7988357) and an evaluation API (https://github.com/broadinstitute/MorphEm.git) to facilitate objective comparisons in future research and applications.
format Preprint
id arxiv_https___arxiv_org_abs_2310_19224
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CHAMMI: A benchmark for channel-adaptive models in microscopy imaging
Chen, Zitong
Pham, Chau
Wang, Siqi
Doron, Michael
Moshkov, Nikita
Plummer, Bryan A.
Caicedo, Juan C.
Computer Vision and Pattern Recognition
Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset (https://doi.org/10.5281/zenodo.7988357) and an evaluation API (https://github.com/broadinstitute/MorphEm.git) to facilitate objective comparisons in future research and applications.
title CHAMMI: A benchmark for channel-adaptive models in microscopy imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.19224