Adversarial Domain Adaptation for Cell Segmentation

Mohammad Minhazul Haq, Junzhou Huang
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:277-287, 2020.

Abstract

To successfully train a cell segmentation network in fully-supervised manner for a particular type of organ or cancer, we need the dataset with ground-truth annotations. However, high unavailability of such annotated dataset and tedious labeling process enforce us to discover a way for training with unlabeled dataset. In this paper, we propose a network named CellSegUDA for cell segmentation on the unlabeled dataset (target domain). It is achieved by applying unsupervised domain adaptation (UDA) technique with the help of another labeled dataset (source domain) that may come from other organs or sources. We validate our proposed CellSegUDA on two public cell segmentation datasets and obtain significant improvement as compared with the baseline methods. Finally, considering the scenario when we have a small number of annotations available from the target domain, we extend our work to CellSegSSDA, a semi-supervised domain adaptation (SSDA) based approach. Our SSDA model also gives excellent results which are quite close to the fully-supervised upper bound in target domain.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-haq20a, title = {Adversarial Domain Adaptation for Cell Segmentation}, author = {Haq, Mohammad Minhazul and Huang, Junzhou}, pages = {277--287}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/haq20a/haq20a.pdf}, url = {http://proceedings.mlr.press/v121/haq20a.html}, abstract = {To successfully train a cell segmentation network in fully-supervised manner for a particular type of organ or cancer, we need the dataset with ground-truth annotations. However, high unavailability of such annotated dataset and tedious labeling process enforce us to discover a way for training with unlabeled dataset. In this paper, we propose a network named CellSegUDA for cell segmentation on the unlabeled dataset (target domain). It is achieved by applying unsupervised domain adaptation (UDA) technique with the help of another labeled dataset (source domain) that may come from other organs or sources. We validate our proposed CellSegUDA on two public cell segmentation datasets and obtain significant improvement as compared with the baseline methods. Finally, considering the scenario when we have a small number of annotations available from the target domain, we extend our work to CellSegSSDA, a semi-supervised domain adaptation (SSDA) based approach. Our SSDA model also gives excellent results which are quite close to the fully-supervised upper bound in target domain.} }
Endnote
%0 Conference Paper %T Adversarial Domain Adaptation for Cell Segmentation %A Mohammad Minhazul Haq %A Junzhou Huang %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-haq20a %I PMLR %J Proceedings of Machine Learning Research %P 277--287 %U http://proceedings.mlr.press %V 121 %W PMLR %X To successfully train a cell segmentation network in fully-supervised manner for a particular type of organ or cancer, we need the dataset with ground-truth annotations. However, high unavailability of such annotated dataset and tedious labeling process enforce us to discover a way for training with unlabeled dataset. In this paper, we propose a network named CellSegUDA for cell segmentation on the unlabeled dataset (target domain). It is achieved by applying unsupervised domain adaptation (UDA) technique with the help of another labeled dataset (source domain) that may come from other organs or sources. We validate our proposed CellSegUDA on two public cell segmentation datasets and obtain significant improvement as compared with the baseline methods. Finally, considering the scenario when we have a small number of annotations available from the target domain, we extend our work to CellSegSSDA, a semi-supervised domain adaptation (SSDA) based approach. Our SSDA model also gives excellent results which are quite close to the fully-supervised upper bound in target domain.
APA
Haq, M.M. & Huang, J.. (2020). Adversarial Domain Adaptation for Cell Segmentation. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:277-287

Related Material