Scalable Unsupervised Domain Adaptation for Electron Microscopy

Bermúdez-Chacón, Róger; Becker, Carlos; Salzmann, Mathieu; Fua, Pascal

doi:10.1007/978-3-319-46723-8_38

Cited by 25 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ciompi et al (2010); Conjeti et al (2016) address differences between in vitro and in vivo ultrasound, where the absence/presence of blood flow causes a distribution shift. Bermúdez-Chacón et al (2016) focus on segmentation of cells in microscopy images of different parts of the brain, which results in heterogeneous appearances.…”

Section: Different Domains Same Taskmentioning

confidence: 99%

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Cheplygina

Bruijne

Pluim

2019

Medical Image Analysis

747

441

View full text Add to dashboard Cite

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research.

show abstract

Section: Different Domains Same Taskmentioning

confidence: 99%

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Cheplygina

Bruijne

Pluim

2019

Medical Image Analysis

747

441

View full text Add to dashboard Cite

show abstract

“…A useful notion of adjacency is for instance given by neighbouring frames in a video stream [11]. We either compute the coefficients of A based on the label maps, or based on results from template matching with NCC, similar to [1].…”

Section: Auxiliary Manifold Embeddingmentioning

confidence: 99%

Semi-supervised Deep Learning for Fully Convolutional Networks

Baur

Albarqouni

Navab

2017

Lecture Notes in Computer Science

105

View full text Add to dashboard Cite

Abstract. Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data for training. Recently, semisupervised deep learning has been intensively studied for standard CNN architectures. However, Fully Convolutional Networks (FCNs) set the state-of-the-art for many image segmentation tasks. To the best of our knowledge, there is no existing semi-supervised learning method for such FCNs yet. We lift the concept of auxiliary manifold embedding for semisupervised learning to FCNs with the help of Random Feature Embedding. In our experiments on the challenging task of MS Lesion Segmentation, we leverage the proposed framework for the purpose of domain adaptation and report substantial improvements over the baseline model.

show abstract

“…II. RELATED WORK Domain shift has been a long-standing problem in medical image analysis due to the common inter-scanner or crossmodality variations [21]- [24]. Deep domain adaptation has recently been an active research field to transfer knowledge learned from the source domain to the target data either in a supervised or unsupervised manner.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation

Chen

Dou

Chen

et al. 2020

IEEE Trans. Med. Imaging

336

185

View full text Add to dashboard Cite

Unsupervised domain adaptation has increasingly gained interest in medical image computing, aiming to tackle the performance degradation of deep neural networks when being deployed to unseen data with heterogeneous characteristics. In this work, we present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA), to effectively adapt a segmentation network to an unlabeled target domain. Our proposed SIFA conducts synergistic alignment of domains from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features by leveraging adversarial learning in multiple aspects and with a deeply supervised mechanism. The feature encoder is shared between both adaptive perspectives to leverage their mutual benefits via end-to-end learning. We have extensively evaluated our method with cardiac substructure segmentation and abdominal multi-organ segmentation for bidirectional crossmodality adaptation between MRI and CT images. Experimental results on two different tasks demonstrate that our SIFA method is effective in improving segmentation performance on unlabeled target images, and outperforms the state-of-the-art domain adaptation approaches by a large margin.

show abstract

Scalable Unsupervised Domain Adaptation for Electron Microscopy

Cited by 25 publications

References 17 publications

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Semi-supervised Deep Learning for Fully Convolutional Networks

Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation

Contact Info

Product

Resources

About