Project

Back to overview

Domain Adaptation for Microscopy Imaging

English title Domain Adaptation for Microscopy Imaging
Applicant Fua Pascal
Number 166107
Funding scheme Project funding (Div. I-III)
Research institution Laboratoire de vision par ordinateur EPFL - IC - ISIM - CVLAB
Institution of higher education EPF Lausanne - EPFL
Main discipline Information Technology
Start/End 01.08.2016 - 31.08.2018
Approved amount 256'168.00
Show all

Keywords (3)

Computer Vision; Microscopy; Transfer Learning

Lay Summary (French)

Lead
Les techniques actuelles de microcopie tant optique qu’électronique peuvent fournir d’énormes quantités d’image à très haute résolution et leur traitement doit être automatisé. Les algorithmes utilisés pour ce faire reposent dans une très large mesure sur des techniques d’apprentissage statistique et requièrent des données d’entrainement qui doivent être extraites manuellement par des experts qui sont peu disponibles et dont le temps est précieux.
Lay summary
Dans ce projet, nous développerons donc des techniques pour le transfert de connaissances adaptées au domaine de la microscopie. Elles faciliteront le travail de ces experts et réduiront grandement la quantité d’effort qui leur sera demandé. Plus spécifiquement, nos méthodes seront utilisées pour exploiter ce qui aura été appris précédemment pour réentrainer les algorithmes de traitement d’image en n’utilisant qu’un minimum de nouvelles données. 
Direct link to Lay Summary Last update: 12.04.2016

Responsible applicant and co-applicants

Employees

Publications

Publication
A domain-adaptive two-stream U-Net for electron microscopy image segmentation
Bermudez-Chacon Roger, Marquez-Neila Pablo, Salzmann Mathieu, Fua Pascal (2018), A domain-adaptive two-stream U-Net for electron microscopy image segmentation, in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DCIEEE, Washington DC, USA.
Beyond the Pixel-Wise Loss for Topology-Aware Delineation
MosinskaAgata, Marquez NeilaPablo, KosinskiMateusz, FuaPascal (2018), Beyond the Pixel-Wise Loss for Topology-Aware Delineation, in Medical Image Computing and Computer Assisted Intervention, Granada, SpainSpringer International Publishing, Cham.
Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency
Glowacki Przemysaw, Pinheiro Miguel, Mosinska Agata, Türetken Engin, Lebrecht Daniel, Sznitman Raphael, Holtmaat Anthony, Kybic Jan, Fua Pascal (2018), Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency, in Transactions on Pattern Analysis and Machine Intelligence, 40(3), 755-761.
Active Learning and Proofreading for Delineation of Curvilinear Structures
MosinskaAgata, TarnawskiJakub, FuaPascal (2017), Active Learning and Proofreading for Delineation of Curvilinear Structures, in Medical Image Computing and Computer-Assisted Intervention, Springer, Quebec City, Canada.
Active Learning for Delineation of Curvilinear Structures Agata
Mosinska Agata, Sznitman Raphael, Głowacki Przemysław, Fua Pascal (2016), Active Learning for Delineation of Curvilinear Structures Agata, in Computer Vision and Pattern Recognition, IEEE, Las Vegas, NE, USA.
Scalable Unsupervised Domain Adaptation for Electron Microscopy
Bemudez Roger, Becker Carlos, Salzmann Matthieu, Fua Pascal (2016), Scalable Unsupervised Domain Adaptation for Electron Microscopy, in Medical Image Computing and Computer Assisted Intervention, MICCAI, Athens, Greece.

Collaboration

Group / person Country
Types of collaboration
Katholieke Universität Leuwen Belgium (Europe)
- in-depth/constructive exchanges on approaches, methods or results
- Publication
- Exchange of personnel
University of Geneva Switzerland (Europe)
- in-depth/constructive exchanges on approaches, methods or results
- Publication
- Exchange of personnel

Associated projects

Number Title Start Funding scheme
172500 Modeling People and their Clothes in Crowded Scenes 01.01.2018 Project funding (Div. I-III)
177237 Synergistic Approach to Capturing and Exploiting Microscopy Images 01.09.2018 Sinergia
170082 Unbiased Analysis of Excitatory Synaptic Connectivity in the Aging Cerebral Cortex 01.09.2017 Project funding (Div. I-III)
149866 Delineating Trees in Noisy 2D Images and 3D Image-Stacks 01.10.2013 Project funding (Div. I-III)
149866 Delineating Trees in Noisy 2D Images and 3D Image-Stacks 01.10.2013 Project funding (Div. I-III)

Abstract

Imaging modalities such as Electron and Light Microscopy can now deliver high-quality, high-resolution image stacks of neural structures. Manual and semi-automated segmentation or annotation tools are then used to extract structures of interest. However, while the ever growing mass of available imagery should help unlock the secrets of neural function, the required amounts of human intervention remain a major bottleneck. Therefore, there has been great interest in automating the annotation process and most state-of-the-art algorithms rely on Machine Learning.However, such algorithms still require significant amounts of manual annotation for training purposes. For everyday scenes, this can be done by crowd-sourcing. In microscopy, this is not an option because only experts whose time is scarce and precious can annotate them reliably. This is problematic because the data preparation processes tend to be complicated and not easily repeatable, which means that a classifier trained on one acquisition will not perform very well on a new one, even when using the same modality.In earlier work, we have investigated approaches that involve acquiring sufficient amounts of labeled training data after one specific image acquisition and then using it in conjunction with a small amount of additional labeled training data that can be acquired quickly after each subsequent one to retrain the classifiers. We have so far focused mostly on synapse detection and delineation of curvilinear structures. In the proposed project continuation, we intend to broaden the scope of this effort and to develop generally applicable Domain Adaptation that are generally applicable in the field of bio-medical image processing.
-