Lab meeting

10-03-2020

Lab meeting

10-03-2020

29th - 2nd

3rd

4th - 6th

Centre Broca Nouvelle-Aquitaine

Notes from the conference:

https://docs.google.com/document/d/15_PKAJcwZF_L4cAQujGqA64VdOS0JS7gCgi_G3ZcjbU/edit?usp=sharing

Taggathon

http://biii.eu/

https://test.biii.eu/

http://biii.eu/

https://test.biii.eu/

https://www.comulis.eu/correlation-software-porto2019

Sattelite
meeting

Sattelite meeting

• Machine learning for Microscopy
• Bioimage Analysis Facility Management

https://deepimagej.github.io/deepimagej/index.html

https://deepimagej.github.io/deepimagej/index.html

• Uses the Tensorflow Java API
• Easily run pre-trained models on ImageJ
• A community platform for models as if they were plugins
• Macro recordable
• CPU and GPU compatible
• Good way to make your network accessible to biologists

GPU cluster at Pasteur

• Contact: Dmitry Ershov
  https://research.pasteur.fr/en/member/dmitry-ershov/
• They use Slurm as workload manager.
  https://slurm.schedmd.com/
  Maybe it has better GPU support?
• Discussion about training in loop to find the best network architechture/parameters

Ilastik
https://www.ilastik.org/

• Pixel classifier with friendly interface
• Easy input from users
• Supports

  • Pixel classification

  • Object classification

  • Carving (segmentation in 3D)

  • Boundary based segmentation (Multicut)

  • Tracking

• 3 facilities joined the discussion
  Porto, Nantes and Zurich
• 3 different approaches:
  Free, Almost free, Expensive
• Good discussion, it's important feedback for our Image Facility

Bioimage analysis Facility management

Symposium

QuPath

https://qupath.github.io/

• For histopathology data, huge images (60Gb) that are represented in different resolutions.
  (google maps style)
   
• Cell detection and feature measurement.
  Has a classifier that can learn from user input annotation.
   
• From the public feedback, it’s widely used.

Piximi

https://github.com/piximi/application

• Open source app for object recognition, from the Broad institute and Carpenter lab
   
• It’s a deep learning cell classifier on a web application (piximi.app)
   
• The idea is to replace CellProfiler
   
• Really nice interface

Panel discussion

https://image.sc

F1000 Research

https://f1000research.com

• Immediate publication (after editorial review) and actual peer-review  post-publication

  • There’s a clear label on the paper during this waiting peer review period

  • Lots of different categories to publish

• Open peer review (reviewers always named)

  • Report of reviewers is accessible

• Peer review for the technical aspect, not the impact of research (PLoS like)

• All versions of the paper are accessible and citable

• Interactive figures with Plotly or Shiny apps

• Readers get notified if a new version of the paper they downloaded is available

Emma Lundberg

One of the responsibles for The human protein atlas and also the organization of the Kaggle competition for cell classification, that's finished and published now.

32 million classifications

70 working years

CLIJ - GPU support for Fiji

https://clij.github.io/clij-docs/

Spot detection example:

2h40 hours on CPU

11min on GPU

Kristin Branson

https://arxiv.org/pdf/1611.00094.pdf

• Deep learning model for tracking flies in videos
• Automated system analysed 400 000 flies
• All the acquired data allowed to create another DL model that simulates the social behavior fo synthetic flies

Conclusions

• Everything is Deep learning now. More than 90% of the image analysis conference was about DL.
   
• People talked a lot about a "Model Zoo". A single place where DL trained models can be downloaded. Tensor flow is, without doubt, the standard.
   
• image.sc is building strength, lots of developers are talking about it.
   
• Artificial Labeling is getting mainstream, especially with the industry software (Nikon, Zeiss, etc)

thanks!