🔍 Introduction and Goal 

The Cell Behavior Video Classification Challenge (CBVCC) is a challenge designed to develop/adapt computer vision methods for classifying videos capturing cell behavior through Intravital Microscopy (IVM).

IVM is a powerful imaging technique that allows for non-invasive visualization of biological processes in living animals. Platforms such as two-photon microscopes exploit multiple low-energy photons to deliver high-resolution, three-dimensional videos depicting tissues and cells deep within the body. IVM has been used to visualize a wide range of biological processes, including immune responses, cancer development, and neurovascular function. 

The primary goal of the CBVCC challenge is to create models that can accurately classify videos based on the movement patterns of cells. Specifically, the models should be able of:

  • Identifying videos where cells exhibit sudden changes in their direction of movement.
  • Distinguishing these from videos where cells show consistent, linear movement, stationary cells as well as from videos containing only background.

The CBVCC challenge aims to provide a platform for researchers to develop innovative methods for classifying IVM videos, potentially leading to new insights into biological processes.

 

👩‍🔬👨‍🔬 The CBVCC Challenge 

The CBVCC challenge will be open to researchers from all over the world. Participants will be asked to develop computational models to classify IVM videos. The models will be evaluated based on their accuracy to classify videos.

The challenge will be divided into two phases:

  • Phase 1: In the first phase, participants will be provided with a training dataset and a test dataset of IVM images and labels. They will use this data to develop and evaluate their models.
  • Phase 2: In the second phase, participants will submit their results obtained on a distinct test dataset of IVM images. The models will be ranked based on their performance on the test dataset.

The challenge results will be decided based on the performance of the Phase 2 submission. 

 

🏅 The Challenge timeline (first attempt) 

The CBVCC challenge will begin on October 1, 2024, and end on December 6, 2024. The timeline of the key events is organized as follows:

  • September 15th 2024 to September 30th 2024: Participants are invited to join the challenge by registering on the website. 
  • October 1th 2024: The train dataset will be published, officially launching the challenge.  Additionally, a validation leaderboard will be made available for participants. 
  • November 30th 2024: The test dataset will be released. 
  • December 6th 2024: The challenge will be closed, and results and winners will be announced. 

 

Dataset 

The CBVCC dataset consists of 2D video-patches extracted from IVM videos. These videos capture the behavior of regulatory T cells in the abdominal flank skin of mice undergoing a contact sensitivity response to the sensitizing hapten, oxazolone. The videos are acquired either 24 or 48 hours after the initial skin challenge with oxazolone. Each video sequence lasts for 30 minutes, with images captured at one-minute intervals, resulting in a total of 31 acquisitions per video.

The primary goal of this challenge is to classify the provided video-patches into two distinct categories:

  1. Video-patches where cells suddenly change their direction of movement (class 1): These videos contain cells that demonstrate sudden changes in their migratory paths.
  2. Video-patches without sudden changes in cell direction (class 0): These videos either show cells moving in a linear manner, remain stationary, or contain video with only the background and no visible cells.

The dataset comprises a total of 300 2D video-patches extracted from 48 different videos, representing both classes (n=180 class 0 and n=120 class 1). Each video-patch is a 2D projection along the z-axis of a 3D video sequence, carefully adjusted to a common contrast range to enhance the visibility of the biological processes. Additionally, all videos have been preprocessed to ensure a uniform pixel size of 0.8 µm. Video-patches are saved as RGB .avi files.

The dataset consists of 300 pairs of video-patches and their corresponding labels, divided as follows:

  • Training set: 210 video-patches (70%)
  • Phase 1 test set: 30 video-patches (10%)
  • Phase 2 test set: 60 video-patches (20%)

Each subset includes video patches extracted from different and independent IVM videos.

 

Evaluation

The evaluation metrics for the challenge are designed to comprehensively assess the models' performance in classifying video-patches. The metrics include:

  • Area Under the ROC Curve (AUC)
  • Sensitivity
  • Specificity
  • Balanced Accuracy

The final score will be calculated as:

score = 0.4*AUC + 0.2*(Precision+Recall+Balanced Accuracy)

The evaluation code will be made public later.

 

Rules of Participation

  • The data used to train algorithms may be restricted to the data provided by the challenge.
  • Participants must not manually annotate the test dataset to train a supervised model for phase 1 or 2 submissions.
  • All results will be made publicly available.
  • During the submission phase, participants will be asked to upload their model predictions (in terms of probabilities) and an abstract describing the methodology used (in Phase 2).
  • There is no monetary prize for the winners of the challenge.
  • Both AI-based and non-AI-based methods are allowed.

 

We will collaborate with participants to create a comprehensive journal article summarizing the key results and analyses from this challenge. Participants who submit valuable work are welcome to contribute to the publication, with up to three authors from each team being acknowledged.

In order for us to include you in our paper:

  • Please submit a detailed description of your solution with your final test phase submission.
  • You are welcome to submit additional paragraphs and figures about your submission via email (see the Contact info on the Organizers page).

Besides, we encourage all participants to independently submit their results without imposing any publication embargo.

 

👥 Organizers

  • Diego Ulisse Pizzagalli - Faculty of Biomedical Sciences, Università della Svizzera Italiana, Lugano, Switzerland
  • Rolf Krause - Euler Institute, Università della Svizzera Italiana, Lugano, Switzerland
  • Santiago Fernandez Gonzalez - Institute for research in biomedicine, Bellinzona, Switzerland
  • Raffaella Fiamma Cabini - Euler Institute, Università della Svizzera Italiana, Lugano, Switzerland
  • Elisa Palladino - Institute for research in biomedicine, Bellinzona, Switzerland
  • Enrico Moscatello - Euler Institute, Università della Svizzera Italiana, Lugano, Switzerland

Thank you for visiting IMMUNEMAP, a website created and hosted by the Università della Svizzera italiana (USI).
The IMMUNEMAP website is an academic project. The information stored on the IMMUNEMAP website shall be exploited for the sole purpose of academic research, and are not suitable for medical nor commercial use.
In order to access the contents of the IMMUNEMAP website you need to agree to be bound by the present Terms of Use as amended from time to time.
Please take the time to read these Terms of Use as they contain important information regarding your legal rights remedies and obligations.

By accessing the IMMUNEMAP website, you accept to abide these Terms of Use. You may browse, share, upload and download content.

Usage terms

Usage for research purposes is permitted upon citation of both the original work that generated data, and the authors with the accession number provided by IMMUNEMAP.

Ownership and License

All rights in any material content which you contribute to IMMUNEMAP website (i.e. videos, cell tracks, and textual annotations), are licensed by you to and through the IMMUNEMAP website under the Creative Commons license CC BY-NC-SA 4.0 (the “License”). The terms of the License are available under https://creativecommons.org/licenses/by-nc-sa/4.0/

Users uploading and downloading material to/from IMMUNEMAP website implicitly accept to abide to the terms of the License.

Disclaimer and Limitations of Liability

The IMMUNEMAP website, including namely the image, video, sound and text content, is provided on an “as is” and “as available” basis. USI will not provide any kind of support (including but not limited to technical support) to the IMMUNEMAP’s users.

To the extent permitted by law, you expressly agree that:

* You assume all risks associated with the use of the IMMUNEMAP website.

* USI takes no responsibilities and makes no warranties, either expressed or implied, of any kind regarding namely:

o accuracy, currency, completeness, reliability or usefulness of any content available on the IMMUNEMAP website;

o maintaining confidentiality of data and information transmitted through the IMMUNEMAP website;

o merchantability, quality, fitness for a particular purpose of the IMMUNEMAP website and any of its content;

o non-infringement of any third parties rights (including but not limited to intellectual property rights);

o absence of defects, viruses, or malwares (namely such as worms or Trojan horses) that may interfere with or damage the operations of a computer system or cause the stealing of data;

o non-interruption or error-free of the IMMUNEMAP website.

* You shall take your own precautions to ensure that whatever action related to the use of the IMMUNEMAP website is free of defects, viruses or malwares (namely such as worms or Trojan horses) that may interfere with or damage the operations of a computer system or cause the stealing of data. In no case, USI shall be liable for damage to your computer system and/or private equipment. USI excludes any liability to any person for loss, cost, expense, claim or damage of any kind arising from or relating in any way to any access to or use of the IMMUNEMAP website.

USI is only acting as the host of the IMMUNEMAP website and does not control in any respect any content hosted like, but not limited to, video, data, text and information.

The IMMUNEMAP website may host link to third parties services for the sole purpose of convenience, but in no way USI is related to such service provider.

Indemnity

To the maximum extent permitted by law, you shall indemnify USI from and against any claims, losses, liabilities, costs, expenses and damages of any kind whatsoever and howsoever, directly or indirectly arising out of or in connection with these Terms of Use or your access to or use of the IMMUNEMAP website, including liability arising in connection with your breach of these Terms of Use.

Termination

USI may for any reason or for no reason at all, without liability to you or anyone else, terminate your account or your access to the IMMUNEMAP website or discontinue the IMMUNEMAP website itself. USI will notify you in written form via email upon the decision.

Privacy

Cookies are used by the IMMUNEMAP website in order to remember your search settings. Some cookies persist after you exit the browser. Cookies are never used for either identification or tracking purposes.

Applicable law

These Terms of Use shall be governed by and be interpreted in accordance the laws of Switzerland.

Any dispute arising from the application, interpretation or performance of these Terms of Use shall be submitted to the exclusive jurisdiction of the competent Courts of Lugano, Switzerland.

Final Provisions

If any provision of these Terms of Use shall be held unenforceable, the remaining provisions shall remain in full force.

These Terms of Use are immediately effective.

These Terms of Use may be amended from time to time. Registered uses will be notified in writing via email about eventual changes.


By your use of the IMMUNEMAP website, you accept to be bound to these Terms of Use as amended.

API Documentation

These are the main APIs to interface with immunemap. Base URL is https://api.immunemap.org/

  • GET​/acquisition​/{id}
    function to get an Acquisition by Acquisition ID
  • GET​/acquisition​/video​/{video}
    function to get an Acquisition by video ID
  • GET​/video​/{video}
    function to get a video by Video ID
  • GET​/video​/acquisition​/{acquisition}
    function to get a video by Acquisition ID
  • GET​/video​/{video}​/tracks
    function to get a video tracks by Video ID
  • GET​/video​/​{video}/preview
    function to get the video preview file

 More details below.

Acquisition API Documentation

GET /acquisition/{id}

This endpoint allows you to retrieve information about a specific Acquisition entity by its unique identifier.

Resource URL

https://api.immunemap.org/acquisition/10

 

Parameters

  • {id} (required, integer) - The unique identifier of the Acquisition entity to retrieve. The {id} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: application/json

Example Response:

json

{

"id":10

"experimental_group":8

"name":"10 hours post vaccination"

"sequence":1

"area":"Lymph node"

"magnification":25

"notes":"intravital imaging using two-photon microscopy, of NK cells (green) and macrophages (red) in the lymph node, into a Ncr1-GFP animal, after UV-PR8 virus injection (white). "cell_stainings":

"video":17

"video_details":

                  "DB_id":17

                  "id":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "uid":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "owner":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "author":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "location":"\/srv\/immunemap\/backend\/public\/uploads\/c5637a29-40ed-4d88-89d5-405c5b63a474.data"

                  "size":

                                   "width":555

                                   "height":555

                                   "slices":16

                                   "frames":30

                                   "spacing":[0.8,0.8,3]

                                   "fps":0.01702620332692

                                   "number_of_channels":4

                                   "channel_configuration":

                                   "deleted":false

                  "created":

                                   "date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"

                  "recorded":

                  "date":"2014-09-30 16:56:42.000000","timezone_type":3,"timezone":"UTC"

                  "notes":

                  "time_steps":

                  "annotations":[]

                  "uploaded_from":"10.25.11.22"

                  "uploaded_on":{"date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"}

                  "size":854447056,

                  "name":"15-27-16.ims"

                  "upload_status":4

"tags":

                  {"value":"collagen"}

                  {"value":"follicular-dendritic-cells"}

                  {"value":"influenza"}

                  {"value":"influenza-a"}

                  {"value":"macrophages"}

                  {"value":"natural-killer-cells"}

                  {"value":"vaccination"}]

"links":

"mouseId":"0"

"official_mouse_name":

"gender":"male"

 

}

 

Authorization

This endpoint requires the user to have the VIEW permission on the specified Acquisition entity. Users without this permission will receive a 403 Forbidden response.

Request Example

You can make a GET request to this endpoint to retrieve information about a specific Acquisition entity. Replace {id} with the actual identifier of the Acquisition you want to retrieve.

http

GET /acquisition/10

 

 

 

 

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Acquisition entity with the given ID does not exist, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the specified Acquisition entity, the API will return a 403 Forbidden

 

 

Acquisition by Video ID API Documentation

GET /acquisition/video/{videoId}

This endpoint allows you to retrieve Acquisitions associated with a specific Video by its unique identifier.

Resource URL

https://api.immunemap.org/acquisition/video/17

Parameters

  • {videoId} (required, integer) - The unique identifier of the Video entity to retrieve associated Acquisitions. The {videoId} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: application/json

Example Response:

json

{

"id":10

"experimental_group":8

"name":"10 hours post vaccination"

"sequence":1

"area":"Lymph node"

"magnification":25

"notes":"intravital imaging using two-photon microscopy, of NK cells (green) and macrophages (red) in the lymph node, into a Ncr1-GFP animal, after UV-PR8 virus injection (white). "cell_stainings":

"video":17

"video_details":

                  "DB_id":17

                  "id":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "uid":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "owner":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "author":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "location":"\/srv\/immunemap\/backend\/public\/uploads\/c5637a29-40ed-4d88-89d5-405c5b63a474.data"

                  "size":

                                   "width":555

                                   "height":555

                                   "slices":16

                                   "frames":30

                                   "spacing":[0.8,0.8,3]

                                   "fps":0.01702620332692

                                   "number_of_channels":4

                                   "channel_configuration":

                                   "deleted":false

                  "created":

                                   "date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"

                  "recorded":

                  "date":"2014-09-30 16:56:42.000000","timezone_type":3,"timezone":"UTC"

                  "notes":

                  "time_steps":

                  "annotations":[]

                  "uploaded_from":"10.25.11.22"

                  "uploaded_on":{"date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"}

                  "size":854447056,

                  "name":"15-27-16.ims"

                  "upload_status":4

"tags":

                  {"value":"collagen"}

                  {"value":"follicular-dendritic-cells"}

                  {"value":"influenza"}

                  {"value":"influenza-a"}

                  {"value":"macrophages"}

                  {"value":"natural-killer-cells"}

                  {"value":"vaccination"}]

"links":

"mouseId":"0"

"official_mouse_name":

"gender":"male"

 

}

 

Authorization

This endpoint requires the user to have the VIEW permission on the specified Video entity. Users without this permission will receive a 403 Forbidden response.

Request Example

You can make a GET request to this endpoint to retrieve Acquisitions associated with a specific Video. Replace {videoId} with the actual identifier of the Video you want to retrieve acquisitions for.

http

GET /acquisition/video/57

 

 

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Video entity with the given ID does not exist, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the specified Video entity, the API will return a 403 Forbidden

 

 

Video by Video ID API Documentation

GET /video/{videoId}

This endpoint allows you to retrieve information about a specific Video entity by its unique identifier.

Resource URL

bash

https://api.immunemap.org/video/17

 

Parameters

  • {videoId} (required, integer) - The unique identifier of the Video entity to retrieve. The {videoId} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: application/json

Example Response:

json

{

"DB_id":17

"id":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "uid":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "owner":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "author":"This email address is being protected from spambots. You need JavaScript enabled to view it.

"location":"\/srv\/immunemap\/backend\/public\/uploads\/c5637a29-40ed-4d88-89d5-405c5b63a474.data"

"video_details":

                  "size":

                                   "width":555

                                   "height":555

                                   "slices":16

                                   "frames":30

                                   "spacing":[0.8,0.8,3]

                                   "fps":0.01702620332692

                                   "number_of_channels":4

                                   "channel_configuration":

                                   "deleted":false

                  "created":

                                   "date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"

                  "recorded":

                  "date":"2014-09-30 16:56:42.000000","timezone_type":3,"timezone":"UTC"

                  "notes":

                  "time_steps":

                  "annotations":[]

                  "uploaded_from":"10.25.11.22"

                  "uploaded_on":{"date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"}

                  "size":854447056,

                  "name":"15-27-16.ims"

                  "upload_status":4

 

}

Authorization

This endpoint requires the user to have the VIEW permission on the specified Video entity. Users without this permission will receive a 403 Forbidden response.

Request Example

You can make a GET request to this endpoint to retrieve information about a specific Video entity. Replace {videoId} with the actual identifier of the Video you want to retrieve.

http

GET /video/17

 

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Video entity with the given ID does not exist, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the specified Video entity, the API will return a 403 Forbidden

 

 

 

Video by Acquisition ID API Documentation

GET video/acquisition/{acquisitionId}

This endpoint allows you to retrieve the Video associated with a specific Acquisition entity by its unique identifier.

Resource URL

https://api.immunemap.org/video/acquisition/10

Parameters

  • {acquisitionId} (required, integer) - The unique identifier of the Acquisition entity for which you want to retrieve the associated Video. The {acquisitionId} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: application/json

Example Response:

json

{

"DB_id":17

"id":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "uid":"37AXXPYHHN80XBCD4D57ENTKFA"

                  "owner":"This email address is being protected from spambots. You need JavaScript enabled to view it."

                  "author":"This email address is being protected from spambots. You need JavaScript enabled to view it.

"location":"\/srv\/immunemap\/backend\/public\/uploads\/c5637a29-40ed-4d88-89d5-405c5b63a474.data"

"video_details":

                  "size":

                                   "width":555

                                   "height":555

                                   "slices":16

                                   "frames":30

                                   "spacing":[0.8,0.8,3]

                                   "fps":0.01702620332692

                                   "number_of_channels":4

                                   "channel_configuration":

                                   "deleted":false

                  "created":

                                   "date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"

                  "recorded":

                  "date":"2014-09-30 16:56:42.000000","timezone_type":3,"timezone":"UTC"

                  "notes":

                  "time_steps":

                  "annotations":[]

                  "uploaded_from":"10.25.11.22"

                  "uploaded_on":{"date":"2022-03-10 14:38:37.000000","timezone_type":3,"timezone":"UTC"}

                  "size":854447056,

                  "name":"15-27-16.ims"

                  "upload_status":4

 

}

 

Authorization

This endpoint requires the user to have the VIEW permission on the associated Video entity. Users without this permission will receive a 403 Forbidden response.

Request Example

You can make a GET request to this endpoint to retrieve the Video associated with a specific Acquisition entity. Replace {acquisitionId} with the actual identifier of the Acquisition entity for which you want to retrieve the associated Video.

http

GET video/acquisition/10

 

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Acquisition entity with the given ID does not exist or does not have an associated Video, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the associated Video entity, the API will return a 403 Forbidden

 

 

Video Tracks by Video ID API Documentation

GET /video/{videoId}/tracks

This endpoint allows you to retrieve the tracks associated with a specific Video entity by its unique identifier.

Resource URL

https://api.immunemap.org/video/17/tracks

Parameters

  • {videoId} (required, integer) - The unique identifier of the Video entity for which you want to retrieve the associated tracks. The {videoId} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: application/json

Example Response:

json

{

"id":44639

"label":"15-27-16_1ime0000_ct1.csv_0"

"color":"#FFFF00"

"author":6

"video":17

"date":{"date":"2022-06-29 00:00:00.000000","timezone_type":3,"timezone":"UTC"}

"points":[[0,6.5,459.5,1],[1,3.25,463.25,1],[2,4.25,467.75,1],[3,3.25,478.5,1],[4,3,479.25,1]]

"cellTypeObject":null

"cellTypeName":"NK cells"

 

}

Authorization

This endpoint requires the user to have the VIEW permission on the specified Video entity. Users without this permission will receive a 403 Forbidden response.

 

Request Example

You can make a GET request to this endpoint to retrieve the tracks associated with a specific Video entity. Replace {videoId} with the actual identifier of the Video for which you want to retrieve tracks.

http

GET /video/17/tracks

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Video entity with the given ID does not exist, or it does not have associated tracks, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the specified Video entity, the API will return a 403 Forbidden

 

 

 

Video Preview File API Documentation

GET /video/{videoId}/preview

This endpoint allows you to retrieve the preview file of a specific Video entity by its unique identifier.

Resource URL

https://api.immunemap.org/video/17/preview

Parameters

  • {videoId} (required, integer) - The unique identifier of the Video entity for which you want to retrieve the preview file. The {videoId} must be a positive integer.

Response

  • HTTP Status Code: 200 OK
  • Content Type: video/mp4 (MPEG-4 video file)

Authorization

This endpoint requires the user to have the VIEW permission on the specified Video entity. Users without this permission will receive a 403 Forbidden response.

Request Example

You can make a GET request to this endpoint to retrieve the preview file of a specific Video entity. Replace {videoId} with the actual identifier of the Video for which you want to retrieve the preview file. You can also include the forceCreate query parameter if needed.

http

GET /video/17/preview

 

 

Response

If the request is successful, you will visualize a video player with the preview.

Error Responses

  • HTTP Status Code: 404 Not Found
    If the specified Video entity with the given ID does not exist, the API will return a 404 Not Found
  • HTTP Status Code: 403 Forbidden
    If the user does not have the VIEW permission on the specified Video entity, the API will return a 403 Forbidden
  • HTTP Status Code: 500 Internal Server Error
    If an error occurs during the retrieval or creation of the preview file, the API will return a 500 Internal Server Error

 

Artificial intelligence applied to intravital video microscopy, 3rd edition
13 - 15 November 2023

This workshop will cover theoretical and practical aspects regarding the application of A.I. -based methods for the analysis of cell motility from microscopy data, with a focus on immune cells observed in vivo. Moreover, we will discuss the importance of Open Source and Open Data resources in image-driven immunological research.
The methods presented in the workshop can be applied also to other cell types and imaging modalities. A basic understanding of microscopy is recommended.
How: Best would be to attend in presence, with practical cases to be solved in small groups. We will provide data and tools. You have to bring your own laptop. You can also bring your own data to be analyzed with the help of the peers.
For those who cannot come to Lugano in person we will leave open the possibility to connect via Google meet, attending lectures and watching the demonstrations. However, interactions may be restricted.

Link to attend online https://meet.google.com/qiq-yuug-vif 

Where: USI Campus EST, Via La Santa 1, 6962 Lugano – Switzerland

Organizers:
Prof. Santiago Fernandez Gonzalez
Prof. Rolf Krause
Dr. Diego Ulisse Pizzagalli

Confirmed speakers:
Pau Carrillo Barbera (University of Edinburgh)
Raffaella Fiamma Cabini (University of Pavia & USI Lugano)
Diego Morone (IRB Bellinzona)
Santiago Fernandez Gonzalez (IRB Bellinzona)
Mariaclaudia Nicolai (USI Lugano)
Elisa Palladino (IRB Bellinzona)
Diego Ulisse Pizzagalli (USI Lugano)
Alain Pulfer (IRB Bellinzona)
Inge Wortel (Radboud University)

Contact: For questions do not hesitate to contact us at This email address is being protected from spambots. You need JavaScript enabled to view it.

DAY 1: November 13th. Introduction, intravital imaging and Open Data

Learning objectives. Understanding the applications and advantages of intravital microscopy / the importance of Open Data research / Practice with immunemap platform and other tools

09:00 - 10:00 Introduction - DUP
10:00 - 11:15 Principles of fluorescence and intravital microscopy – DM
11:15 - 11:30 Coffee break
11:30 - 12:30 Studying the immune system in vivo, surgical models and applications - SFG
12:30 - 14:00 Lunch Break
14:00 - 15:00 Open Data research, FAIR principles and Immunemap  DUP + EP
15:00 - 17:00 Practical session 1 in small groups: Reuse of datasets and Open source tools

DAY 2: November 14th: Analysis with tracking. 

Learning objectives. Understanding what can be extracted from IVM data using the classical image analysis pipeline (tracking and track measures), challenges and new perspectives.

09:00 - 09:45 Basic measures of cell motility and cell-to-cell interaction. DUP+MN
10:15 - 10:30 Advanced metrics of cell motility + introduction to CelltrackR. IW
10:30 - 10:45 Coffee break
10:45 - 12:30 Practical session 2: Exercises to quantify motility
12:30 - 14:00 Lunch Break
14:00 - 15:00 Tracking with FIJI/Trackmate – PCB
15:00 - 16:00 Practical session 3: Practice with FIJI and Trackmate
16.00 - 17.00 Deep learning based cellular action recognition (mock dissertation - AP)

DAY 3: November 15th: Analysis without tracking.

Learning objectives. Understanding how image processing and computer vision techniques can be applied to analyze IVM data without necessarily using of cell tracking

09:00 - 10:15 Image processing and supervised machine learning techniques to
                      - facilitate cell detection and tracking DUP+RFC
                      - quantify motility when it is impossible to track individual cells DUP
10:15 - 10:30 Coffee break
10:30 - 12:00 Unsupervised machine learning technique for
- cell segmentation RFC
- cell swarming analysis DUP
- identification of main motility patterns DUP
12:00 - 13:00 Lunch Break
13:00 - 14:00 Discussion: recent trends in computer vision methods
14:00 - 16:00 Practical session 3: Analyzing cell migration without tracking
16:10 - 17:00 Conclusion

PAST EDITIONS

Artificial intelligence applied to intravital microscopy of the immune system, 2nd edition 16 - 18 May 2022

This workshop will cover theoretical and practical aspects regarding the application of A.I. -based methods for the analysis of intravital imaging data.
We will focus on the migration and interaction of immune cells observed in vivo, explaining how to get accurate tracking analysis, or how to extract insights from videos without using cell tracking.
Moreover, we will discuss the importance of Open Source and Open Data resources in image-driven immunological research.
The topics and tools presented in this workshop can be applied also for other imaging modalities and cell types but a basic knowledge in microscopy is recommended.

How: Blend modality. Best would be to attend in presence, with practical cases to be solved in small groups. We will provide data and tools and can offer a few workstations to be used but is encouraged to bring your own laptop. You can also bring your own data to be analyzed. For those who cannot come to Bellinzona we will leave open the possibility to connect via Zoom and watch the demonstrations.

When: May 16th – 18th, optional excursion on May 19th

Where: Institute for Research in Biomedicine, Via Francesco Chiesa 5, CH-6500 Bellinzona (Switzerland) / or online on Zoom (we will do the possible to let you following, but consider that technical issues may arise for the practical sessions)
Registration: up to May 8th 2022 23:59 CEST at https://forms.gle/x3XqkdqG7PxMBVH56 15 places available, served on a first come first served basis. You will receive a confirmation via email.

Cost: Free of charge

Contact: For questions do not hesitate to contact us at This email address is being protected from spambots. You need JavaScript enabled to view it. with the subject of the email ai-ivm2022

Program is in CEST timezone. Program can be subjected to changes, here you will always find the most updated schedule.

DAY 1: May 16th. Introduction to intravital microscopy (IVM).

Learning objectives. Understanding the applications and advantages of intravital microscopy / Understanding the importance of Open Data research / Practice with the immunemap platform

08:45-09:15: Walk-in and welcome of participants

9:15-10:15: Introduction of the course and Ice-breaker activity (Pizzagalli DU)

10:15-11:15: Technical Introduction to IVM (Morone D)

11:15-11:30 Coffee break

11:30-12:30: Surgical models and biological applications of IVM (Virgilio T)

12:30-14:00: Lunch Break

14.00-14:25: Summary of the concepts presented during the morning, Q&A session (Pizzagalli DU)

14:30-15:15: Introduction to cell tracking and open data research (Pizzagalli DU)

15:15-15:45: Coffee break

15:45-16:00: Presentation of immunemap (Palladino E / Ceni K)

16:00-17:00: Practical session 1: Use of immunemap and open data resources (Palladino E / Ceni K / Thelen B)

 

DAY 2: May 17th: Analysis with tracking. 

Learning objectives. Understanding which type of information can be extracted from IVM data using the classical image analysis pipeline, challenges and new perspectives

9:00-10:30: Classical image analysis pipeline, artifacts, quality requirements (Pulfer A)

10:30-10:45 Coffee break

10:45-12:00: The relevance of cell tracking in life sciences, motility parameters (Pizzagalli DU)

12:30-14:00: Lunch Break

14.00-14:25: Summary of the concepts presented during the morning, Q&A session (Pizzagalli DU)

14:25-15:00: Practical session 2a, Facilitating automatic tracking using computer-assisted colocalization (Pizzagalli DU)

15:00-16:00: Practical session 2b, Analysis of motility measures and cell-to-cell interaction (Pizzagalli DU)

16:00-16:15 Coffee break

16:15-17:30: Practical session 2c, Manual tracking and crowd-based tracking using immunemap. Manual tracking in FIJI/Trackmate and Imaris on request. (Ceni K, Carrillo-Barbera P, Palladino E).

 

DAY 3: May 18th: Analysis without tracking.

Learning objectives. Understanding how image processing and computer vision techniques can be applied to analyze IVM data without the usage of cell tracking

9:00-10:30: From pixels to cell actions (Pizzagalli DU)

10:30-10:45 Coffee break

9:00-10:30: Recent trends in computer vision methods (Pulfer A)

12:30-14:00: Lunch Break

14.00-14:25: Summary of the concepts presented during the morning, Q&A session (Pizzagalli DU)

14:25-15:45: Practical session 3: Advanced analysis of cell migration (Motility heatmaps, Optical flow, Tracklet-based action recognition, Colocalization, Cell death detection, Swarm detection) (Pizzagalli DU, Pulfer A)

15:45-16:00: Coffee break

16:15-16:45: Practical session 4: Unsupervised machine learning to identify migration modalities (Pizzagalli DU)

16:45-17:00: Conclusion

 

DAY 4: May 19th: Social activity

09:00–12:00: Visit to the castles of Bellinzona

Organizers:
Dr. Santiago Fernandez Gonzalez - Institute for Research in Biomedicine (CH)

Dr. Diego Ulisse Pizzagalli - Institute for Research in Biomedicine and Euler Institute, USI (CH)

Tutors:
Dr. Pau Carrillo-Barbera – The University of Edinburgh (UK)

Kevin Ceni – Institute for Research in Biomedicine (CH)
Diego Morone – Institute for Research in Biomedicine (CH)
Elisa Palladino – Institute for Research in Biomedicine (CH)
Alain Pulfer – Institute for Research in Biomedicine and ETH Zurich (CH)
Benedikt Thelen – Euler institute (CH)

Dr. Tommaso Virgilio - Institute for Research in Biomedicine (CH)

 

 

---- MATERIAL FROM PREVIOUS EDITION (2021) ----

Description

This summer school covered theoretical and practical aspects regarding the analysis of immune cell migration and interaction, using intravital microscopy and new A.I.-based methods. We had 18 participants (4 from USI, 14 external), from 4 european countries including BSc, MSc, PhD students, postdocs and imaging specialists.

Organizers. Dr. Santiago Fernandez Gonzalez, Dr. Diego Ulisse Pizzagalli, dr. Pau Carrillo Barbera
Tutors. Diego Morone, Alain Pulfer, Kevin Ceni, Benedikt Thelen
Supported by. IRB PhD program    Cell Migration PhD program    USI - Biomedical PhD program    IMMUNEMAP consortia    Euler Institute

Program

DAY 1: June 14th. Introduction to intravital microscopy (IVM).

Learning objectives. Understanding the applications and advantages of intravital microscopy / Understanding the importance of Open Data research / Practice with the immunemap platform

Introduction and networking activity (Pizzagalli)

1

9:00 - 10:00

Physics of 2-photon intravital microscopy (Morone)

1

10:30 - 11:30

Intravital imaging of the immune system (Gonzalez)

1

11:45 - 12:45

Image formation / histograms / Properties of digital images (Barbera / Morone)

1

14:00 - 15:00

The role of Open Data and Open Source in biomedical research , FAIR principles and IMMUNEMAP project (Pizzagalli / Barbera)

1

15:10 - 15:45

FIJI introduction (Morone)

1

15:45 - 17:00

DAY 2: June 15th: Analysis with tracking. 

Learning objectives. Understanding which type of information can be extracted from IVM data using the classical image analysis pipeline, challenges and new perspectives

Exercise 1

  • Which histogram is saturated
  • Thresholding
  • Use pixel inspector

2

9:00 - 9:30

Image analysis pipeline, quantification of cell motility, dynamism, and interaction (Pizzagalli)

2

9:30-10:30

The possibilities of Machine Learning in IVM (Pizzagalli)

2

10:45-11:30

Excercise 2 (Morone / Pulfer / Barbera Pizzagalli)

  • cell detection (classical / Otsu etc)
  • Thresholding with TWS
  • stardist
  • trackmate
  • automatic tracking with trackmate
  • computation of measures: collective (i.e. preferential direction) and individual cell behavior (i.e. change of speed)

2

14:00 - 17:00

DAY 3: June 16th: Analysis without tracking.

Learning objectives. Understanding how image processing techniques working at pixel-level can be applied to analyze IVM data without the usage of cell tracking

Exercise: track-based measures on neutrophil chemotaxis

Exercise: migration differences between WT and KO cells in spleen

 

9:00 – 10:30

Discussion Exercise 1 (Pizzagalli)

Contact analysis in Exercise 1 (Pizzagalli)

Advanced analysis without tracking (of/recruitment) (Pizzagalli)

3

10:45 - 11:00

Image processing techniques (Pulfer)

3

11:15 - 12:15

Exercise 3

  • Quantify the recruitment in vessels
  • Analyze whole LN images with OF
  • Apply the bayes coloc plugin by Alain (cell-cell interaction)
  • Imaris workshop (tracking, coloc, heatmaps, and cell-cell interaction)

3

14:00 - 17:00

DAY 4: June 17th:  Beyond tracking.

Learning objectives. Understanding how computer vision methods for action recognition can be applied to analyze IVM data without the usage of cell tracking

Inside AI: neural networks and clustering (Pizzagalli)

4

9:00 – 10:00

Trends in computer vision: classic, deep learning, generative (Pulfer)

4

10:05 - 11:00

Action recognition applied to immune cells (Pizzagalli)

  • Review of motility patterns displayed by immune cells in vivo and their biological meaning
  • Application of action recognition to quantify neutrophil dynamics and migration morpho-phenotypes

4

11:15 - 12:15

Exercise 4 (Pulfer / Pizzagalli)

  • Usage of the apoptosis detection program (incl. challenge)
  • Discussion on the limits and potential usage of Deep Learning in IVM
  • Neutrophil swarm detection

4

14:00 - 16:00

Discussion on good practices for IVM analysis (Barbera + Pizzagalli)

4

16:15 - 17:00

DAY 5: June 18th: Workshop and conclusion

Workshop: analyze data by participants (Pizzagalli):

- Quantification of leukocyte migration within and outside blood vessels via track-based measures and pixel classification.

- Analysis of DCs – Macrophage interaction via supervised spectral unmixing, contact analysis, and bayesian colocalization.
- Quantification of neutrophil swarm dynamics via unsupervised machine learning.

5

9:00 - 12:00

Exam

5

14:00 - 15:00

Concluding remarks

5

15:30 - 16:30

 

Project partners

Immunemap is a collaborative project supported by a network of international laboratories willing at making 2-photon imaging data of the immune system FAIR (Findable, Accessible, Interoperable, Reusable).

 

  • Britta Engelhardt (Theodor Kocher Institute, University of Bern, Bern, Switzerland). The group of Prof. Engelhardt developed an extensive in vivo imaging biobank that includes 2P-IVM imaging of T cell interactions in the cervical spinal cord microvessels of mice suffering from experimental autoimmune encephalomyelitis. Prof. Engelhard has a solid career as a relevant world expert on imaging autoimmune diseases.
  • Cornelia Halin (ETH, Zurich, Switzerland). The group of Prof. Halin is specialized in the study of intravital microscopy observations of migratory T cells and dendritic cells in and around dermal lymphatic capillaries in murine skin. Since the establishment of her lab in ETH, Prof. Halin has published her innovative research in the most important journal in the field of immunology.
  • Wolfgang Kastenmuller (University of Bonn, Bonn, Germany). Prof. Kastenmuller directs a dynamic group that focuses on the characterization of the interactions between DC and CD8 and CD4 T cell subsets in the LN in response to different conditions. The Kastenmuller lab has significantly contributed to the field of immuno-imaging and has published his innovative imaging articles in top journals like Immunity or Nature Immunology
  • Andres Hidalgo (Centro Nacional de Investigaciones Cardiovasculares, Madrid, Spain). The group of Dr. Hidalgo is specialized in the study the migration mechanisms that lead the recruitment of inflammatory cells from the blood vessels following different insults. He has published his recent papers on neutrophil dynamics in journals like Cell or Science.
  • Matteo Iannacone (San Raffaele Research Institute, Milan, Italy). MD PhD Iannacone directs a group specialized in studying the activation of adaptive immune cells and immunopathology during viral infection and cancer. He has developed specific models to study the dynamics of T cells in the liver in response to viral infection. Iannaccone’s group has recently published novel research that regards liver imaging in the journal Cell.
  • Johannes Textor (Radboud University, Nijmegen, Netherlands). Dr. Johannes Textor leads the Computational Immunology group at Radboud University, employing simulation models, machine learning, and causal inference to study the adaptive immune system. Their research aims to understand immune responses to pathogens and tumors, informing immunological treatments. They develop Artificial Immune Systems to compare immune and nervous system information processing, investigating their distinct architectures and complementary roles. Collaborating with colleagues at Radboudumc's Tumor Immunology department, they provide computational support, advancing immunological research through diverse methodologies.

 

  • Thomas Murooka (University of Manitoba, Manitoba, Canada). The laboratory of Dr. Murooka specialized in the study of T cells and DC as well as their migration during HIV infection in lymphoid tissues. Additionally, they studied the effector and regulatory T cell behaviors during Leishmania major infection in mouse skin. During his career, Dr. Murooka have published high impact factor papers in journals like Nature.
  • Michael Carroll (Harvard Medical School, Boston, USA). The group of Prof. Carroll has made important contributions to the field of antigen trafficking and B cell biology. He has extensive experience characterizing the behavior of DC and B cells in different models including infectious diseases and autoimmune diseases. The group publishes their research in a regular base in the highest impact factor journals in the field including Nature, Science or Cell.

 

Free Joomla! templates by Engine Templates
We use cookies

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.