BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:SDSC-AI4Science seminar: A graph matching approach to tracking neu
 rons in freely-moving C. Elegans
DTSTART:20230111T160000
DTEND:20230111T170000
DTSTAMP:20260510T165013Z
UID:b347e9535e2350d26a77b9b56a54898d92bb24946f67344ca4f918f0
CATEGORIES:Conferences - Seminars
DESCRIPTION:Corinne Jones\, Sr. Data Scientist at SDSC\nWe are happy to an
 nounce the second seminar of the SDSC - AI4Science monthly seminar series.
 \n\nPlace:  BCH 2103 (or via zoom https://epfl.zoom.us/j/63741505372)\n\n
 Speaker: Corinne Jones\, Sr. Data Scientist at SDSC\n\nTitle: A Graph Matc
 hing Approach to Tracking Neurons in Freely-Moving C. elegans\n\n \n\nAbs
 tract: Recent advances in 3D microscopy allow for recording the neurons in
  freely-moving C. elegans at high frame rates. In order to be able to stud
 y the calcium activity in the neurons\, it is necessary to be able to trac
 k the individual neurons from frame to frame. However\, doing this by hand
  for tens of neurons in a single ten-minute recording requires more than a
  hundred hours. Moreover\, most methods proposed in the literature for tra
 cking neurons focus on immobilized or partially-immobilized worms and fail
  to generalize to the freely-moving-worm setting. In this talk I will pre
 sent an approach based on graph matching for tracking freely-moving C. ele
 gans in the setting where a subset of neurons are marked with red fluoresc
 ence. The approach will be demonstrated on three recordings. We find that 
 with two labeled frames we can typically track the neurons and pieces of n
 eurites with over 70% accuracy\, with more reliable annotations for the mo
 st distinctive neurons. This is joint work with the lab of Sahand Rahi and
  Guillaume Obozinski. \n\nThe SDSC - AI4Science seminar is co-organized m
 onthly by the EPFL AI4Science Initiative and the Swiss Data Science Center
  and focussing on projects in which data science\, statistics\, machine le
 arning and AI are applied to the sciences. Each seminar will feature a pre
 sentation of one applied project\, geared towards an audience with experti
 se in Data Science methods\, from the initial formulation of a research qu
 estion in science associated with sources of data\, to the model\, algorit
 hms and analyses produced. The presentation will be highlighting the choic
 es made\, the challenges encountered\, interesting technical questions and
  possible further developments. A number of the projects presented will be
  collaborative projects of the Swiss Data Science Center. One of the objec
 tives of the seminar is to foster exchanges between researchers working in
  methods and applied data science research in the sciences\, and to create
  new opportunities of collaborations.\n\nEach session will feature a talk 
 followed by a discussion with the audience\, to be continued over fingerfo
 od and drinks
LOCATION:https://epfl.zoom.us/j/63741505372
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR