BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20241027T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28046.field_data.0@www.glad.uniroma1.it
DTSTAMP:20260405T093538Z
CREATED:20240413T194327Z
DESCRIPTION:Abstract:In fluorescence microscopy\, the capability to disting
 uish between various fluorophores is highly desirable and essential to per
 form multicolor imaging. The ability to discriminate between different flu
 orophores based on their temporal fingerprints\, which are independent of 
 their emission spectra but related to fluorescence lifetime information\, 
 is significantly advantageous. In fact\, exploiting temporal information\,
  would be possible to multiplex/demultiplex the fluorescence signal of spe
 ctrally overlapping fluorophores. Moreover\, the lifetime provides insight
 s into the underlying biological phenomena\, therefore would be useful to 
 estimate its value.Over the years\, several methods have emerged for disti
 nguishing fluorophores using either tempo- ral or spectral fingerprints. N
 otable techniques operating in the frequency domain include the phasor app
 roach [1] and SPLIT [2]. We introduce a deep learning approach designed to
  separate the signal contributions coming from two fluorophores\, potentia
 lly spectrally overlapping\, in time-resolved flu- orescence microscopy im
 ages. The proposed method leverages a CNN-based network based on both temp
 oral features and 2D spatial characteristics within the images. Since the 
 purpose of the network is to separate contributions from different fluorop
 hores and to estimate the lifetime values\, the neural network is divided 
 into two sections\, each separating one of the two different fluorescence 
 time decay components. We focus in enhancing the explainability of the neu
 ral network architecture incorporating the physical model\, rendering our 
 approach highly interpretable and enabling a deeper comprehension of the u
 nderlying mechanisms. This research paves the way for our comprehension of
  sub-cellular components and macro-molecular complexes by facilitating sim
 ultaneous labeling and imaging of diverse bio-molecules. The introduced de
 ep learning method effectively addresses spectral overlap challenges\, by 
 providing a more precise and adaptable analysis of fluorescence microscopy
  data using fluorescence lifetime. Short bio:Lisa Cuneo is a postdoctoral 
 researcher at the Italian Institute of Technology (IIT). She holds a a Mas
 ter's degree in Applied Mathematics and Ph.D. in Physics and Nanosciences 
 from the University of Genova\, Italy\, where her research focused on comp
 utational analysis of biomedical images by means of machine learning algor
 ithms and inverse problems techniques. Lisa's academic career has included
  visiting positions at prestigious institutions such as the University of 
 Cambridge and Aalto University\, where she honed her skills in computation
 al biology and MEG inverse problems respectively. 
DTSTART;TZID=Europe/Paris:20240415T103000
DTEND;TZID=Europe/Paris:20240415T103000
LAST-MODIFIED:20240415T065044Z
LOCATION:Room B203
SUMMARY:Lisa Cuneo: Explainable-by-design machine learning model for unmixi
 ng fluorescence signal based on fluorescence lifetime - Lisa Cuneo
URL;TYPE=URI:http://www.glad.uniroma1.it/node/28046
END:VEVENT
END:VCALENDAR