BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:2DeteCT - A large 2D expandable\, trainable\, experimental Compute
 d Tomography dataset for machine learning - Maximilian Kiss\, Centrum Wisk
 unde &amp\; Informatica
DTSTART:20231115T130000Z
DTEND:20231115T140000Z
UID:TALK208015@talks.cam.ac.uk
CONTACT:Yuan Huang
DESCRIPTION:Recent research in computational imaging largely focuses on de
 veloping machine learning (ML) techniques for image reconstruction\, which
  requires large-scale training datasets consisting of measurement data and
  ground-truth images. However\, suitable experimental datasets for X-ray C
 omputed Tomography (CT) are scarce\, and methods are often developed and e
 valuated only on simulated data. We fill this gap by providing the communi
 ty with a versatile\, open 2D fan-beam CT dataset suitable for developing 
 ML techniques for a range of image reconstruction tasks. To acquire it\, w
 e designed a sophisticated\, semi-automatic scan procedure that utilizes a
  highly-flexible laboratory X-ray CT setup. A diverse mix of samples with 
 high natural variability in shape and density was scanned slice-by-slice (
 5\,000 slices in total) with high angular and spatial resolution and three
  different beam characteristics: A high-fidelity\, a low-dose and a beam-h
 ardening-inflicted mode. In addition\, 750 out-of-distribution slices were
  scanned with sample and beam variations to accommodate robustness and seg
 mentation tasks. We provide raw projection data\, reference reconstruction
 s and segmentations based on an open-source data processing pipeline.\n\n\
 nThe seminar will be held in a hybrid format. We strongly encourage you to
  participate in person at MR 11\, Centre of Mathematical Sciences\, CB3 0W
 A. \n\nAlternatively\, please join using the following Zoom link:\n\n*Join
  Zoom Meeting:* https://maths-cam-ac-uk.zoom.us/j/93331132587?pwd=MlpReFY3
 MVpyVThlSi85TmUzdTJxdz09
LOCATION:Centre for Mathematical Sciences\, MR11
END:VEVENT
END:VCALENDAR