# Speeding up image reconstruction in computed tomography

- Institution: CERN
- Department: Inverted CSC
- Speaker: Victoria Tokareva
- Year: 2018
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3007345)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Computed tomography (CT) is a technique for imaging cross-sections of an object using X-ray measurements taken from different angles. In last decades a significant progress has happened there: today advanced algorithms allow fast image reconstruction and obtaining high-quality images even with missing or dirty data, modern detectors provide high resolution without increasing radiation dose, and high-performance multi-core computing devices are there to help us solving such tasks even faster.

I will start with CT basics, then briefly present existing classes of reconstruction algorithms and their differences. After that I will proceed to employing distinctive architectural features of modern multi-core devices (CPUs and GPUs) and popular program interfaces (OpenMP, MPI, CUDA, OpenCL) for developing effective parallel realizations of image reconstruction algorithms. Decreasing full reconstruction time from long hours up to minutes or even seconds has a revolutionary impact in diagnostic medicine and industrial non-destructive testing applications..

0:00:00 Slide 1

0:01:11 Slide 2

0:01:22 Slide 3

0:01:26 Slide 4

0:01:37 Slide 5

0:02:44 Slide 6

0:03:51 Slide 7

0:04:13 Slide 8

0:07:05 Slide 9

0:07:21 Slide 10

0:07:34 Slide 11

0:07:38 Slide 12

0:07:48 Slide 13

0:09:02 Slide 14

0:10:12 Slide 15

0:10:50 Slide 16

0:11:52 Slide 17

0:12:19 Slide 18

0:12:37 Slide 19

0:12:50 Slide 20

0:12:57 Slide 21

0:13:14 Slide 22

0:13:24 Slide 23

0:13:30 Slide 24

0:13:49 Slide 25

0:14:41 Slide 26

0:14:47 Slide 27

0:14:52 Slide 28

0:15:06 Slide 29

0:15:28 Slide 30

0:16:33 Slide 31

0:17:07 Slide 32

0:17:36 Slide 33

0:18:39 Slide 34

0:20:07 Slide 35

0:20:49 Slide 36

0:20:56 Slide 37

0:21:28 Slide 38

0:22:47 Slide 39

0:24:20 Slide 40

0:24:52 Slide 41

0:26:34 Slide 42

0:27:39 Slide 43

0:29:33 Slide 44

0:29:46 Slide 45

0:30:39 Slide 46

0:31:37 Slide 47

0:32:21 Slide 48

0:33:04 Slide 49

0:33:55 Slide 50

0:34:30 Slide 51

0:34:51 Slide 52…

## Lectures

1. [Speeding up image reconstruction in computed tomography](https://invisiblenetwork.ai/learn/cern/3007345/c16156d25802), 50 min (CERN's player)