.png){kind=icon}
Return
ALGEBRAIC RECONSTRUCTION TECHNIQUES CAN BE MADE COMPUTATIONALLY EFFICIENT
.png){kind=icon}
PRE
AI
DOI：10.1109/42.241889.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Algebraic reconstruction techniques (ART) are iterative procedures for recovering objects from their projections. It is claimed in this paper that by a careful adjustment of the order in which the collected data are accessed during the reconstruction procedure and of the so-called ''relaxation parameters'' that are to be chosen in an algebraic reconstruction technique, ART can produce high-quality reconstructions with excellent computational efficiency. We demonstrate this by showing, on an example based on a particular (but realistic) medical imaging task, that ART can match the performance of the standard EM approach for maximizing likelihood (from the point of view of that particular medical task), but at an order of magnitude less computational cost.
Keywords:
POSITRON EMISSION TOMOGRAPHY
IMAGE-RECONSTRUCTION
ALGORITHM
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.8
Papers:
6.3K
Citations:
3.7W
Organization
No organization information available
Cited Papers
ShareSaveNano-silica extracted from rice husk and its application in acetic acid steam reforming.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAIShareSave no more
no more