A knowledge-based system that utilizes the full 3-D information from a sequence of parallel planes in order to recognize anatomical organs in nuclear magnetic resonance (NMR) images is presented. After 3-D preliminary processing (surface-preserving smoothing), a set of elementary volumes are extracted from the multislice sequence by a 3-D segmentation process. The recognition task is performed by a rule-based system and consists in the interpretation of each elementary volume as an organ or part of an organ.
EXPERT SYSTEM FOR THE RECOGNITION OF ANATOMICAL ORGANS FROM 3D DATA-BASE
DELLEPIANE, SILVANA;SERPICO, SEBASTIANO;VERNAZZA, GIANNI;REGAZZONI, CARLO
1987-01-01
Abstract
A knowledge-based system that utilizes the full 3-D information from a sequence of parallel planes in order to recognize anatomical organs in nuclear magnetic resonance (NMR) images is presented. After 3-D preliminary processing (surface-preserving smoothing), a set of elementary volumes are extracted from the multislice sequence by a 3-D segmentation process. The recognition task is performed by a rule-based system and consists in the interpretation of each elementary volume as an organ or part of an organ.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.