http://www.cnr.it/ontology/cnr/individuo/prodotto/ID135231

Advanced image processing techniques for liver tissue classification (Contributo in volume (capitolo o saggio))

Type

Label

Advanced image processing techniques for liver tissue classification (Contributo in volume (capitolo o saggio)) (literal)

Anno

Alternative label

Massoptier L.; Casciaro S. (2007)
Advanced image processing techniques for liver tissue classification
Lupiensis Biomedical Publications, Lecce (Italia) in New Technology Frontiers in Minimally Invasive Therapies, 2007
(literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

Pagina inizio

Pagina fine

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#citta

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note

In: New Technology Frontiers in Minimally Invasive Therapies. pp. 35 - 42. Sergio Casciaro, B. Gersak (eds.). Lupiensis Biomedical Publications, 2007. (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#pagineTotali

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#descrizioneSinteticaDelProdotto

Liver cancer is the fourth most common cancer in the world. Its diagnosis and treatments are changed in the last years thanks to the improvement of technology systems. Imaging technologies are now essential for taking medical decisions, because their progresses enable to detect smaller tumors in an earlier stage of development. Therefore, modern local treatments rely on software and image processing techniques to assist practitioners in the optimal extraction of information for better diagnosis. Active contours and graphcuts are two powerful advanced approaches for this purpose. In this chapter, a summary of both methods is proposed relying on their various possible approaches, their advantages and their limitations. Then, a comparative assessment is done describing some theoretical connections between these two methods. Liver segmentation has been performed with both active contours and graph-cuts. The latter seems to overcome some problems encountered by the former. However, many issues remain open for the graph-cuts application to the liver segmentation task, mainly because its recent initial development and application. (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

CNR-IFC, National Council of Research - Institute of Clinical Physiology, Lecce, Italy (literal)

Titolo

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#inCollana

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn

Abstract

Liver cancer is the fourth most common cancer in the world. Its diagnosis and treatments are changed in the last years thanks to the improvement of technology systems. Imaging technologies are now essential for taking medical decisions, because their progresses enable to detect smaller tumors in an earlier stage of development. Therefore, modern local treatments rely on software and image processing techniques to assist practitioners in the optimal extraction of information for better diagnosis. Active contours and graph-cuts are two powerful advanced approaches for this purpose. In this chapter, a summary of both methods is proposed relying on their various possible approaches, their advantages and their limitations. Then, a comparative assessment is done describing some theoretical connections between these two methods. Liver segmentation has been performed with both active contours and graph-cuts. The latter seems to overcome some problems encountered by the former. However, many issues remain open for the graph-cuts application to the liver segmentation task, mainly because its recent initial development and application. (literal)

Editore