hrcak mascot   Srce   HID

Izvorni znanstveni članak

Ultrasound Image Segmentation using Stochastic Templates

C. A. Glasbey ; Biomathematics and Statistics Scotland, JCMB, King's Buildings, Edinburgh EH9 3JZ, Scotland

Puni tekst: engleski, pdf (4 MB) str. 107-116 preuzimanja: 33* citiraj
APA 6th Edition
Glasbey, C.A. (1998). Ultrasound Image Segmentation using Stochastic Templates. Journal of computing and information technology, 6 (2), 107-116. Preuzeto s https://hrcak.srce.hr/150228
MLA 8th Edition
Glasbey, C. A.. "Ultrasound Image Segmentation using Stochastic Templates." Journal of computing and information technology, vol. 6, br. 2, 1998, str. 107-116. https://hrcak.srce.hr/150228. Citirano 23.07.2019.
Chicago 17th Edition
Glasbey, C. A.. "Ultrasound Image Segmentation using Stochastic Templates." Journal of computing and information technology 6, br. 2 (1998): 107-116. https://hrcak.srce.hr/150228
Harvard
Glasbey, C.A. (1998). 'Ultrasound Image Segmentation using Stochastic Templates', Journal of computing and information technology, 6(2), str. 107-116. Preuzeto s: https://hrcak.srce.hr/150228 (Datum pristupa: 23.07.2019.)
Vancouver
Glasbey CA. Ultrasound Image Segmentation using Stochastic Templates. Journal of computing and information technology [Internet]. 1998 [pristupljeno 23.07.2019.];6(2):107-116. Dostupno na: https://hrcak.srce.hr/150228
IEEE
C.A. Glasbey, "Ultrasound Image Segmentation using Stochastic Templates", Journal of computing and information technology, vol.6, br. 2, str. 107-116, 1998. [Online]. Dostupno na: https://hrcak.srce.hr/150228. [Citirano: 23.07.2019.]

Sažetak
Point distribution models (PDMs) are incorporated into Bayesian image analysis, thus combining two approaches to the fitting of stochastic templates. Manually segmented images are used to identify both a PDM and a likelihood function, leading to a posterior distribution from which inferences can be drawn. The methodology 1s explored and illustrated using 144 ultrasound images of sheep. A pseudo-likelihood is found to give better results than a likelihood based on the distribution of pixel values in the training images. Estimates of sheep fat and muscle depths are shown to be comparable in accuracy with manual interpretation of images.

Ključne riječi
Bayesian methods; Likelihood; Point distribution models

Hrčak ID: 150228

URI
https://hrcak.srce.hr/150228

Posjeta: 58 *