Detekce a identifikace typu obratle v CT datech onkologických pacientů

Abstract

Automaticka detekce a segmentace patere nebo obratlu z CT snimku je narocnym ukolem z nekolika duvodu. Jednim z duvodu jsou nejasne hranice obratlu ve snimcich a nezretelne hranice mezi jednotlivymi obratli, dale artefakty, vyskytujici se v obrazech, ale take anatomicka slozitost. Tato prace se zabyva navrhem a realizaci detekce a klasifikace typu obratle v CT snimcich onkologickych pacientu, coz pridava na slozitosti z duvodu pritomnosti deformaci nekterych obratlu. Pri samotne segmentaci obratlu je vyuzita Otsuova metoda. Detekce obratlu je zalozena na hledani hranic oddelujici jednotlive obratle vsagitalnich rezech. Pro identifikaci potom slouzi rozhodovaci stromy nebo zobecnena Houghova, pricemz jsou obratle hledany v rezech CT snimku na zaklade podobnosti tvaru s modely jednotlivych obratlu.Automated spine or vertebra detection and segmentation from CT images is a difficult task for several reasons. One of the reasons is unclear vertebra boundaries and indistinct boundaries between vertebra. Next reason is artifacts in images and high degree of anatomical complexity. This paper describes the design and implementation of vertebra detection and classification in CT images of cancer patients, which adds to the complexity because some of vertebrae are deformed. For the vertebra segmentation, the Otsu’s method is used. Vertebra detection is based on search of borders between individual vertebra in sagittal planes. Decision trees or the generalized Hough transform is applied for the identification whereas the vertebra searching is based on similarity between each vertebra model shape and planes of CT scans.