Soft classification of trabeculae in trabecular bone

• Classification of trabecular bone aims at discriminating different types of trabeculae. This paper proposes a method to perform a soft classification from binary 3D images. In a first step, the local structure tensor is used to estimate a membership degree of every voxel to three different classes, plate-, rod- and junction-like trabeculae. In a second step, the global structure tensor of plate-like trabeculae is compared with the local orientation of rod-like trabeculae in order to discriminate aligned from non-aligned rods. Results show that soft classification can be used for estimating independent parameters of trabecular bone for every different class, by using the classification as a weighting function.

Ämnesord

Natural Sciences  (hsv)

Computer and Information Sciences  (hsv)

Computer Vision and Robotics (Autonomous Systems)  (hsv)

Naturvetenskap  (hsv)

Data- och informationsvetenskap  (hsv)

Datorseende och robotik (autonoma system)  (hsv)

Medical and Health Sciences  (hsv)

Clinical Medicine  (hsv)

Radiology, Nuclear Medicine and Medical Imaging  (hsv)

Medicin och hälsovetenskap  (hsv)

Klinisk medicin  (hsv)

Radiologi och bildbehandling  (hsv)

TECHNOLOGY  (svep)

Other technology  (svep)

Mechanical engineering  (svep)

TEKNIKVETENSKAP  (svep)

Övriga teknikvetenskaper  (svep)

Maskinteknik  (svep)

TECHNOLOGY  (svep)

Information technology  (svep)

Image analysis  (svep)

TEKNIKVETENSKAP  (svep)

Informationsteknik  (svep)

Bildanalys  (svep)

MEDICINE  (svep)

Physiology and pharmacology  (svep)

Radiological research  (svep)

Radiology  (svep)

MEDICIN  (svep)

Fysiologi och farmakologi  (svep)

Radiologisk forskning  (svep)

Radiologi  (svep)

Nyckelord

Biomedical image analysis

trabecular bone

classification of tissue

structure tensor

micro computed tomography