Texture analysis base on Gabor filters improves the estimate of bone fracture risk from DXA images

Rui-Sheng Lu, Elaine Dennison, Hayley Dension, Cyrus Cooper, Mark Taylor, Murk Bottema

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We investigated whether novel parameters derived from a Dual-energy X-ray absorptiometry (DXA) scan might improve fracture risk estimation. In this study, we analysed hip DXA scans from 29 older adults with a history of fragility fracture and 90 non-fractured controls. Active shape models and active appearance models were used to allow a quantitative characterisation of the shape and gross structure of the proximal femur. We also performed image texture analysis applied to various regions of interest. Feature selection was used to determine which method, or combination of methods, was best to discriminate between the fracture and control groups. Texture features derived from Gabor filters in combination with total T-score provided better estimates of risk (AUC = 0.787) than the standard measures of areal bone mineral density or total T-score alone (AUC = 0.699 and 0.692, respectively). Estimates of risk were more accurate when the texture was measured on the whole femoral neck compared to other regions. The features extracted from the active models were weaker with poor classification performance (AUC < 0.570). This study shows that image texture based on Gabor filters can complement the standard measures to improve fracture risk estimation.

Original languageEnglish
Pages (from-to)453-464
Number of pages12
JournalComputer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Volume6
Issue number4
DOIs
Publication statusPublished - 2017

Fingerprint Dive into the research topics of 'Texture analysis base on Gabor filters improves the estimate of bone fracture risk from DXA images'. Together they form a unique fingerprint.

Cite this