Diagnosis and prognosis of Ostheoarthritis by texture analysis using sparse linear models

Joselene Marques, Line Katrine Harder Clemmensen, Erik Dam

    Research output: Contribution to conferencePaperResearchpeer-review

    107 Downloads (Pure)

    Abstract

    We present a texture analysis methodology that combines uncommitted machine-learning techniques and sparse feature transformation methods in a fully automatic framework. We compare the performances of a partial least squares (PLS) forward feature selection strategy to a hard threshold sparse PLS algorithm and a sparse linear discriminant model. The texture analysis framework was applied to diagnosis of knee osteoarthritis (OA) and prognosis of cartilage loss. For this investigation, a generic texture feature bank was extracted from magnetic resonance images of tibial knee bone. The features were used as input to the sparse algorithms, which dened the best features to retain in the model. To cope with the limited number of samples, the data was evaluated using 10 fold cross validation (CV). The diagnosis evaluation using sparse PLS reached a generalization area-under-the-ROC curve (AUC) of 0.93 and the prognosis had AUC of 0.70, both superior to established cartilage based markers known to relate to OA diagnosis and prognosis.
    Original languageEnglish
    Publication date2012
    Number of pages8
    Publication statusPublished - 2012
    Event15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2012) : Workshop in Sparsity Techniques in Medical Imaging (STMI) - Nice , France
    Duration: 5 Oct 2012 → …
    http://www.miccai2012.org/

    Workshop

    Workshop15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2012) : Workshop in Sparsity Techniques in Medical Imaging (STMI)
    CountryFrance
    CityNice
    Period05/10/2012 → …
    Internet address

    Keywords

    • Sparse PLS
    • Sparse LDA
    • Sparsity
    • Feature selection
    • Texture analysis
    • OA
    • Bone structure

    Fingerprint Dive into the research topics of 'Diagnosis and prognosis of Ostheoarthritis by texture analysis using sparse linear models'. Together they form a unique fingerprint.

    Cite this