PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Humans and computer observer models often rely on feature analysis from a single imaging modality. We will examine benefits of new features that assist in image classification and detection of malignancies in MRI and X-Ray tomographic images. While the image formation principles are different in these modalities, there are common features like contrast that are often employed by humans (radiologist) in each of these when making decision. We will examine other features that may not be well-understood or explored such as grey level co-occurrence matrix (GLCM) texture features. As preliminary data, we show here the utility of some of these features along with classification methods aided by Gaussian mixture models (GMM) and fuzzy C-Means dimensionality reduction. GLCM maps characterize the image texture and provide a numerical and spatial tool of the texture signatures present in it. We will present pathways for using these in tissue classification, segmentation and development of task-based assessments.
Diego Andrade,Howard C. Gifford, andMini Das
"Multi-modality GLCM image texture feature for segmentation and tissue classification", Proc. SPIE 12463, Medical Imaging 2023: Physics of Medical Imaging, 124634P (7 April 2023); https://doi.org/10.1117/12.2659078
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Diego Andrade, Howard C. Gifford, Mini Das, "Multi-modality GLCM image texture feature for segmentation and tissue classification," Proc. SPIE 12463, Medical Imaging 2023: Physics of Medical Imaging, 124634P (7 April 2023); https://doi.org/10.1117/12.2659078