Conference Paper

Concept detection in longitudinal brain MR images using multi-modal cues

Univ. of Maryland, Baltimore County, Catonsville, MD, USA
DOI: 10.1109/ISBI.2009.5193073 Conference: Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Source: IEEE Xplore

ABSTRACT Advances in medical imaging techniques and devices has resulted in increased use of imaging in monitoring disease progression in patients. However, extracting decision-enabling information from the resulting longitudinal multi-modal image sets poses a challenge. Radiologists often have to manually identify and quantify certain regions of interest in the longitudinal image sets, which bear upon the patient's condition. As the number of patients increases, the number of longitudinal multi-modal images grows, and the manual annotation and quantification of pathological concepts quickly becomes impractical. In this paper we explore how minimal annotations provided by the user at a few time points can be effectively leveraged to automatically annotate data in the entire multi-modal longitudinal image sets. In particular, we investigate the required number of annotated images per time point and across time for obtaining reasonable results for the entire image set, and what multi-modal cues can help boost the overall annotation results.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper discussed some highlights on biomedical image processing. Some topics discussed were; diffusion tensor imaging, MR spectroscopy, cardiac 4D ultrasound,electron crystallography of proteins, and learning based medical computer vision.
    IEEE Reviews in Biomedical Engineering 02/2010;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semi-supervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre- and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.
    01/2014; 17(Pt 1):714-21.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This article resumes on a selected set of topics and collects promising and recent research advances in the field of multimodal temporal data analysis, high-field magnetic resonance spectroscopy, trends in computer-aided diagnosis and advances in cardiac diagnostic imaging. The first section briefly points to promising work on statistical models for tracking, detection, and segmentation in multimodal temporal imagery. Section III gives a brief snapshot of slice selective free induction decay (FID) acquisition for 7 tesla high-field MR imaging. Section IV outlines highlights in comparative validation of computer-aided diagnosis and associated image analysis algorithms spanning a variety of application domains from the heart to the eye. Lastly, Section V describes advances in the analysis of real-time three-dimensional (3-D) echocardiography for computing myocardial strain.
    IEEE Reviews in Biomedical Engineering 02/2009;


Available from