Conference Paper

Adaptive Detection of Hotspots in Thoracic Spine from Bone Scintigraphy.

DOI: 10.1007/978-3-642-24955-6_31 Conference: Neural Information Processing - 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part I
Source: DBLP

ABSTRACT In this paper, we propose an adaptive algorithm for the detection of hotspots in thoracic spine from bone scintigraphy. The intensity distribution of spine is firstly analyzed. The Gaussian fitting curve for the intensity distribution of thoracic spine is estimated, in which the influence of hotspots is eliminated. The accurate boundary of hotspot is delineated via adaptive region growing algorithm. Finally, a new deviation operator is proposed to train the Bayes classifier. The experiment results show that the algorithm achieve high sensitivity (97.04%) with 1.119 false detections per image for hotspot detection in thoracic spine.

0 Followers
 · 
99 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a novel method for the segmentation of spine and ribs from posterior whole-body bone scintigraphy images. The knowledge-based method is first applied to determine the thoracic region. An adaptive thresholding method is then used to extract the thoracic spine from it. The rib segmentation algorithm is carried out in two steps. First, the rib skeleton is extracted based on standard template and image information. The skeleton is then used to locate the accurate boundary of the respective ribs. The introduction of standard template can deal with significant variations among different patients well, while the skeleton-based method is robust against the low contrast between the ribs and the adjacent intervals. The experiments show that our method is robust and accurate compared to existing methods.
    Neural Information Processing - 18th International Conference, ICONIP 2011, Shanghai, China, November 13-17, 2011, Proceedings, Part I; 01/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Accurate segmentation of images is one of the most important objectives in image analysis. The two conventional methods of image segmentation, region based segmentation and boundary finding, often suffer from a variety of limitations. Many methods have been proposed to overcome the limitations but the solutions tend to be problem specific. Here we present a new region growing method with the capability of finding the boundary of a relatively bright/dark region in a textured background. The method relies on a measure of contrast of the region which represents the variation of the region gray level as a function of its evolving boundary during the growing process. It helps to identify the best external boundary of the region. The application of a reverse test using a gradient measure then yields the highest gradient boundary for the region being grown. A number of experiments have been performed both on synthetic and real images to evaluate the new approach. The proposed scheme can be ca...
    IEEE Transactions on Image Processing 02/1998; 7(7):1079-84. DOI:10.1109/83.701170 · 3.11 Impact Factor