• Title/Summary/Keyword: Guided Feathering

Search Result 2, Processing Time 0.02 seconds

Improved Minimum Spanning Tree based Image Segmentation with Guided Matting

  • Wang, Weixing;Tu, Angyan;Bergholm, Fredrik
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.16 no.1
    • /
    • pp.211-230
    • /
    • 2022
  • In image segmentation, for the condition that objects (targets) and background in an image are intertwined or their common boundaries are vague as well as their textures are similar, and the targets in images are greatly variable, the deep learning might be difficult to use. Hence, a new method based on graph theory and guided feathering is proposed. First, it uses a guided feathering algorithm to initially separate the objects from background roughly, then, the image is separated into two different images: foreground image and background image, subsequently, the two images are segmented accurately by using the improved graph-based algorithm respectively, and finally, the two segmented images are merged together as the final segmentation result. For the graph-based new algorithm, it is improved based on MST in three main aspects: (1) the differences between the functions of intra-regional and inter-regional; (2) the function of edge weight; and (3) re-merge mechanism after segmentation in graph mapping. Compared to the traditional algorithms such as region merging, ordinary MST and thresholding, the studied algorithm has the better segmentation accuracy and effect, therefore it has the significant superiority.

A Smart Setup for Craniospinal Irradiation

  • Peterson, Jennifer L.;Vallow, Laura A.;Kim, Siyong;Casale, Henry E.;Tzou, Katherine S.
    • Progress in Medical Physics
    • /
    • v.24 no.4
    • /
    • pp.230-236
    • /
    • 2013
  • Our purpose is to present a novel technique for delivering craniospinal irradiation in the supine position using a perfect match, field-in-field (FIF) intrafractional feathering, and simple forward-optimization technique. To achieve this purpose, computed tomography simulation was performed with patients in the supine position. Half-beam, blocked, opposed, lateral, cranial fields with a collimator rotation were matched to the divergence of the superior border of an upper-spinal field. Fixed field parameters were used, and the isocenter of the upper-spinal field was placed at the same source-to-axis distance (SAD), 20 cm inferior to the cranial isocenter. For a lower-spinal field, the isocenter was placed 40 cm inferior to the cranial isocenter at a constant SAD. Both gantry and couch rotations for the lower-spinal field were used to achieve perfect divergence match with the inferior border of the upper-spinal field. A FIF technique was used to feather the craniospinal and spinal-spinal junction daily by varying the match line over 2 cm. The dose throughout the target volume was modulated using the FIF simple forward optimization technique to obtain homogenous coverage. Daily, image-guided therapy was used to assure and verify the setup. This supine-position, perfect match craniospinal irradiation technique with FIF intrafractional feathering and dose modulation provides a simple and safe way to deliver treatment while minimizing dose inhomogeneity.