Using deep image prior to assist variational selective segmentation deep learning algorithms

Burrows, Liam and Chen, Ke and Torella, Francesco; Romero, Eduardo and Costa, Eduardo Tavares and Brieva, Jorge and Rittner, Leticia and Linguraru, Marius George and Lepore, Natasha, eds. (2021) Using deep image prior to assist variational selective segmentation deep learning algorithms. In: 17th International Symposium on Medical Information Processing and Analysis. Proceedings of SPIE - The International Society for Optical Engineering, 12088 . SPIE, BRA. ISBN 9781510650527 (https://doi.org/10.1117/12.2606212)

[thumbnail of Burrows-etal-SPIE2021-Using-deep-image-prior-assist-variational-selective-segmentation-deep-learning-algorithms]
Preview
 Text. Filename: Burrows-etal-SPIE2021-Using-deep-image-prior-assist-variational-selective-segmentation-deep-learning-algorithms.pdf
Accepted Author Manuscript
Download (3MB)| Preview

Abstract

Variational segmentation algorithms require a prior imposed in the form of a regularisation term to enforce smoothness of the solution. Recently, it was shown in the Deep Image Prior work that the explicit regularisation in a model can be removed and replaced by the implicit regularisation captured by the architecture of a neural network. The Deep Image Prior approach is competitive, but is only tailored to one specific image and does not allow us to predict future images. We propose to incorporate the ideas from Deep Image Prior into a more traditional learning algorithm to allow us to use the implicit regularisation offered by the Deep Image Prior, but still be able to predict future images.

  • Item type:Book Section
    ID code:87143
    Dates:
    Date
    Event
    10 December 2021
    Published
    1 September 2021
    Accepted
    Notes:Publisher Copyright: © 2021 SPIE. Liam Burrows, Ke Chen, Francesco Torella, "Using deep image prior to assist variational selective segmentation deep learning algorithms," Proc. SPIE 12088, 17th International Symposium on Medical Information Processing and Analysis, 120880S (10 December 2021); doi: 10.1117/12.2606212
    Subjects:Science > Mathematics > Electronic computers. Computer science
    Department:Faculty of Science > Mathematics and Statistics
    Depositing user: Pure Administrator
    Date deposited:02 Nov 2023 13:19
    Last modified:08 Apr 2024 14:24
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/87143
CORE (COnnecting REpositories)