Kernel Smoothing-based Probability Contours for Tumour Segmentation

Zhang, W. and Ray, S. (2022) Kernel Smoothing-based Probability Contours for Tumour Segmentation. 26th UK Conference on Medical Image Understanding and Analysis (MIUA 2022), University of Cambridge, 27-29 July 2022.

[img] Text
280381.pdf - Published Version
Restricted to Repository staff only

504kB

Abstract

Statistical imaging together with other machine learning techniques are the epitome of digitalizing healthcare and are culminating towards developing innovative tools for automatic analysis of three-dimensional radiological images — PET (Positron Emission Tomography) images. In this project, we have developed a kernel smoothing probability contour method on PET image segmentation which can be trained with a relatively low number of samples. A clear advantage of our kernel smoothing probability contour method is that it provides a surface over images which produces contour-based results rather than pixel-wise results, thus mimicking human observers’ behaviour. In addition, our methodology provides the tools for developing a probabilistic approach with uncertainty measurement along with the segmentation.

Item Type:Conference or Workshop Item
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Zhang, Wenhui and Ray, Professor Surajit
Authors: Zhang, W., and Ray, S.
College/School:College of Science and Engineering > School of Mathematics and Statistics > Statistics
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record