Output details
11 - Computer Science and Informatics
University of East Anglia
Return to search
Output 0 of 0 in the submission
Article title
On the segmentation and classification of hand radiographs
Type
D - Journal article
Title of journal
International Journal of Neural Systems
Article number
1250020
Volume number
22
Issue number
05
First page of article
-
ISSN of journal
1793-6462
Year of publication
2012
URL
-
Number of additional authors
4
Additional information
<15>We investigate methods to automatically estimate bone age in order to help paediatricians produce faster and more accurate predictions. Segmenting and classifying hand outline is part of the process, and our rigorous experimentation demonstrates that, perhaps surprisingly, standard image segmentation approaches cannot consistently extract the outline of a hand from a radiograph. We propose a novel algorithm for this problem based on ensembling a range of techniques and demonstrate that it outperforms other methods on a data set of over one thousand images.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
1
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-