Download:
|
by Reyer Zwiggelaar, James E. Schumm, Christopher J. Taylor
http://www.dcs.port.ac.uk/~reyer/ps-papers/RZ_MIUA97_1.ps.gz
Add To MetaCart
Abstract:
Abstract. Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80 % is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature. 1
Citations
|
1020
|
Numerical Recipes: The Art of Scientific Computing
– Press, Flannery, et al.
- 1986
|
|
19
|
Multiscale recursive medians, scale-space and transforms with applications to image processing
– Bangham, Ling, et al.
- 1996
|
|
19
|
Recursive implementation of erosions and dilations along discrete lines at arbitrary angles
– Soille, Breen, et al.
- 1996
|
|
11
|
Multivariate Statistics, A Practical Approach
– Johnson, Wichern
- 1988
|
|
9
|
The Computer-Aided Detection of Abnormalities in Digital Mammograms
– Hutt
- 1996
|
|
6
|
Evaluation of digital mammography by roc analysis
– Metz
- 1996
|
|
4
|
The detection of malignant masses by non-linear multiscale analysis
– Miller, Ramsey
- 1996
|
|
4
|
Detection criteria for evaluation of computer aided diagnosis systems
– Brake, Karssemeijer
- 1996
|
|
3
|
Investigation of a temporal subtraction scheme for computerized detection of breast masses in mammograms
– Zouras, Giger, et al.
- 1996
|
|
1
|
Computer-aided breast mass detection: false positive reduction using breast tissue composition
– Petrick, Chan, et al.
- 1996
|
|
1
|
should this contribution be considered important? The work described shows initial results for the detection of masses in mammographic images that look very promising and are comparable with the best results in the literature to date. Besides this specifi
– Why
|
|
1
|
What is the most closely related work by others and how does this work differ
– Bangham, Ling, et al.
- 1996
|
|
1
|
your work been tested or developed in association with clinical practice? We have worked with screening radiologists in Manchester and 12 other centres in the UK to establish the conditions under which computer-aided mammographic screening would improve r
– has
- 1996
|
