Rojas Dominguez, Alfonso (2007) Automated detection, segmentation and classification of breast masses in digitised mammograms. Doctoral thesis, University of Liverpool.
This is the latest version of this item.
Full text not available from this repository.
Official URL: http://alfonso.rojas.googlepages.com/
A method for automatic detection of mammographic masses is presented. As part of this method, an enhancement algorithm is proposed that improves image contrast based on local statistical measures of the mammograms. After enhancement, regions are segmented via thresholding at multiple levels, and a set of features is computed from each of the segmented regions. A region-ranking system is also presented that identifies the regions most likely to represent abnormalities based on the features computed. The method was tested on 57 mammographic images of masses and achieved a sensitivity of 80% at 2.3 false-positives per image (average of 0.32 false-positives). Two new algorithms for segmentation of masses are presented. These are based on the Dynamic Programming-based Boundary Tracing (DPBT) algorithm proposed in: Timp and Karssemeijer, Med. Phys. 31 (5), pp. 958-971, (2004). The DPBT algorithm contains two main steps: 1) construction of a local cost function, and 2) application of dynamic programming to the selection of the optimal boundary. Modifications to the computation of the local cost function are proposed and produce the Improved-DPBT (IDPBT) algorithm. A procedure for the dynamic selection of the strength of the components of the local cost function is also presented that makes these parameters independent of the image dataset, and produces another new algorithm, ID2PBT. Both of the new algorithms outperform the original DPBT. Four new features for the analysis of breast masses are presented. These features are designed to be insensitive to the exact shape of the contour of the masses, so that an approximate contour, such as one extracted via an automated segmentation algorithm, can be employed in their computation. Two of the features, SpSI and SpGO, measure the degree of spiculation of a mass and its likelihood of being spiculated. The last two features, Fz1 and Fz2, measure the local fuzziness of the mass margins based on points defined automatically. The features were tested for characterisation and diagnosis of breast masses using a set of 319 masses and three different classifiers, and obtained approximately 90% and 76% correct classification, respectively.
|Item Type:||Thesis (Doctoral)|
|Uncontrolled Keywords:||breast cancer; mammography; image processing; pattern recognition; image analysis; computer-aided diagnosis|
|Subjects:||T Technology > TK Electrical engineering. Electronics Nuclear engineering|
|Departments, Research Centres and Related Units:||Academic Faculties, Institutes and Research Centres > Faculty of Engineering > Department of Electrical Engineering and Electronics|
|Deposited On:||24 Nov 2010 10:38|
|Last Modified:||20 May 2011 16:48|
Available Versions of this Item
- Automated detection, segmentation and classification of breast masses in digitised mammograms. (deposited 24 Nov 2010 10:38) [Currently Displayed]
Repository Staff Only: item control page