Mammogram Inspection by Computer

A framework for computer-aided analysis of mammograms is described. General computer vision algorithms are combined with application specific procedures in a hierarchical fashion. The system is under development and is currently limited to detection of a few types of suspicious areas. The image features are extracted by using feature extraction methods where wavelet techniques are utilized. A low-pass pyramid representation of the image is convolved with a number of quadrature filters. The filter outputs are combined according to simple local Fourier domain models into parameters describing the local neighbourhood with respect to the model. This produces estimates for each pixel describing local size, orientation, Fourier phase, and shape with confidence measures associated to each parameter. Tentative object descriptions are then extracted from the pixel-based features by application-specific procedures with knowledge of relevant structures in mammograms. The orientation, relative brightness and shape of the object are obtained by selection of the pixel feature estimates which best describe the object. The list of object descriptions is examined by procedures, where each procedure corresponds to a specific type of suspicious area, e.g. clusters of microcalcifications.

show abstract

“…O k (ρ, ϕ) = a 1 (B 10 cos ϕ k + B 11 sin ϕ k ) + a 3 (B 30 cos 3ϕ k + B 31 sin 3ϕ k ) (25) which in terms of filter responses gives: …”

Section: Discussionmentioning

confidence: 99%

Feature Extraction for Computer-Aided Analysis of Mammograms

Bårman

Granlund

Haglund

1993

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Wee et al [1], in 1975, developed a procedure to evaluate calcifications on mammograms based on a set of features. Spiesberger [2] proposed a similar procedure, in which features were applied in a decision tree for calcification detection. During the period of 1987 to 1990, Chan et al [3] reported on a series of detection systems based on a difference-image technique.…”

Section: Inrroducnonmentioning

confidence: 99%

A knowledge-based position matching technique for mammographic calcifications

Shen

Rangayyan

Desautels

1992

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

The purpose of this paper is to present a knowledge-based position matching technique which can be used to determine the corresponding calcifications in two views (MLO/CC) of a breast. The procedure includes two stages: First, an initial matching list is produced based on a matching parameter; then, three checking parameters are used to extract the best matching pairs from the initial list. This procedure should aid in the analysis of shapes of calcifications.

show abstract

“…In early 1979, Spiesberger and Wolfgang showed the reliability and feasibility to inspect mammograms by computer [4]. They used brightness measures, gray-level statistics, and a compactness measure in detection algorithm.…”

Section: Introductionmentioning

confidence: 99%

A contrast enhancement algorithm in the DCT domain with reduced artifacts for cancer detection

et al. 2009

View full text Add to dashboard Cite

Current DCT based image enhancement techniques will produce heavy artifacts when the enhancement factors are increased. In order to attack this issue, in this paper, we develop a new image enhancement algorithm in the DCT domain for radiologists to screen mammograms. In the proposed algorithm, with a given target contrast value and visual quality requirement, genetic algorithm is used to search the optimal parameter setting for image enhancement. The new image enhancement algorithm can reduce the artifact introduced by the enhancement effectively. Both objective test and subjective test were used to verify the proposed algorithm. The experimental results show that the enhanced images have reduced artifacts and better visual quality.

show abstract

Mammogram Inspection by Computer

Cited by 53 publications

References 11 publications

Feature Extraction for Computer-Aided Analysis of Mammograms

Feature Extraction for Computer-Aided Analysis of Mammograms

A knowledge-based position matching technique for mammographic calcifications

A contrast enhancement algorithm in the DCT domain with reduced artifacts for cancer detection

Contact Info

Product

Resources

About