Microcalcifications Detection in Digitized Mammographic Images
نویسندگان
چکیده
A method has been developed to detect and analyse microcalcifications in digitized mammographic images. The algorithms presented in this work combine an image preprocessing to denoise the digital image and image treatment techniques to localize and characterize the features of the microcalcifications. Two image denoising methods have been applied to the mammographies, the first one is an adaptive noise removal Wiener filter and the second one is a wavelet filter based on the wavelet coefficients shrinkage. After denoisig, the microcalcification location is carried out by applying digital image processing techniques as image local thresholding to detect objects of interest, a regional growing method based on determining the maximum of the slope function for different space directions of a wavelet smoothed version of the mammographic image, and the morphological operator application to fix the microcalcifications shape and size. Once the microcalcifications are characterized in the image, a big quantity of data about its characteristics can be obtained as location, size, eccentricity, bright level in relation to the background, signal to noise ratio, etc. This information about the mammography microcalcifications, that due to its small size and lowly contrast can be obtained very difficultly by direct observation, can be used to define an image quality index (IQI) which characterizes the quality image in an objective way. The image quality index is defined as the smallest microcalcification diameter calculated as the average at the major and minor axes of the microcalcification. This way of determining the image quality is similar to the system used by the radiologist, with the difference that the presented computer assisted method is more objective and independent of the radiologist who analyses the image. The IQI serve to compare images obtained at different mammographic centers and also, to study the temporal evolution of the image quality produced by determined mammographic equipment.
منابع مشابه
Mammographic microcalcifications: detection with xerography, screen-film, and digitized film display.
Pulverized bone specks and aluminum oxide specks were measured by hand into sizes ranging from 0.2 mm to 1.0 mm and then arranged in clusters. These clusters were superimposed on a human breast tissue phantom, and xeromammograms and screen-film mammograms of the clusters were made. The screen-film mammograms were digitized using a high-resolution laser scanner and then displayed on cathode ray ...
متن کاملCombination of Wavelet Analysis and Non-Linear Enhancement Function for Computer Aided Detection of Microcalcifications
Microcalcifications are small densities that appear as bright spots on mammograms. Its detection plays a very important role in breast cancer detection at early stages in digitized mammographic images. This paper presents an approach for computer aided detection of microcalcifications. The main idea of the proposed approach is to apply wavelet analysis followed by a non-linear transformation fu...
متن کاملFree-response receiver operating characteristic evaluation of lossy JPEG2000 and object-based set partitioning in hierarchical trees compression of digitized mammograms.
PURPOSE To assess the effects of two irreversible wavelet-based compression algorithms--Joint Photographic Experts Group (JPEG) 2000 and object-based set partitioning in hierarchical trees (SPIHT)--on the detection of clusters of microcalcifications and masses on digitized mammograms. MATERIALS AND METHODS The use of the images in this retrospective image-collection study was approved by the ...
متن کاملAutomatic Classification of Clustered Microcalcifications by a Multiple Classifier System
Mammography is a not invasive diagnostic technique widely used for early detection of breast cancer. One of the main indicants of cancer is the presence of microcalcifications, i.e. small calcium accumulations, often grouped into clusters. Automatic detection and recognition of malignant clusters of microcalcifications are very difficult because of the small size of the microcalcifications and ...
متن کاملWavelet Based Microcalcifications Detection in Digitized Mammograms
Detection of microcalcifications in mammograms has received much attention from researchers and public health practitioners in these last years. The challenge is to quickly and accurately overcome the development of breast cancer which affects more and more women through the world. Microcalcifications appear in a mammogram as fine, granular clusters, which are often difficult to identify in a r...
متن کامل