Denise Guliato

Segmentation of breast tumors in mammograms by fuzzy region growing

Segmentation of tumor regions in mammograms is not easy due to the low contrast and the fuzzy nature of the boundaries of malignant tumors. General image segmentation procedures do not consider the uncertainty present around the boundaries of a tumor region. In this paper we present a segmentation method based on fuzzy region growing. The procedure starts with a seed pixel, and uses a fuzzy membership function based upon statistical measures of the region being grown. Results of testing with several mammograms indicate that the method can provide boundaries of tumors close to those drawn by an expert radiologist. The regions obtained preserve the transition information present around tumor boundaries. Statistical measures computed from the resulting regions have shown the potential to classify masses and tumors as benign or malignant.

Polygonal Modeling of Contours of Breast Tumors With the Preservation of Spicules

Malignant breast tumors typically appear in mammograms with rough, spiculated, or microlobulated contours, whereas most benign masses have smooth, round, oval, or macrolobulated contours. Several studies have shown that shape factors that incorporate differences as above can provide high accuracies in distinguishing between malignant tumors and benign masses based upon their contours only. However, global measures of roughness, such as compactness, are less effective than specially designed features based upon spicularity and concavity. We propose a method to derive polygonal models of contours that preserve spicules and details of diagnostic importance. We show that an index of spiculation derived from the turning functions of the polygonal models obtained by the proposed method yields better classification accuracy than a similar measure derived using a previously published method. The methods were tested with a set of 111 contours of 65 benign masses and 46 malignant tumors. A high classification accuracy of 0.94 in terms of the area under the receiver operating characteristics curve was obtained.

Segmentation of breast tumors in mammograms using fuzzy sets

Defining criteria to determine precisely the boundaries of masses in mammograms is a difficult task. The problem is com- pounded by the fact that most malignant tumors possess fuzzy boundaries with a slow and extended transition from a dense core region to the surrounding less-dense tissues. We propose two seg- mentation methods that incorporate fuzzy concepts. The first method determines the boundary of a mass or tumor by region growing after a preprocessing step based on fuzzy sets to enhance the region of interest (ROI). Contours provided by the method have demonstrated a good match with the contours drawn by a radiolo- gist, as indicated by good agreement between the two sets of con- tours for 47 mammograms. The second segmentation method is a fuzzy region-growing method that takes into account the uncertainty present around the boundaries of tumors. The difficult step of decid- ing on a crisp boundary is obviated in the proposed method. Mea- sures of inhomogeneity computed from the pixels present in a suit- ably defined fuzzy ribbon have indicated potential use in classifying the masses and tumors as benign or malignant, with a sensitivity of 0.8 and a specificity of 0.9.

Feature extraction from a signature based on the turning angle function for the classification of breast tumors.

Malignant breast tumors and benign masses appear in mammograms with different shape characteristics: the former usually have rough, spiculated, or microlobulated contours, whereas the latter commonly have smooth, round, oval, or macrolobulated contours. Features that characterize shape roughness and complexity can assist in distinguishing between malignant tumors and benign masses. Signatures of contours may be used to analyze their shapes. We propose to use a signature based on the turning angle function of contours of breast masses to derive features that capture the characteristics of shape roughness as described above. We propose methods to derive an index of the presence of convex regions (XRTA), an index of the presence of concave regions (VRTA), an index of convexity (CXTA), and two measures of fractal dimension (FDTA and FDdTA) from the turning angle function. The methods were tested with a set of 111 contours of 65 benign masses and 46 malignant tumors with different parameters. The best classification accuracies in discriminating between benign masses and malignant tumors, obtained for XRTA, VRTA, CXTA, FDTA, and FDdTA in terms of the area under the receiver operating characteristics curve, were 0.92, 0.92, 0.93, 0.93, and, 0.92, respectively.

POSTGRESQL-IE: An Image-handling Extension for PostgreSQL

The last decade witnessed a growing interest in research on content-based image retrieval (CBIR) and related areas. Several systems for managing and retrieving images have been proposed, each one tailored to a specific application. Functionalities commonly available in CBIR systems include: storage and management of complex data, development of feature extractors to support similarity queries, development of index structures to speed up image retrieval, and design and implementation of an intuitive graphical user interface tailored to each application. To facilitate the development of new CBIR systems, we propose an image-handling extension to the relational database management system (RDBMS) PostgreSQL. This extension, called PostgreSQL-IE, is independent of the application and provides the advantage of being open source and portable. The proposed system extends the functionalities of the structured query language SQL with new functions that are able to create new feature extraction procedures, new feature vectors as combinations of previously defined features, and new access methods, as well as to compose similarity queries. PostgreSQL-IE makes available a new image data type, which permits the association of various images with a given unique image attribute. This resource makes it possible to combine visual features of different images in the same feature vector. To validate the concepts and resources available in the proposed extended RDBMS, we propose a CBIR system applied to the analysis of mammograms using PostgreSQL-IE.

Detection of Breast Tumor Boundaries Using ISO-Intensity Contours and Dynamic Thresholding

Mammograms are, at times, difficult to interpret: developing signs of cancer may be masked by superimposed tissues. Additional diagnostic procedures may be recommended when the original mammogram is equivocal.

Spatial Locality Weighting of Features Using Saliency Map with a Bag-of-Visual-Words Approach

In this paper we propose a new descriptor for content-based image retrieval that explores the locality of features. We propose to extend the bag-of-visual-words method by weighting the visual words according to their spatial locality in terms of foreground and background by using fuzzy saliency models. We evaluated our method using databases that obtains images with different conditions of illumination, color, rigid and scale transformations, and changes of the background. The analysis of the results demonstrated that our proposal presents significant improvements over competitive approaches.

Polygonal Modeling of Contours Using the Turning Angle Function

Several types of signatures have been defined to facilitate the analysis of contours of objects. The turning angle function of a given contour may be used as a signature to analyze the contour. We propose a method to use the turning angle function to derive a polygonal model of the given contour in such a manner as to preserve the important details in the contour. We demonstrate the usefulness of the resulting polygonal model in deriving efficient shape factors, and illustrate its application in the classification of breast masses. Most malignant breast tumors, as seen in mammograms, have rough and spiculated contours; on the contrary, benign masses usually have smooth, round, or oval contours. An index of spiculation derived from the proposed polygonal model was tested with a set of 111 contours of which 65 are related to benign masses and 46 are related to malignant tumors. A high classification accuracy of 0.92 was obtained, in terms of the area under the receiver operating characteristics curve, with a data compression of 0.025 on average.

Fuzzy fusion operators to combine results of complementary medical image segmentation techniques

The detection of masses and tumors in a mammogram is a difficult problem that could benefit from the use of multiple approaches. We propose an abstract concept of information fusion based on a finite automaton and fuzzy sets to integrate and evaluate results of multiple image segmentation procedures. We give examples on how the method can be applied to the problem of mammographic image segmentation, combining results of region growing and closed-contour detection techniques. We also propose a measure of fuzzyness to assess the agreement between a segmented region and a reference contour. Application of the fusion technique to breast tumor detection in mammograms indicates that the fusion results agree with the reference contours provided by a radiologist to a higher extent than the results of the individual methods.

Segmentation and centromere locating methods applied to fish chromosomes images

The objective of this paper is to describe a new approach for locating the centromere of each chromosome displayed in the digitalized photomicrography of fish cells. To detect the centromere position, the authors propose methods for both image segmentation and split touching chromosomes based on the fuzzy sets theory and a method for the rotation of chromosomes. These methods were applied to two species of fish chromosomes: Astyanax scabripinnis and Astyanax eigenmanniorum. Using a database with 40 images including metacentric, submetacentric and subtelocentric chromosomes, and comparing the centromere locating obtained by the proposed algorithm with the manual results obtained by two expert cytogeneticists, the average accuracies were 81.79% and 82.54% respectively.