Ctlina POPESCU-MINA 2)

Journal of Digital Imaging, 2007

Fractal analysis has been shown to be useful in image processing for characterizing shape and gray-scale complexity. Breast masses present shape and gray-scale characteristics that vary between benign masses and malignant tumors in mammograms. Limited studies have been conducted on the application of fractal analysis specifically for classifying breast masses based on shape. The fractal dimension of the contour of a mass may be computed either directly from the 2-dimensional (2D) contour or from a 1-dimensional (1D) signature derived from the contour. We present a study of four methods to compute the fractal dimension of the contours of breast masses, including the ruler method and the box counting method applied to 1D and 2D representations of the contours. The methods were applied to a data set of 111 contours of breast masses. Receiver operating characteristics (ROC) analysis was performed to assess and compare the performance of fractal dimension and four previously developed shape factors in the classification of breast masses as benign or malignant. Fractal dimension was observed to complement the other shape factors, in particular fractional concavity, in the representation of the complexity of the contours. The combination of fractal dimension with fractional concavity yielded the highest area (A z) under the ROC curve of 0.93; the two measures, on their own, resulted in A z values of 0.89 and 0.88, respectively.

Lecture Notes in Computer Science, 2007

In this paper it is shown that there is a difference in local fractal dimension between imaged glandular tissue, supporting tissue and muscle tissue based on an assessment from a mammogram. By estimating the density difference at four different local dimensions (2.06, 2.33, 2.48, 2.70) from 142 mammograms we can define a measure and by using this measure we are able to distinguish between the tissue types. A ROCanalysis gives us an area under the curve-value of 0.9998 for separating glandular tissue from muscular tissue and 0.9405 for separating glandular tissue from supporting tissue. To some extent we can say that the measured difference in fractal properties is due to different fractal properties of the unprojected tissue. For example, to a large extent muscle tissue seems to have different fractal properties than glandular or supportive tissue. However, a large variance in the local dimension densities makes it difficult to make proper use of the proposed measure for segmentation purposes.

Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

it is known that the malignancy of breast lesions is strongly correlated with their shape; the more irregular the lesion is, the more malignant it tends to be. For this reason, CAD systems aimed at assisting the classification of breast lesions often rely on quantitative measures, such as fractal dimension (FD), which can help characterizing the smoothness (or the roughness) of the lesion's shape (1).

Breast cancer is one of the diseases that cause more deaths around the world. One of the ways to reduce the high rates is the detection of the disease in its early stages. The faster the cancer is diagnosed, the greater the chances of cure without major consequences. Mammography is considered the most effective way to diagnose the lump in the breast. However, due to some factors, it is not always possible to draw conclusive results through the exam. In order to minimize misunderstandings on examinations and to assist the experts, increasingly computational techniques are used during the diagnosis. The similarity between fractals and the nodules suggests that the calculation of fractal dimension can be used as a means of classifying focal breast lesions. Through the results obtained in this work, we conclude that the fractal analysis of the mass outline is an efficient way of classifying mammograms.

In this paper, based on digital image processing and classification, we intend to investigate the possibility of breast cancer presence in doubtful cases. A mammography is classified in a BI-RADS category (Breast Imagining Reporting Data System) from 1 to 5. The 1-3 categories signify that the probability to be a malignant tumour is very small; the 5

2015

This study aims to classify and distinguish breast masses into benign and malignant using fractal analysis of the contours of breast mass in mammograms.

Cancer Letters, 1994

As a first step in determining the effkacy of using computers to assist in diagnosis of medical images, an investigation has been conducted which utilizes the patterns, or textures, in the images. To be of value, any computer scheme must be able to recognize and differentiate the various patterns. An obvious example of this in mammography is the recognition of tumorous tissue and non-malignant abnormal tissue from normal parenchymal tissue. We have developed a pattern recognition technique which uses features derived from the fractal nature of the image. Further. we are able to develop mathematical models which can be used to differentiate and classify the many tissue types. Based on a limited number of cases of digitized mammograms, our computer algorithms have been able to distinguish tumorous from healthy tissue and to distinguish among various parenchymal tissue patterns. These preliminary results indicate that discrimination based on the fractal nature of images may well represent a viable approach to utilizing computers to assist in diagnosis.

Journal of Physics: Conference Series, 2019

Breast cancer is one of the major causes of death among women. Small clusters of micro calcifications appearing as collection of white spots on mammograms show an early warning of breast cancer. Image segmentation is an important element of Digital Image processing that subdivides the image into discrete regions/objects, each identified by the property of homogeneity of pixels. X-ray mammography is used as diagnostic tool for diagnosis of breast cancer. Edge detection of micro calcification clusters in mammogram images is the main issue of early detection of breast cancer. Fractals are of rough or fragmented geometric shape that can be subdivided in parts, each of which is a reduced similar of the whole. Fractal dimension and Hurst exponent are used to locate the micro calcifications in the mammogram. The concept of fractal is associated with geometrical objects satisfying criteria such as self-similarity and fractal dimensionality. Present method of edge detection is superior compa...

International Journal of Biomedical Engineering and Technology, 2018

Breast cancer continues to rank at the forefront of public health problems. Characterisation of breast tissue is a step in computer-aided diagnosis, so we focus on it considering in particular texture and contour analysis of tumour masses with fractal and statistical approaches. Fist we extracted the mammographic mass with the mathematical morphology segmentation tool Watershed Line algorithm. Then we calculated fractal dimension of the mass contour using box counting algorithm. In addition to that we measured textural attributes from the grey-level co-occurrence matrix of the segmented image (region). Finally, we used Support Vector Machine classifier evaluated in K-fold cross-validation mode with OneVsOne strategy considering multiclass classification: Benin masses/Malignant masses. As a result we obtained a classification rate of 98%.

The American Journal of the Medical Sciences, 1996

The increased use of screening mammography has led to increased pressure to differentiate between benign and malignant lesions. Even those lesions considered "suspicious" by qualitative radiologists' interpretations may prove malignant in less than 30% of cases. Fractal analysis is a mathematical technique that quantifies complex shapes. The hypothesis tested is that fractal analysis can quantify the difference between the shapes of benign and malignant lesions as imaged by mammography. Ten mammograms from patients with biopsy-proven invasive ductal carcinoma and 10 mammograms from patients with biopsy-proven benign disease were compared using the box-counting technique of fractal analysis. The fractal dimension of the mediolateral and craniocaudal views were added together to derive the composite fractal dimension. Statistical analysis was done using the Mann-Whitney U test. The median composite fractal dimension for benign lesions was 1.831 (range 1.359-2.009) and for malignant lesions 2.477 (range 2.084-3.158) (P < 0.0001). In addition, all benign lesions had fractal dimensions ::;; 2.009, and all malignant lesions had fractal dimensions~ 2.084. In this sample of 10 mammograms of malignant lesions versus 10 mammograms of benign masses, the composite fractal dimension was perfectly discriminatory. Fractal analysis may be useful to evaluate mammographically discovered breast masses. A blinded, prospective trial will be needed to determine its