Detection of single and clustered microcalcifications in mammograms using fractals models and neural networks

Bocchi, Leonardo; Coppini, Giuseppe; Nori, Jacopo; Valli, G.

doi:10.1016/j.medengphy.2003.11.009

Cited by 99 publications

(59 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the same training data set and test data set, the TWSVMs classifier achieved a sensitivity of 90.01%, 9.63% false positive rate and Az=0.9459, and SVMs achieved a sensitivity of 87.13%, 9.88% false positive rate and Az=0.9298.Comparisons of the proposed methodology with others reported in the literatures are not straightforward because those experiments were conducted on different data. Using fractals models and neural networks, L. Bocchiet al [6] reported cluster detection results of about TPR=87% and FPR=7% in their test set. J. Jiang et al [23] used a genetic algorithm design to classify and detect MCs with manually selected 300 MC-present blocks and 300 non-MC blocks from DDSM, and achieved their experimental results with Az = 0.987.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Ac y c (6) This problem can be solved in polynomial time by standard linear programming or quadratic programming methods. Even more efficient methods are available when the solution is known to be very sparse.…”

Section: Research Methods 21 Sparse Representation and Sparse Solutionmentioning

confidence: 99%

“…Because of its importance in breast cancer diagnosis accurate detection of MCs has become a key research and application task, and a number of approaches have recently been developed, which have been greatly assisting doctors and radiologists in diagnosing breast cancer [1,2]. Among them, focusing on image segmentation and specification of regions of interest (ROI), several methods have been proposed, such as classical image filter and local threshold [3,4], and techniques based on mathematical morphology [5], fractal models [6], optimal filters [7], wavelet analysis and multi-scale analysis [3]. Various classification approaches have also been presented to characterize MCs, such as rule-based systems [8], fuzzy logic systems [9,10], statistical methods based on Markov random fields(MRF) [11], and support vector machines [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse Representation for Detection of Microcalcification Clusters

Zhang

Wang

2012

TELKOMNIKA

View full text Add to dashboard Cite

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Research Methods 21 Sparse Representation and Sparse Solutionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sparse Representation for Detection of Microcalcification Clusters

Zhang

Wang

2012

TELKOMNIKA

View full text Add to dashboard Cite

show abstract

“…Bocchi et al (23) implement the classification algorithm using a Kohonen layer followed by a multilayer feed-forward network. The use of one hidden layer in the neural network give 91% TP, whereas without using a hidden layer the result was 82% TP.…”

Section: Multiscale Texture Features Extraction -Wavelet Based Methodmentioning

confidence: 99%

Classification algorithms for microcalcifications in mammograms (Review)

Sakka

Prentza²,

Koutsouris³

2006

Oncol Rep

View full text Add to dashboard Cite

Abstract. Early detection is the key to improve breast cancer prognosis. The only proven effective method of breast cancer early detection is mammography. An early sign of 30-50% of breast cancer is the appearance of clusters of fine, granular microcalcifications and 60-80% of breast carcinomas reveal microcalcification clusters upon histological examination. The high correlation between the appearance of the microcalcification clusters and diseases, proves that computer aided diagnosis (CAD) systems for automated classification of microcalcification clusters will be very useful and helpful for breast cancer control. The fuzzy nature of microcalcification, the low contrast and the low ability of distinguishing them from their surroundings make automated characterization of them extremely difficult. In this study, we give an overview of the currently available literature on characterization of malignant and benign microcalcifications. We compare and evaluate some of the classification algorithms on microcalcifications in mammograms used in various CAD systems, which are separated into categories according to the method in use. Neural networks are used in applications where only a few decisions are required concerning an amount of data. The K-nearest neighbour classifier distinguishes unknown patterns based on the similarity to known samples and the decision tree approach is much simpler than neural networks and does not need extensive knowledge of the probability distribution of the features.

show abstract

“…The MCs has important characteristics in their size, shape/morphology, amount, and distribution. Their sizes vary from 0.1 mm to 1 mm [2]. MC detection is very difficult in mammographies with overlapping breast tissues or high breast tissue density.…”

Section: Introductionmentioning

confidence: 99%

Automatic Microcalcification Detection Using Wavelet Transform

Abu-Baker¹

2014

IJCTE

View full text Add to dashboard Cite

I. INTRODUCTIONBreast cancer is the most common type of cancer among women [1]. Some important signs of breast cancer that radiologists are seeking to find are microcalcifications (MCs), masses, and structural disorders. MCs are observed in mammograms as white spots varying in size and shape. Mammography as a screening tool is one of the best proven technique for early breast cancer detection. Mammographic image analysis is a complicated and difficult task which requires opinion of highly trained radiologists. Detection of MCs, a possible symptom of breast cancer is a complex task because of the inhomogeneous background and the high noise level in the images due to emulsion artifacts. The MCs has important characteristics in their size, shape/morphology, amount, and distribution. Their sizes vary from 0.1 mm to 1 mm [2]. MC detection is very difficult in mammographies with overlapping breast tissues or high breast tissue density. Moreover, low contrast MCs can be perceived as noise while comparing them with the nonhomogeneous background. MCs are observed in mammograms individually or in clusters. Clustered MCs are more likely to be malignant. A cluster is defined as a group consisting of 3 or more MCs in a 1-cm 2 area. As proposed in this study, many computer-aided detection systems have been developed for MCs.There are problems with the subjective analysis of mammographic images by radiologist. Subjective analysis depends mainly of the experience of the human operator, but Manuscript received February 4, 2014; revised April 16, 2014. Ayman A. AbuBaker is with the Electrical and Computer Engineering Department, Applied Science University, Amman, Jordan (e-mail: a_abubaker@asu.edu.jo).it is also affected by fatigue and other human-related factors. Since, the interpretation is a repetitive task that requires lot of attention to minute details, it requires lot of staff time and effort, which results in increasing diagnosis time. On the other hand, the objective analysis of mammograms, which is carried out by automated systems, provides consistent performance but its accuracy is usually lower. Due to the sensitivity of this problem, I believe that radiologists should be involved and computers should not replace them completely. However, computer systems can help them perform better by enhancing the quality of images, highlighting the suspicious regions and providing better analysis tools.For these reasons, computer-aided diagnoses (CAD) are exciting a great deal of attention from the radiologist community [3], [4]. CAD is defined as a diagnosis made by a physician taking into account the computer output as a second opinion. The goal of applying CAD is to support radiologists' image interpretation and improve the diagnostic accuracy and consistency [4], [5].Many authors have implemented a variety of CAD algorithms to detect the MCs in the mammogram images, with a range of success. This paper presents a new algorithm that can detect the MCs in the mammogram images accurately. This algorithm uses several unique charact...

show abstract

Detection of single and clustered microcalcifications in mammograms using fractals models and neural networks

Cited by 99 publications

References 23 publications

Sparse Representation for Detection of Microcalcification Clusters

Sparse Representation for Detection of Microcalcification Clusters

Classification algorithms for microcalcifications in mammograms (Review)

Automatic Microcalcification Detection Using Wavelet Transform

Contact Info

Product

Resources

About