Improving mass candidate detection in mammograms via feature maxima propagation and local feature selection

Melendez, Jaime; Sánchez, Clara I.; Ginneken, Bram van; Karssemeijer, Nico

doi:10.1118/1.4885995

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Texture is one of the major mammographic characteristics for mass classification. For instance, several studies have used texture analysis methods to distinguish between normal and abnormal tissue [3][4][5][6][7][8] or to discriminate between benign and malignant masses [9][10][11]. Table 1 briefly summarizes some of this previous work.…”

Section: Introductionmentioning

confidence: 99%

The Impact of Pixel Resolution, Integration Scale, Preprocessing, and Feature Normalization on Texture Analysis for Mass Classification in Mammograms

Abdel-Nasser

Melendez

Moreno

et al. 2016

International Journal of Optics

Self Cite

View full text Add to dashboard Cite

Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

The Impact of Pixel Resolution, Integration Scale, Preprocessing, and Feature Normalization on Texture Analysis for Mass Classification in Mammograms

Abdel-Nasser

Melendez

Moreno

et al. 2016

International Journal of Optics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some of them are presented by Fonseca in 2013 (40), who revealed accuracies of 52.73% for dense and 51.60% for fatty tissue; and Melendez (48) who increased the mean sensitivity from 0.926 to 0.948 on detecting breast lesions by using RF. …”

Section: Random Forestmentioning

confidence: 99%

Using Data Mining Techniques to Support Breast Cancer Diagnosis

Diz

Marreiros

2015

New Contributions in Information Systems and Technologies

View full text Add to dashboard Cite

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method.In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis.In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings.Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix.For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests).The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS ® scale.The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications.The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques. VIII IX ResumoCada vez mais assistimos a um aumento global do número de métodos de apoio a decisão e diagnóstico assistido por computador, aplicados a diversas áreas da medicina.Na área de investigação do cancro da mama muitos são os trabalhos que têm sido desenvolvidos como segunda leitura de modo a reduzir o número de falsos positivos no diagnóstico.Neste estudo é apresentado um conjunto de técnicas de data mining que poderão ser aplicadas a um sistema de apoio à decisão na área do diagnóstico de cancro da mama.Esta abordagem tem por objetivo ajudar os clínicos na identificação de achados mamográficos como microcalcificações, massas e mesmo tecidos normais, de forma a evitar diagnósticos errados.Para isso, neste trabalho é usada uma base de dados fidedigna, de 410 imagens correspondentes a 115 pacientes, contendo análises prévias, realizadas por radiologistas, de microcalcificações, massas e tecidos considerados normais.Ao longo deste trabalho são utilizadas duas técnicas de extração de características, a matriz de coocorrência de níveis de cinza e a matriz de comprimento da linha de níveis de cinza.

show abstract