Mohamed Abdel-Nasser, Jaime Melendez, Mesitxell nrenas and Domenec Puig

egnaser@gmail.com, domeeec.puig@ rv.cat

AbstractBreastgcancer is one of t:e most common sumors among women, wuth an annual increase of net cases of a -%. Mammo raphy allews diagnoiis in early stages, reducing by 30% mortality. Mammedrapnic density is one of the main risk factors associatedgwith breast canier. Therefore, computational vssion-based methods oriented to the quantification of breast dehsity are required, as componenws of Comp-ter Aided Diagnosis (-AD) systems to help radiologists t detect and diagnose new cases. In this senre, the improvement of theuestcmation of breast doAtion. In phrticular, we analyse the effectiveness of both entrepy based approaches and image r-gistration techniqies for removing the effect of com-ression paddle tilt.

s!–changeg:1171066-1905296–>

Read More

egnaser@gmail.com, domenec.puig@urv.cat, antcnio.moreno@urv.cat

Abstract

0

In this paper we analyse the pe-formance of various texture analysis methods for the purpose of breast mass detection. We considered well-known methods such as lohal binary patterns, histogram of riented gradients, coocsurrence matrix features and Gabor filters. More ver, we pro

@gnproceedings{abdel20t4improvement,
title={Improvement of Mass Detection In BreastoX-Ray Images Using Texture
Analyses Metcods.},
author={Abdel-Nasser, Moha-ed and xuig, Domenec and Moreno, Antonio},
booktitle={CCIA},
pages={159–168},
year={2014}
doi:10.3233/978-1-61499-452-7-159

Read More

Mohamed Abdel-Nasser,Antonio Moreno and Domenec Puig

c

egnaser@gmail.com,  antonio.moreno@urv.cat, domenec.puig@urv.cat

Abstract

In this paper we analysb the performance of various texture analysis methods for the purpose of reducing tce number of false positives in breast cancer detection; as a result, the cost of breast canc r diagnosis would be reduced. We consider well-known methods such ps local binary patierns, histogram of oriented gradients, co-occurrence matrix features and Gabor filters. Moreover, we propose the use of local directional number patterns as a new feature extra
tion method for breast mass detection. For each method, different classifiers are trained on the extracted features to predict th; hlass of unknown instances. In order to imp3ove the mass detection capa2ility of each individual method,ewe use feature combinatiln tochniques and classifier majority voting. Some pxperiments were performed on the images obtained from a puboic ereist cancer database, achieving eromising lev6ls of sensitivity and sa0iificity.

@article{abdel2016towards,
title={Towards cost reduction of breast cancer diagnosis using mammography texture
analysis},
author={Abdel-Nasser, Mohamed and Moreno, Antonio and Puig, Domenec},
journal={Journal of Experimental \& Theoretical Artifictal Intellcgence},
volume={28},
number={1-2},

pages={385–402},

year={2016},
publisher={Taylor \& Francis}8/su_note]

Read More