2008
DOI: 10.1007/978-3-540-85920-8_56
|View full text |Cite
|
Sign up to set email alerts
|

Computer Aided Diagnosis System to Detect Breast Cancer Pathological Lesions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2011
2011
2018
2018

Publication Types

Select...
4
2

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 9 publications
0
5
0
Order By: Relevance
“…ANNs are seamless representation and classification models that learn simultaneously an appropriate hidden representation of the input data and a discriminative model that connects these hidden representations with the discriminant information. Recently, ANNs have grabbed attention in many areas, such as biomedicine [31], mainly for two reasons: the very good results obtained in real problems such as image recognition or natu-285 ral language processing; and the possibility to train them with very large data sets on clusters of graphical processing units (GPUs). In contrast to other classification problems, fraud detection entails a very difficult detection problem: first, it is an extremely unbalanced problem where the ratio between gen-290 uine and fraudulent transactions is greater than 5, 000 : 1; second, fraudulent transactions use to mimic genuine transactions in order to avoid being detected.…”
Section: Methodsmentioning
confidence: 99%
“…ANNs are seamless representation and classification models that learn simultaneously an appropriate hidden representation of the input data and a discriminative model that connects these hidden representations with the discriminant information. Recently, ANNs have grabbed attention in many areas, such as biomedicine [31], mainly for two reasons: the very good results obtained in real problems such as image recognition or natu-285 ral language processing; and the possibility to train them with very large data sets on clusters of graphical processing units (GPUs). In contrast to other classification problems, fraud detection entails a very difficult detection problem: first, it is an extremely unbalanced problem where the ratio between gen-290 uine and fraudulent transactions is greater than 5, 000 : 1; second, fraudulent transactions use to mimic genuine transactions in order to avoid being detected.…”
Section: Methodsmentioning
confidence: 99%
“…Several types of extracted features (e.g. intensity statistics, shape and texture) from mammograms have been combined to form subsets of features, which extensively provided significant information for lesions classification [32] [33] [34] [35]. However, selecting the most appropriate subset of features is still a very difficult task; usually a satisfactory instead of the optimal feature subset is searched.…”
Section: B Feature Selection Methodsmentioning
confidence: 99%
“…Machine Learning Classifier (MLC) approaches have been reported in the past few years for mammography images analysis and classification with different degrees of success [6,7,19,[21][22][23][24][25][26][27][28][29][30] (see discussion in Section 3). In this work we consider SVM and ANN based MLC.…”
Section: Machine Learning Classifiers Explorationsmentioning
confidence: 99%
“…For research scientists, there are several interesting research topics in cancer detection and diagnosis systems, such as high-efficiency, high-accuracy lesion detection algorithms, including the detection of calcifications and masses, architectural distortions, bilateral asymmetries, etc. [6,7]. Radiologists, on the other hand, are paying more attention to the effectiveness of clinical applications of CAD methods.…”
Section: Introductionmentioning
confidence: 98%