A Computer-Aided Diagnosis System for the Detection and Classification of Breast Cancer

doi:10.1097/JCE.0000000000000160

Home
/
Papers
/
A Computer-Aided Diagnosis System for the Detection and Classification of Breast Cancer

Journal Article•DOI•

A Computer-Aided Diagnosis System for the Detection and Classification of Breast Cancer

Sahar Haj Ali A. Mohammed, Soha Ekrima K. Yousuf

01 Apr 2016-Journal of clinical engineering (Ovid Technologies (Wolters Kluwer Health))-Vol. 41, Iss: 2, pp 96-100

TL;DR: Results demonstrated that the proposed methodologies have high potential localizing, detecting, and classifying the breast tumor and have proved to effectively discriminate between malignant and benign tumors with an effective level of precision.

read less

Abstract: Breast cancer is currently the foremost cause in women’s mortality worldwide. In Sudan, the increasing incidence, detection at late stages, and the early onset of the disease make early detection and diagnosis of breast cancer an overbearing task. The objective of this study is to create an automated computer interfacing system for the localization, detection, and classification of breast mass. This study is implemented using MATLAB software. A Graphical User Interface is designed for the implemented algorithm. Results demonstrated that the proposed methodologies have high potential localizing, detecting, and classifying the breast tumor. The system was able to achieve an accuracy of 88% sensitivity, 72% specificity, an Az value of 0.84, and an overall classification accuracy of 80%. The created systems have therefore proved to effectively discriminate between malignant and benign tumors with an effective level of precision.

...read moreread less

Citations

PDF

Open Access

More filters

Journal Article•DOI•

Fuzzy PGA filter technique performance on the mini-MIAS database of mammograms

[...]

Estibaliz Parcero, D. Segrelles, Vicente Vidal¹, Gumersindo Verdú•Institutions (1)

Polytechnic University of Valencia¹

17 Nov 2015-The International Journal on the Image

TL;DR: This part of the study focused on validating the stability of the fuzzy peer group averaging technique for its use in mammograms by demonstrating its effectiveness regardless of the case.

...read moreread less

Abstract: Medical image processing promises major advances in medicine as higher fidelity images are produced, e.g., filters improve image quality to facilitate diagnosis or reduce radiation absorption. We evaluated the fuzzy peer group averaging technique in terms of effectiveness and stability. Effectiveness was measured by applying the filter to a set of mammograms and comparing the results to the obtained by different methods. This technique obtained the best peak signal-to-noise ratio values. Stability means that a filter applied to a mammogram must perform adequately in any case regardless of the type of tissue, the class of abnormality, and the severity. Thus, this part of the study focused on validating the stability of the fuzzy peer group averaging technique for its use in mammograms by demonstrating its effectiveness regardless the case. The normal distribution of the peak signal-to-noise ratio in the frequency histograms obtained validated this assumption.

...read moreread less

29 citations

Book Chapter•DOI•

Computer Aided Diagnosis of Early Breast Cancer by Multimodal Imaging

[...]

Jingsi Xie¹•Institutions (1)

Penn State College of Communications¹

28 Feb 2020

TL;DR: Combining the multimodal imaging and computer aided, used in the diagnosis of early breast cancer, and to analyze the results, aims to improve the diagnosed rate and quality, providing certain theoretical basis for related research.

...read moreread less

Abstract: Breast cancer is one of the common tumors threatening women’s health, early detection and treatment is an important way to improve the cure rate of breast cancer and save the lives of patients. In recent years, with the development of sequencing technology and pathological image technology, a large number of multimodal data of omics and pathological image have been accumulated. The introduction of the above multi-modal data in early breast cancer research can greatly improve the cure rate of breast cancer. Therefore, how to effectively integrate the above multi-modal data is an urgent problem in the field of early breast cancer diagnosis. In addition, computer-aided diagnosis is one of the important applications of medical imaging. It helps doctors to draw conclusions on reading films through automatic detection and recognition, effectively solves the problem of easy fatigue and uneven professional skills of doctors, and has great application value in medical diagnosis. So based on related literature, technology and academic research on the basis of the analysis, combining the multimodal imaging and computer aided, used in the diagnosis of early breast cancer, and to analyze the results, aims to improve the diagnosis of early breast cancer rate and quality, providing certain theoretical basis for related research.

...read moreread less

References

PDF

Open Access

More filters

Journal Article•DOI•

Computer-aided detection and classification of microcalcifications in mammograms: a survey

[...]

Heng-Da Cheng¹, Xiaopeng Cai¹, Xiaowei Chen¹, Liming Hu¹, Xueling Lou¹ - Show less +1 more•Institutions (1)

Utah State University¹

01 Dec 2003-Pattern Recognition

TL;DR: The high correlation between the appearance of the microcalcification clusters and the diseases show that the CAD (computer aided diagnosis) systems for automated detection/classification of MCCs will be very useful and helpful for breast cancer control.

...read moreread less

563 citations

"A Computer-Aided Diagnosis System f..." refers methods in this paper

...The training data are repeatedly presented to the neural network and weights are adjusted until the MSE is reduced to an acceptable value.(10,15,16) The constructed neural network consists of 6 input neurons for the extracted features....
[...]

Journal Article•DOI•

Approaches for automated detection and classification of masses in mammograms

[...]

Heng-Da Cheng¹, X. J. Shi¹, R. Min¹, Liming Hu¹, Xiaopeng Cai¹, H. N. Du¹ - Show less +2 more•Institutions (1)

Utah State University¹

01 Apr 2006-Pattern Recognition

TL;DR: The methods for mass detection and classification for breast cancer diagnosis are discussed, and their advantages and drawbacks are compared.

...read moreread less

526 citations

"A Computer-Aided Diagnosis System f..." refers background or methods in this paper

...The ROI begins as a single pixel, the ‘‘seed,’’ and grows iteratively, aggregating with the pixels that have similar intensity and local contrast.(3,5) In this study, the seed point was selected according to the radiologist’s expertise....
[...]
...1% for regionally advanced and metastatic cancer, respectively.(2,3) Of the many breast cancer lesions, masses and microcalcifications are the most important indicators of malignancy, and their detection is integral for early breast cancer diagnosis....
[...]
...The difficulty in detecting masses is a greater challenge because of its form of natural growth from within the epithelial and connective tissues of the breast, making it similar or obscured to normal breast parenchyma.(3) Mass classification using a combination of support vector machine, radial basis function, kernel and waveletbased feature extraction was achieved by Gorgel et al....
[...]

Book•DOI•

Intelligent Control Systems Using Soft Computing Methodologies

[...]

Ali Zilouchian, Mohammad Jamshidi

01 Dec 2000

TL;DR: Intelligent Control Systems explores recent advances in the field from both the theoretical and the practical viewpoints and integrates intelligent control design methodologies to give designers a set of flexible, robust controllers and providestudents with a tool for solving the examples and exercises within the book.

...read moreread less

Abstract: From the Publisher: In recent years, intelligent control has emerged as one of the most active and fruitful areas of research and development. Until now, however, there has been no comprehensive text that explores the subject with focus on the design and analysis of biological and industrial applications. Intelligent Control Systems Using Soft Computing Methodologies does all that and more. Beginning with an overview of intelligent control methodologies, the contributors present the fundamentals of neural networks, supervised and unsupervised learning, and recurrent networks. They address various implementation issues, then explore design and verification of neural networks for a variety of applications, including medicine, biology, digital signal processing, object recognition, computer networking, desalination technology, and oil refinery and chemical processes.The focus then shifts to fuzzy logic, with a review of the fundamental and theoretical aspects, discussion of implementation issues, and examples of applications, including control of autonomous underwater vehicles, navigation of space vehicles, image processing, robotics, and energy management systems. The book concludes with the integration of genetic algorithms into the paradigm of soft computing methodologies, including several more industrial examples, implementation issues, and open problems and open problems related to intelligent control technology.Suited as both a textbook and a reference, Intelligent Control Systems explores recent advances in the field from both the theoretical and the practical viewpoints. It also integrates intelligent control design methodologies to give designers a set of flexible, robust controllers and providestudents with a tool for solving the examples and exercises within the book.

...read moreread less

252 citations

"A Computer-Aided Diagnosis System f..." refers methods or result in this paper

...Furthermore, the Az value obtained for this study is within the specified range of 0.80 to 0.90 for mammography analysis as stated by Zilouchian.13 The SE of the classifier obtained is recorded at an even higher value than that obtained in the works of Campanini et al,17 who scored an SE of 84%....
[...]
...90 for mammography analysis as stated by Zilouchian.(13) The SE of the classifier obtained is recorded at an even higher value than that obtained in the works of Campanini et al,(17) who scored an SE of 84%....
[...]
...The following 6 extracted features were used as the classifier’s inputs: entropy, sum entropy, difference variance, energy, contrast, and dissimilarity.(12,13)...
[...]

Posted Content•

Early Detection of Breast Cancer using SVM Classifier Technique

[...]

Y. Ireaneus Anna Rejani, S. Thamarai Selvi

11 Dec 2009-arXiv: Learning

TL;DR: A tumor detection algorithm from mammogram that focuses on the solution of two problems, how to detect tumors as suspicious regions with a very weak contrast to their background and how to extract features which categorize tumors.

...read moreread less

Abstract: This paper presents a tumor detection algorithm from mammogram. The proposed system focuses on the solution of two problems. One is how to detect tumors as suspicious regions with a very weak contrast to their background and another is how to extract features which categorize tumors. The tumor detection method follows the scheme of (a) mammogram enhancement. (b) The segmentation of the tumor area. (c) The extraction of features from the segmented tumor area. (d) The use of SVM classifier. The enhancement can be defined as conversion of the image quality to a better and more understandable level. The mammogram enhancement procedure includes filtering, top hat operation, DWT. Then the contrast stretching is used to increase the contrast of the image. The segmentation of mammogram images has been playing an important role to improve the detection and diagnosis of breast cancer. The most common segmentation method used is thresholding. The features are extracted from the segmented breast area. Next stage include, which classifies the regions using the SVM classifier. The method was tested on 75 mammographic images, from the mini-MIAS database. The methodology achieved a sensitivity of 88.75%.

...read moreread less

136 citations

Journal Article•DOI•

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

[...]

Leonardo Bocchi¹, Giuseppe Coppini, J. Nori, Guido Valli¹•Institutions (1)

University of Florence¹

01 May 2004-Medical Engineering & Physics

TL;DR: Results indicate that fractal models provide an adequate framework for medical image processing; consequently high correct classification rates are achieved.

...read moreread less

118 citations

"A Computer-Aided Diagnosis System f..." refers background or methods in this paper

...Regardless, different E-SP tradeoffs can be obtained by changing the classification criterion.(12) The classification performance obtained in this study with an Az value of 0....
[...]
...The following 6 extracted features were used as the classifier’s inputs: entropy, sum entropy, difference variance, energy, contrast, and dissimilarity.(12,13)...
[...]