A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis

Cong, Jinyu; Wei, Benzheng; He, Yunlong; Yin, Yilong; Zheng, Yuanjie

doi:10.1155/2017/4896386

Cited by 29 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cong et al presented a selective methodology for diagnosing breast cancer in ultrasound and mammogram images. The developed selective methodology was integrated with the classifiers, ie, KNN, SVM and Naïve Bayes (NB) for diagnosing the breast cancer.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Detection and classification of normal and abnormal patterns in mammograms using deep neural network

Suresh

Rao

Reddy

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary Breast cancer detection is the most challenging aspect in the field of health monitoring system. In this paper, breast cancer detection was assessed by employing Mammographic Image Analysis Society (MIAS) dataset. The proposed approach contains four major steps, namely, image‐preprocessing, segmentation, feature extraction, and classification. Initially, Laplacian filtering was utilized to identify the area of edges in mammogram images and, also, it was very sensitive to noise. Then, segmentation was carried‐out using modified‐Adaptively Regularized Kernel‐based Fuzzy‐C‐Means (ARKFCM); it was a flexible high level machine learning technique to localize the object in complex template. In conventional ARKFCM, it was hard to segment the ill‐defined masses in mammogram images. To address this concern, the Euclidean distance in ARKFCM was replaced by correlation function in order to improve the segmentation efficiency. The hybrid feature extraction (Histogram of Oriented Gradients (HOG), homogeneity, and energy) was performed on the segmented cancer region to extract feature subsets. The respective feature values were given as the input for a multi‐objective classifier: Deep Neural Network (DNN) for classifying the normal and abnormal regions in mammogram images. The experimental outcome shows that the proposed methodology improved accuracy in breast cancer classification up to 3% to 9% compared to other existing methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Additionally, f-measure and accuracy are the suitable evaluation metrics utilized to find the effectiveness of breast cancer detection and classification. The general formula of accuracy and f-measure for determining breast cancer detection and classification are represented in Equations (20) and (21)…”

Section: Performance Metricsmentioning

confidence: 99%

Detection and classification of normal and abnormal patterns in mammograms using deep neural network

Suresh

Rao

Reddy

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The breast cancer detection process was not efficient. A selective ensemble method KNN, SVM, and Naive Bayes were introduced in [8] to detect the breast cancer using both ultrasound images and mammography images. This ensemble method failed to concentrate on the features in images.…”

Section: Related Workmentioning

confidence: 99%

Breast Cancer Detection using Gradient Boost Ensemble Decision Tree Classifier

Ezhilraman¹,

Srinivasan²,

Suseendran³

2019

IJEAT

View full text Add to dashboard Cite

Detection of any abnormalities in the human is a big challenge faced by many of the field experts. One such challenge is to detect the Breast Cancer. The prime mottobehind in making this paper is to detect the breast cancer with the help of breast images in an advanced and appropriate way. In this study, an attempt is made in such a way by applying the combination of various existing technics in the extracted breast images for getting better result in detecting the Breast Cancer. Consequently,feature extracting images are appliedusing Light gradient boosting ensemble decision tree classifier for identifying benign and malign features of an image. As a result, the normal and abnormal breast cancer image is detected by combining above applications. Besides, classification accuracy and minimize classification time metrics are also achieved more appropriately than the existing detectingtechnics.

show abstract

“…Essa neoplasia vem despertando maior atenção na saúde pública, bem como na comunidade científica, onde pesquisadores estão utilizando técnicas de inteligência computacional no desenvolvimento de sistemas de apoio ao diagnóstico por computador (CAD), visando aumentar a taxa de detecção do câncer de mama [4,7,15]. Dentre essas técnicas destacam-se as Redes Neurais Artificiais -RNAs [2,12,17,18] e as Máquinas de Vetores de Suporte -SVMs [3,9,11,14], por serem robustas em um conjunto de dados ruidosos.…”

Section: Introductionunclassified

Predição do Câncer de Mama com Aplicação de Modelos de Inteligência Computacional

Silva

Leal

Lima

2019

Tend. Mat. Apl. Comput.

View full text Add to dashboard Cite

RESUMO. O uso de modelos para diagnóstico auxiliado por computador (CAD) tem sido proposto para auxiliar na detecção e classificação do câncer de mama. Neste trabalho, avaliou-se o desempenho dos modelos de rede neural de perceptrons de múltiplas camadas e máquina de vetores de suporte não linear para classificar nódulos de câncer de mama. Dez características morfológicas, do contorno de 569 amostras, foram usadas como entrada nos classificadores. Os resultados médios obtidos no conjunto das 50 simulações realizadas, mostram que os modelos propostos apresentaram bom desempenho (todos ultrapassaram a 90,0%) em termos da acurácia no conjunto de teste. O algoritmo de máquina de vetor de suporte não linear destacase quando comparado ao algoritmo de rede neural de perceptrons de múltiplas camadas proposto, com acurácia de ≈ 99,0% e taxa de falso negativo de ≈ 2,0%. O modelo de rede neural apresentou desempenho inferior ao classificador de máquina de vetor de suporte não linear. Os resultados médios obtidos, com a aplicação dos modelos propostos, mostram-se promissores, na classificação do câncer de mama.

show abstract

A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis

Cited by 29 publications

References 18 publications

Detection and classification of normal and abnormal patterns in mammograms using deep neural network

Detection and classification of normal and abnormal patterns in mammograms using deep neural network

Breast Cancer Detection using Gradient Boost Ensemble Decision Tree Classifier

Predição do Câncer de Mama com Aplicação de Modelos de Inteligência Computacional

Contact Info

Product

Resources

About