Computer-assisted diagnosis of breast cancer using a data-driven Bayesian belief network

Wang, Xiaohui; Zheng, Bin; Good, Walter F.; King, John A.; Chang, Yuan‐Hsiang

doi:10.1016/s1386-5056(98)00174-9

Cited by 69 publications

(39 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some literatures, such as [5,13], supposed features of breast tumor were independent. According to this assumption, we trained and tested Naïve Bayes (NB) model also based on 5-fold cross validation.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian network modelling on data from fine needle aspiration cytology examination for breast cancer diagnosis

Ding¹,

Cao²,

Zhai³

et al. 2017

Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017

View full text Add to dashboard Cite

Abstract:The paper employed Bayesian network (BN) modelling approach to discover causal dependencies among different data features of Breast Cancer Wisconsin Dataset (BCWD) derived from openly sourced UCI repository. K2 learning algorithm and k-fold cross validation were used to construct and optimize BN structure. Compared to Naïve Bayes (NB), the obtained BN presented better performance for breast cancer diagnosis based on fine needle aspiration cytology (FNAC) examination. It also showed that, among the available features, bare nuclei most strongly influences diagnosis due to the highest strength of the influence (0.806), followed by uniformity of cell size, then normal nucleoli. The discovered causal dependencies among data features could provide clinicians to make an accurate decision for breast cancer diagnosis, especially when some features might be missing for specific patients. The approach can be potentially applied to other disease diagnosis.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Kalet et al [4] used a Bayesian model to detect misdiagnoses made at the initial stage of diseases, such as lung, brain and female breast cancer. Wang et al [5] proposed a three-layer BN for the earlier diagnosis of breast cancer. Hassen et al [6] used Bayesian network to estimate the risk of metastasis for breast cancer patients.…”

Section: Introductionmentioning

confidence: 99%

Bayesian network modelling on data from fine needle aspiration cytology examination for breast cancer diagnosis

Ding¹,

Cao²,

Zhai³

et al. 2017

Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017

View full text Add to dashboard Cite

show abstract

“…3). BBN is a popular statistical learning method that has been investigated and applied in a number of CAD schemes for detecting breast cancer [30][31][32]. One unique advantage of the BBN approach is that the topology of the BBN represents the joint probability distribution of a problem domain by exploiting the dependencies between variables and capturing the knowledge of a given problem in a natural and efficient way [33].…”

Section: A Bayesian Belief Networkmentioning

confidence: 99%

“…To compute these joint probabilities, each node (feature) must be represented by a relatively small number of discrete states. In our study, one feature computed from all training samples was divided into five discrete states with equal sample distribution [31]. Since the decision node (case classification in Fig.…”

Section: A Bayesian Belief Networkmentioning

confidence: 99%

Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts

Yang

Zhang

et al. 2013

J Digit Imaging

View full text Add to dashboard Cite

Dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) of breasts is an important imaging modality in breast cancer diagnosis with higher sensitivity but relatively lower specificity. The objective of this study is to investigate a new approach to help improve diagnostic performance of DCE-MRI examinations based on the automated detection and analysis of bilateral asymmetry of characteristic kinetic features between the left and right breast. An image dataset involving 130 DCE-MRI examinations was assembled and used in which 80 were biopsyproved malignant and 50 were benign. A computer-aided diagnosis (CAD) scheme was developed to segment breast areas depicted on each MR image, register images acquired from the sequential MR image scan series, compute average contrast enhancement of all pixels in one breast, and a set of kinetic features related to the difference of contrast enhancement between the left and right breast, and then use a multifeature based Bayesian belief network to classify between malignant and benign cases. A leave-one-case-out validation method was applied to test CAD performance. The computed area under a receiver operating characteristic (ROC) curve is 0.78±0.04. The positive and negative predictive values are 0.77 and 0.64, respectively. The study indicates that bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy. It also demonstrates the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations based on this new image biomarker.

show abstract

“…(Wang et al, 1999) Mejora la detección del cáncer de mama a partir de la mamografía, en un porcentaje superior al 80%, al emplear una red bayesiana simple, en vez de combinaciones hibridas de redes independientes, en la cual se integra la imagen y las características que no son imagen. (Abbass, 2002) Diseña una red artificial para la predicción del cáncer de mama.…”

Section: Introductionunclassified

Sistema Predictivo Bayesiano para Detección del Cáncer de Mama

2018

View full text Add to dashboard Cite

_____________________________________________________________________________________________________________________________________ ResumenSe propone un método predictivo para detectar el cáncer de mama, basado en las siguientes variables: edad, peso, talla, índice de masa corporal, escolaridad, estrato socioeconómico, seguridad social, fumador, cuando dejo de fumar, fumador pasivo, consume licor, cantidad de licor, herencia familiar de cáncer, edad de la menarca, menopausia, embarazos, partos, edad del primer parto, lactancia, consumo de anticonceptivos orales, cuanto años consumió anticonceptivos orales, tiempo de suspensión de anticonceptivos orales, terapia de reemplazo hormonal y presencia del gen GSTM1. Tomando como referencias pacientes de la región central de Colombia (Caldas), se definieron dos bases de datos, una de personas sin cáncer y otra de personas con cáncer. La misma base de datos de entrenamiento fue empleada para prueba. La metodología propuesta, define y entrena un sistema de clasificación bayesiano, con una base de datos de pacientes con cáncer y sin cáncer. Posteriormente, se realiza una validación del sistema con el fin de determinar el número de aciertos y errores en el reconocimiento de esta enfermedad. Como resultado, se logra un porcentaje de aciertos del 100%. Palabras clave: clasificador bayesiano; cáncer de mama; entrenamiento; detección automatizada de enfermedades Bayesian Predictive System for Detection of Breast Cancer AbstractWe propose a predictive method to detect breast cancer, based on the following variables: Age, weight, height, body mass index, schooling, socioeconomic stratum, social security, smoker, when quit smoking, passive smoker, consumption of liquor, quantity of liquor, family inheritance of cancer, age of menarche, menopause, pregnancies, age of first birth, breastfeeding, consumption of oral contraceptives, how many years of oral contraceptive use, oral contraceptive suspension time, hormone replacement therapy, and the presence of the GSTM1 gene. Taking as reference patients from the central region of Colombia (Caldas), two databases were defined, one of people without cancer and another of people with cancer. The same training database was used for testing. The proposed methodology defines and trains a Bayesian classification system, with a database of patients with cancer and without cancer. Subsequently, a system validation is performed in order to determine the number of successes and errors in the recognition of this disease. As a result, a 100% success rate is achieved.

show abstract

Computer-assisted diagnosis of breast cancer using a data-driven Bayesian belief network

Cited by 69 publications

References 25 publications

Bayesian network modelling on data from fine needle aspiration cytology examination for breast cancer diagnosis

Bayesian network modelling on data from fine needle aspiration cytology examination for breast cancer diagnosis

Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts

Sistema Predictivo Bayesiano para Detección del Cáncer de Mama

Contact Info

Product

Resources

About