Eliminating false-positive microcalcification clusters in a mammography CAD scheme using a Bayesian neural network

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 4322, Issue 3, 2001, Pages 1954-1960

  Edwards, D C ^a   Papaioannou, J ^a   Jiang, Y ^a   Kupinski, M A ^a   Nishikawa, R M ^a  

^a UNIVERSITY OF CHICAGO   (United States)

Author keywords

Bayesian artificial neural networks; CAD; Clustered microcalcifications; Ideal observer approximation; Mammography

Indexed keywords

APPROXIMATION THEORY; CALCIFICATION (BIOCHEMISTRY); COMPUTER AIDED DIAGNOSIS; NEURAL NETWORKS;

BAYESIAN NEURAL NETWORKS (BNN);

MAMMOGRAPHY;

EID: 0034855208     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.431089     Document Type: Conference Paper

References (10)

1. Performance of automated CAD schemes for the detection and classification of clustered microcalcifications
2. An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms
3. Using a Bayesian neural network to optimally eliminate false-positive microcalcification detections in a CAD scheme
4. Ideal observer approximation using Bayesian classification neural networks
5. Malignant and benign clustered microcalcifications: Automated feature analysis and classification
6. Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data
7. Analysis of methods for reducing false positives in the automated detection of clustered microcalcifications in mammograms
8. Finite-sample dependence of classifier assessment in computer-aided diagnosis
9. Classifier design for compurer-aided diagnosis: Effects of finite sample size on the mean performance of classical and neural network classifiers