Selection of an optimal neural network architecture for computer-aided detection of microcalcifications - Comparison of automated optimization techniques

Medical Physics

Volumn 28, Issue 9, 2001, Pages 1937-1948

  Gurcan, M N ^a   Sahiner, B ^a   Chan, H P ^a   Hadjiiski, L ^a   Petrick, N ^a  

^a UNIVERSITY OF MICHIGAN MEDICAL SCHOOL   (United States)

Author keywords

Computer aided diagnosis; Convolution neural network; Mammography; Microcalcification; Optimization algorithm

Indexed keywords

AUTOMATION; CALCIFICATION (BIOCHEMISTRY); COMPUTER AIDED DIAGNOSIS; COMPUTER AIDED NETWORK ANALYSIS; COMPUTER ARCHITECTURE; CONVOLUTION; COST FUNCTIONS; GENETIC ALGORITHMS; GLOBAL OPTIMIZATION; MAMMOGRAPHY; NEURAL NETWORKS; SIMULATED ANNEALING; STEEPEST DESCENT METHOD;

AUTOMATED OPTIMIZATION METHOD; COMPUTER AIDED DETECTION; COMPUTER AIDED DIAGNOSIS(CAD); CONVOLUTION NEURAL NETWORK; MICROCALCIFICATIONS; OPTIMIZATION ALGORITHMS; PRE-SCREENING ALGORITHMS; RECEIVER OPERATING CHARACTERISTIC CURVES;

NETWORK ARCHITECTURE;

ALGORITHM; ARTICLE; AUTOMATION; BRAIN CALCIFICATION; COMPUTER ASSISTED DIAGNOSIS; COST; DIAGNOSTIC ACCURACY; DISEASE CLASSIFICATION; HUMAN; INTERMETHOD COMPARISON; NERVE CELL NETWORK; PRIORITY JOURNAL; RECEIVER OPERATING CHARACTERISTIC; VALIDATION PROCESS;

EID: 0034801275     PISSN: 00942405     EISSN: None     Source Type: Journal    
DOI: 10.1118/1.1395036     Document Type: Article

References (26)

1. Computer-aided detection of mammographic microcalcifications: Pattern recognition with an artificial neural network
2. Artificial convolution neural network for medical image pattern recognition
3. Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images
4. Neural network architecture selection: New Bayesian perspectives in predictive modeling. Application to a soil hydrology problem
5. Constructive algorithms for structure learning in feedforward neural networks for regression problems
6. Pruning algorithms-a review
7. Architecture selection strategies for neural networks: Application to corporate bond rating prediction
8. Prediction risk and architecture selection for neural networks
9. Genetic evolution of the topology and weight distribution of neural networks
10. An evolutionary algorithm that constructs recurrent neural networks
11. Neocognitron: A neural network model for a mechanism of visual pattern recognition
12. ROC analysis applied to the evaluation of medical imaging techniques
13. Maximum-likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data
14. Optimization by simulated annealing
15. Stochastic relaxation, Gibbs distribution and the Bayesian restoration in images
16. Fast simulated annealing
17. Very fast simulated re-annealing
18. Genetic algorithms: A general search procedure
19. Genetic algorithms and very fast simulated reannealing: A comparison
20. When will a genetic algorithm outperform hill climbing?