Application of the mutual information criterion for feature selection in computer-aided diagnosis

Medical Physics

Volumn 28, Issue 12, 2001, Pages 2394-2402

  Tourassi, Georgia D ^a   Frederick, Erik D ^b   Markey, Mia K ^c   Floyd, Carey E ^a  

^a DUKE UNIVERSITY MEDICAL CENTER   (United States)

^b ChemCodes Inc ^*  (United States)

^c Duke University   (United States)

Author keywords

Acute pulmonary embolism; Computer assisted diagnosis; Feature selection; Mutual information

Indexed keywords

DISCRIMINANT ANALYSIS; DISEASES; FEATURE SELECTION; GENETIC ALGORITHMS; INFORMATION THEORY;

ACUTE PULMONARY EMBOLISMS; COMPUTER ASSISTED DIAGNOSIS; FEATURES SELECTION; INFORMATION CRITERION; INFORMATION-THEORETIC APPROACH; LINEAR RELATIONSHIPS; MUTUAL INFORMATION MEASURES; MUTUAL INFORMATIONS; SELECTION TECHNIQUES; STATISTICAL TEXTURE FEATURES;

COMPUTER AIDED DIAGNOSIS;

ARTICLE; COMPUTER ANALYSIS; COMPUTER ASSISTED DIAGNOSIS; COMPUTER NETWORK; HUMAN; INFORMATION PROCESSING; LINEAR SYSTEM; LUNG EMBOLISM; MEDICAL DECISION MAKING; NONLINEAR SYSTEM; PRIORITY JOURNAL;

EID: 0035661275     PISSN: 00942405     EISSN: None     Source Type: Journal    
DOI: 10.1118/1.1418724     Document Type: Article

References (39)

1. Computer-aided diagnosis of breast cancer: Artificial neural network approach for optimized merging of mammographic features
2. Feature-selection in the pattern classification problem of digital chest radiograph segmentation
3. Image feature selection by a genetic algorithm: Application to classification of mass and normal breast tissue
4. Improved noninvasive diagnosis of acute pulmonary embolism using optimally selected clinical and chest radiographic findings
5. Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces
6. Design of a high-sensitivity classifier based on a genetic algorithm: Application to computer-aided diagnosis
7. Feature selection for computerized mass detection in digitized mammograms by using a genetic algorithm
8. A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: Preliminary results
9. Stepwise discriminant analysis
10. Automated three-dimensional registration of magnetic resonance and positron emission tomography brain images by multiresolution optimization of voxel similarity measures
11. A regional registration technique for automated interval change analysis of breast lesions on mammograms
12. Image registration by maximization of combined mutual information and gradient information
13. Improved efficiency for MRI-SPET registration based on mutual information
14. 3D spatial compounding of ultrasound images using image-based nonrigid registration
15. Spatial registration of digital brain atlases based on fuzzy set theory
16. Registration, segmentation, and visualization of multimodal brain images
17. Using mutual information for selecting features in supervised neural net learning
18. Radial basis function network configuration using mutual information and the orthogonal least squares algorithm
19. Information-theoretic algorithm for feature selection
20. Mutual information functions versus correlation functions
21. Relevance of time frequency features for phonetic and speaker-channel classification
22. Ventilation-perfusion scintigraphy in the PIOPED study: Part I. Data collection and tabulation
23. Value of the ventilation/perfusion scan in acute pulmonary embolism: Results of the prospective investigation of pulmonary embolism diagnosis (PIOPED)
24. Multifractal texture analysis of perfusion lung scans as a computer aid for acute pulmonary embolism
25. Textural features for image classification
26. Statistical and structural approaches to texture
27. Classifier design for computer-aided diagnosis: Effects of finite sample size on the mean performance of classical and neural network classifiers
28. Feature selection and classifier performance in computer-aided diagnosis: The effect of finite sample size
29. Training feed-forward networks with the Marquardt algorithm
30. The upward bias in measures of information derived from limited data samples
31. Independent coordinates for strange attractors from mutual information
32. Estimation of the information by an adaptive partitioning of the observation space
33. An estimator of the mutual information based on a criterion for independence
34. Feature selection with limited datasets