Literature DB >> 9232169

Adequacy testing of training set sample sizes in the development of a computer-assisted diagnosis scheme.

B Zheng1, Y H Chang, W F Good, D Gur.   

Abstract

RATIONALE AND
OBJECTIVES: The authors assessed the performance changes of a computer-assisted diagnosis (CAD) scheme as a function of the number of regions used for training (rule-setting).
MATERIALS AND METHODS: One hundred twenty regions depicting actual masses and 400 suspicious but actually negative regions were selected as a testing data set from a database of 2,146 regions identified as suspicious on 618 mammograms. An artificial neural network using 24 and 16 region-based features as input neurons was applied to classify the regions as positive or negative for the presence of a mass. CAD scheme performance was evaluated on the testing data set as the number of regions used for training increased from 60 to 496.
RESULTS: As the number of regions in the training sets increased, the results decreased and plateaued beyond a sample size of approximately 200 regions. Performance with the testing data set continued to improve as the training data set increased in size.
CONCLUSION: A trend in a system's performance as a function of training set size can be used to assess adequacy of the training data set in the development of a CAD scheme.

Mesh:

Year:  1997        PMID: 9232169     DOI: 10.1016/s1076-6332(97)80236-x

Source DB:  PubMed          Journal:  Acad Radiol        ISSN: 1076-6332            Impact factor:   3.173


  7 in total

1.  Computerized comprehensive data analysis of lung imaging database consortium (LIDC).

Authors:  Jun Tan; Jiantao Pu; Bin Zheng; Xingwei Wang; Joseph K Leader
Journal:  Med Phys       Date:  2010-07       Impact factor: 4.071

2.  Automated identification of analyzable metaphase chromosomes depicted on microscopic digital images.

Authors:  Xingwei Wang; Shibo Li; Hong Liu; Marc Wood; Wei R Chen; Bin Zheng
Journal:  J Biomed Inform       Date:  2007-07-10       Impact factor: 6.317

3.  Optimization of reference library used in content-based medical image retrieval scheme.

Authors:  Sang Cheol Park; Rahul Sukthankar; Lily Mummert; Mahadev Satyanarayanan; Bin Zheng
Journal:  Med Phys       Date:  2007-11       Impact factor: 4.071

4.  Assessment of performance and reliability of computer-aided detection scheme using content-based image retrieval approach and limited reference database.

Authors:  Xiao Hui Wang; Sang Cheol Park; Bin Zheng
Journal:  J Digit Imaging       Date:  2011-04       Impact factor: 4.056

5.  Computer-aided detection of breast masses depicted on full-field digital mammograms: a performance assessment.

Authors:  B Zheng; J H Sumkin; M L Zuley; D Lederman; X Wang; D Gur
Journal:  Br J Radiol       Date:  2011-02-22       Impact factor: 3.039

6.  Computer-aided detection; the effect of training databases on detection of subtle breast masses.

Authors:  Bin Zheng; Xingwei Wang; Dror Lederman; Jun Tan; David Gur
Journal:  Acad Radiol       Date:  2010-07-22       Impact factor: 3.173

7.  Computer-Aided Diagnosis in Mammography Using Content-based Image Retrieval Approaches: Current Status and Future Perspectives.

Authors:  Bin Zheng
Journal:  Algorithms       Date:  2009-06-01
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.