Adaptive texture feature extraction with application to ultrasonic image analysis
- PMID: 9691370
- DOI: 10.1177/016173469802000204
Adaptive texture feature extraction with application to ultrasonic image analysis
Abstract
Computer texture analysis methods use texture features that are traditionally chosen from a large set of fixed features known in literature. These fixed features are often not specifically designed to the problem at hand, and as a result they may have low discriminative power, and/or may be correlated. Increasing the number of selected fixed features is statistically not a good solution in limited data environments such as medical imaging. For that reason, we developed an adaptive texture feature extraction method (ATFE) that extracts a small number of features that are tuned to the problem at hand. By using a feed-forward neutral network, we ensure that even nonlinear relations are captured from the data. Using extensive, repeated synthetic ultrasonic images, we compared the performance of ATFE with the optimal feature set. We show that the ATFE method is capable of robust operation on small data sets with a performance close to that of the optimal feature set. Another experiment confirms that our ATFE is capable of capturing nonlinear relations from the dataset. We conclude that our method can improve performance in practical, limited dataset situations where an optimal fixed feature set can be hard to find.
Similar articles
-
Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor.IEEE Trans Image Process. 2009 Oct;18(10):2289-302. doi: 10.1109/TIP.2009.2025560. Epub 2009 Jun 16. IEEE Trans Image Process. 2009. PMID: 19535321
-
Effects of magnetic resonance image interpolation on the results of texture-based pattern classification: a phantom study.Invest Radiol. 2009 Jul;44(7):405-11. doi: 10.1097/RLI.0b013e3181a50a66. Invest Radiol. 2009. PMID: 19465863
-
Rough sets and near sets in medical imaging: a review.IEEE Trans Inf Technol Biomed. 2009 Nov;13(6):955-68. doi: 10.1109/TITB.2009.2017017. Epub 2009 Mar 16. IEEE Trans Inf Technol Biomed. 2009. PMID: 19304490 Review.
-
A wavelet-based optimal texture feature set for classification of brain tumours.J Med Eng Technol. 2008 May-Jun;32(3):198-205. doi: 10.1080/03091900701455524. J Med Eng Technol. 2008. PMID: 18432467
-
Low dimensional adaptive texture feature vectors from class distance and class difference matrices.IEEE Trans Med Imaging. 2004 Jan;23(1):73-84. doi: 10.1109/TMI.2003.819923. IEEE Trans Med Imaging. 2004. PMID: 14719689
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources