Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Adaptive texture feature extraction with application to ultrasonic image analysis

H J Huisman1, J M Thijssen

  • 1Department of Pediatrics, University Hospital, Nijmegen, The Netherlands.

Ultrasonic Imaging
|August 6, 1998
PubMed
Summary

This study introduces an adaptive texture feature extraction (ATFE) method for improved medical imaging analysis. ATFE effectively extracts relevant features, outperforming traditional methods in limited data scenarios.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

CISS effect: Magnetocurrent-voltage characteristics with Coulomb interactions. II.

The Journal of chemical physics·2023
Same author

Quantitative CT perfusion imaging in patients with pancreatic cancer: a systematic review.

Abdominal radiology (New York)·2021
Same author

Interactive 3D U-net for the segmentation of the pancreas in computed tomography scans.

Physics in medicine and biology·2020
Same author

Transport gap renormalization at a metal-molecule interface using DFT-NEGF and spin unrestricted calculations.

The Journal of chemical physics·2017
Same author

Electronic components embedded in a single graphene nanoribbon.

Nature communications·2017
Same author

3D quantitative breast ultrasound analysis for differentiating fibroadenomas and carcinomas smaller than 1cm.

European journal of radiology·2017

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Traditional texture analysis relies on fixed features, often lacking problem-specific relevance and leading to low discriminative power or correlation.
  • Using numerous fixed features is statistically suboptimal in limited data environments like medical imaging.

Purpose of the Study:

  • To develop an adaptive texture feature extraction (ATFE) method for improved performance in limited dataset situations.
  • To create a method that extracts a small, problem-tailored set of features, capturing both linear and nonlinear relationships.

Main Methods:

  • Developed an adaptive texture feature extraction (ATFE) method utilizing a feed-forward neural network.
  • Compared ATFE performance against an optimal feature set using extensive, repeated synthetic ultrasonic images.

Related Experiment Videos

Main Results:

  • ATFE demonstrated robust performance on small datasets, achieving results close to the optimal feature set.
  • Experiments confirmed ATFE's capability to capture nonlinear relationships within the data.

Conclusions:

  • The ATFE method offers improved performance in practical, limited dataset scenarios where optimal fixed feature sets are difficult to determine.
  • ATFE provides a more effective approach to texture analysis in medical imaging and similar fields with data constraints.