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

Advanced soft computing diagnosis method for tumour grading.

E I Papageorgiou1, P P Spyridonos, C D Stylios

  • 1Department of Electrical and Computer Engineering, Laboratory for Automation and Robotic, University of Patras, Rion 26500, Greece. epapageo@ee.upatras.gr

Artificial Intelligence in Medicine
|August 13, 2005
PubMed
Summary

A new soft computing method using fuzzy cognitive maps (FCMs) and active Hebbian learning (AHL) improves urinary bladder tumour grading accuracy. This advanced diagnostic tool offers transparent and explicable results for physicians.

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

Assessing the performance of four different categories of histological criteria in brain tumours grading by means of a computer-aided diagnosis image analysis system.

Journal of microscopy·2015
Same author

Combining latent class analysis labeling with multiclass approach for fetal heart rate categorization.

Physiological measurement·2015
Same author

Expression and distribution of aggrecanases in human larynx: ADAMTS-5/aggrecanase-2 is the main aggrecanase in laryngeal carcinoma.

Biochimie·2012
Same author

Expression of the epidermal growth factor system in endometrial cancer.

European journal of gynaecological oncology·2008
Same author

Expression of metalloproteinases and their tissue inhibitors in squamous cell laryngeal carcinoma.

Oncology reports·2007
Same author

Vaginal cancer in a patient treated for cervical intraepithelial neoplasia (CIN 3): case report.

European journal of gynaecological oncology·2007

Area of Science:

  • Urology
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Accurate urinary bladder tumour grading is crucial for effective treatment planning.
  • Traditional grading systems can be subjective, necessitating advanced diagnostic tools.

Purpose of the Study:

  • To develop an advanced diagnostic method for urinary bladder tumour grading.
  • To apply a novel soft computing methodology combining fuzzy cognitive maps (FCMs) with active Hebbian learning (AHL).

Main Methods:

  • Developed an FCM model with nine concepts, including eight histopathological features and one for tumour grade.
  • Applied the unsupervised AHL algorithm to adjust FCM weights for enhanced classification.
  • Utilized data from 128 urinary bladder cancer cases graded by the WHO system.

Related Experiment Videos

Main Results:

  • The FCM grading model achieved high classification accuracies: 72.5% for grade I, 74.42% for grade II, and 95.55% for grade III tumours.
  • The integrated AHL algorithm improved the classification ability of the FCM model.

Conclusions:

  • An advanced computerized method for tumour grade diagnosis was developed.
  • The novelty lies in using FCMs for histopathological knowledge representation augmented by AHL.
  • The method provides reasonably high accuracy, transparency, and explicability for physicians.