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

Cell-nuclear data reduction and prognostic model selection in bladder tumor recurrence.

Dimitris K Tasoulis1, Panagiota Spyridonos, Nicos G Pavlidis

  • 1Computational Intelligence Laboratory, Department of Mathematics, University of Patras, GR-26110 Patras, Greece. dtas@math.upatras.gr

Artificial Intelligence in Medicine
|September 30, 2006
PubMed
Summary

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

K<sup>+</sup>-Triggered Defect Engineering and Proton-Coupled Storage in V<sub>2</sub>O<sub>5</sub>·nH<sub>2</sub>O for Advanced Zn-Ion Thin-Film and Microbatteries.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

3D Engineered Dual-Redox Zinc-Iodine Microbatteries for Intrinsically Safe on-Chip Energy Storage.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Heart Rate Variability in the Detection of Cognitive Fatigue Through Transfer Learning.

Advances in experimental medicine and biology·2026
Same author

Reducing Artifact Preprocessing in Heart Rate Variability-Based Personalized Psychosis Prediction Using Adaptive Long Short-Term Memory Models.

International journal of neural systems·2025
Same author

Enhancing Stability and Capacity in Planar Zn-Ion Micro-Batteries via 3D Porous Ni Anode Integration.

Small methods·2025
Same author

AΚtransU-Net: Transformer-Equipped U-Net Model for Improved Actinic Keratosis Detection in Clinical Photography.

Diagnostics (Basel, Switzerland)·2025

This study enhances superficial bladder cancer recurrence prediction using feedforward neural networks (FNNs) and unsupervised clustering for feature selection. The method accurately identifies patients likely to experience recurrence, aiding clinical decisions.

Area of Science:

  • Oncology
  • Biomedical Engineering
  • Computational Pathology

Background:

  • Superficial bladder cancer recurrence poses a significant clinical challenge.
  • Accurate prediction of recurrence is crucial for optimizing patient management and treatment strategies.

Purpose of the Study:

  • To improve the prediction accuracy of superficial bladder cancer recurrence.
  • To develop and evaluate a feature selection method using unsupervised clustering for prognostic models.

Main Methods:

  • A retrospective study of 127 patients with superficial urinary bladder cancer.
  • Digitization of biopsy images and extraction of cell nuclei features.
  • Application of unsupervised k-windows (UKW) and fuzzy c-means clustering for feature selection, and feedforward neural networks (FNNs) for classification.

Related Experiment Videos

Main Results:

  • The UKW method significantly reduced feature space dimensionality.
  • Achieved prediction rates of 87.95% for non-recurrent and 91.41% for recurrent cases using the reduced feature set.
  • The adaptive on-line backpropagation algorithm demonstrated superior performance for FNN training.

Conclusions:

  • Feedforward neural networks (FNNs) offer accurate prognosis for bladder cancer recurrence.
  • The proposed feature selection method simplifies prognostic models without compromising predictive accuracy, enhancing clinical applicability.