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

Classifying ovarian tumors using Bayesian Multi-Layer Perceptrons and Automatic Relevance Determination: a

Ben Van Calster1, Dirk Timmerman, Ian T Nabney

  • 1Department of Electrical Engineering, Katholieke Universiteit Leuven, Leuven, Belgium. bvancals@esat.kuleuven.be

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|October 20, 2007
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

Reply of the authors: 'Transvaginal ultrasound as a guiding tool in the management for deep endometriosis'.

Fertility and sterility·2026
Same author

Missing infrastructure for real-world predictive AI impact.

BMJ health & care informatics·2026
Same author

Using routinely collected data for research purposes: challenges and mitigation strategies.

BMJ (Clinical research ed.)·2026
Same author

Critical appraisal of fairness metrics for artificial intelligence-based clinical prediction models: a scoping review.

The Lancet. Digital health·2026
Same author

Comparing methods for handling missing data in electronic health records for dynamic risk prediction of central-line associated bloodstream infection.

BMC medical research methodology·2026
Same author

Clustered flexible calibration plots for binary outcomes using random effects modeling.

Research synthesis methods·2026

Bayesian Multi-Layer Perceptrons (MLPs) accurately predict ovarian tumor malignancy. This AI approach aids pre-surgical assessment, improving treatment planning for common ovarian masses.

Area of Science:

  • Oncology
  • Artificial Intelligence
  • Machine Learning

Background:

  • Ovarian masses are common clinical findings.
  • Accurate pre-surgical assessment of ovarian masses is crucial for effective treatment planning.
  • Distinguishing between benign and malignant ovarian tumors pre-operatively remains a challenge.

Purpose of the Study:

  • To evaluate the efficacy of Bayesian Multi-Layer Perceptrons (MLPs) for predicting the malignancy of ovarian tumors.
  • To assess the performance of MLPs using the evidence procedure and Automatic Relevance Determination (ARD) for variable selection.
  • To compare the MLP model's performance with a Bayesian perceptron model.

Main Methods:

  • Utilized Bayesian Multi-Layer Perceptrons (MLPs) with the evidence procedure for malignancy prediction.

Related Experiment Videos

  • Employed Automatic Relevance Determination (ARD) for selecting relevant variables from over 40 initial inputs.
  • Applied cross-validation to optimize the input set and the number of hidden neurons.
  • Analyzed a dataset of 1066 ovarian tumors from nine European centers.

    • Main Results:

    • Achieved high performance with Area Under the Curve (AUC) values of 0.93-0.94 on independent test data.
    • Demonstrated that the ovarian tumor malignancy prediction problem is largely linearly separable.
    • Indicated that the number of hidden neurons in ARD analysis can impact model performance.

    Conclusions:

    • Bayesian MLPs provide a robust and accurate method for pre-surgical assessment of ovarian masses.
    • ARD is effective in identifying key predictive variables for ovarian tumor malignancy.
    • The study highlights the potential of AI in improving diagnostic accuracy and treatment strategies for ovarian cancer.