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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

[Corrigendum] Effect of SDF‑1/CXCR4 axis on the migration of transplanted bone mesenchymal stem cells mobilized by erythropoietin toward lesion sites following spinal cord injury.

International journal of molecular medicine·2026
Same author

Meaning in life, emptiness and depression among adolescents: a cross-sectional study.

Frontiers in child and adolescent psychiatry·2026
Same author

Coacervates of Lactoferrin with Resistant Dextrin via Noncovalent Interaction for Enhanced Thermal Stability, Interface Characteristics and Docosahexaenoic Acid (DHA) Encapsulation.

Food science of animal resources·2026
Same author

Engineering and characterization of a novel PD-L1/VEGF bispecific antibody with enhanced VEGF-neutralizing capacity.

Biochemical and biophysical research communications·2026
Same author

TCBD substitution induced distinct photoinduced dynamics in C<sub>3</sub>-symmetric star-shaped truxene-centered donor-acceptor systems: a nonadiabatic dynamics simulation.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Nanomedicine carrier-based combined antitumor strategy integrating phototherapy and immunotherapy.

Immunopharmacology and immunotoxicology·2026
Same journal

Identification of FMR1 as a novel cancer prognostic and immunotherapy biomarker through renal cancer experimental validation and pan-cancer analysis.

Discover oncology·2026
Same journal

A novel prognostic zinc finger gene model for hepatocellular carcinoma via machine learning.

Discover oncology·2026
Same journal

High RSPO3 protein expression serves as an independent poor prognostic factor and promotes malignant progression in breast cancer.

Discover oncology·2026
Same journal

Identification of exosome-related genes signature based on bioinformatics and machine learning for prognostic prediction in colorectal cancer.

Discover oncology·2026
Same journal

Tumor location and morphological MRI features in relation to combined 1p/22q deletion in meningioma.

Discover oncology·2026
Same journal

Tumor-induced immune escape mechanisms and translational immunotherapeutic strategies.

Discover oncology·2026
See all related articles

Related Experiment Video

Updated: Mar 12, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Meta learning optimized TabNet for small sample repeat prostate biopsy prediction.

Jienv Lou1, Jiahan Xu2, Dan Mao2

  • 1Department of Ultrasound, The Affiliated People's Hospital of Ningbo University, No. 251, Baizhang East Road, Yinzhou County, Ningbo, Zhejiang, China. 815131765@qq.com.

Discover Oncology
|March 11, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a meta-learning optimized TabNet model for accurate repeat prostate biopsy prediction, overcoming small sample sizes without advanced imaging. The AI tool enhances diagnostic accuracy and reduces unnecessary procedures.

Keywords:
Artificial intelligenceClinical decision supportMeta-learningProstate cancerRepeat biopsyTabNet

More Related Videos

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

1.3K
Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking
05:49

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Published on: October 10, 2019

7.1K

Related Experiment Videos

Last Updated: Mar 12, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K
Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

1.3K
Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking
05:49

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Published on: October 10, 2019

7.1K

Area of Science:

  • Artificial Intelligence in Medicine
  • Urologic Oncology
  • Machine Learning for Healthcare

Background:

  • Repeat prostate biopsy (RB) prediction is hindered by small patient cohorts, limiting artificial intelligence (AI) applications.
  • Existing methods struggle with complex clinical patterns, especially in resource-limited settings lacking advanced imaging like mpMRI.
  • Knowledge transfer from larger initial biopsy (IB) cohorts can improve RB prediction accuracy.

Purpose of the Study:

  • To develop and validate a meta-learning optimized TabNet framework for enhanced RB prediction accuracy.
  • To overcome sample size limitations in AI models for RB prediction using readily available clinical parameters.
  • To provide a tool applicable in resource-limited settings where mpMRI is unavailable.

Main Methods:

  • A retrospective study analyzed 2,087 initial prostate biopsies (IB) and 139 subsequent repeat biopsies (RB) without mpMRI data.
  • A two-stage training paradigm used Model-Agnostic Meta-Learning for pre-training on IB data, followed by fine-tuning on the RB cohort.
  • Performance was evaluated using discrimination, calibration, and decision curve analysis, benchmarked against conventional ML and risk calculators.

Main Results:

  • Meta-learning TabNet achieved superior discriminative performance (AUROC 0.872) on an independent test set compared to XGBoost (0.808) and original TabNet (0.800).
  • The model demonstrated optimal calibration (Brier score 0.068, ECE 0.100) and high specificity (90.0%) with minimal false positives.
  • Performance substantially outperformed established clinical risk calculators like ERSPC and PCPT.

Conclusions:

  • Meta-learning optimization effectively addresses sample size limitations for repeat prostate biopsy prediction without advanced imaging.
  • The developed framework serves as an evidence-based decision support tool, enhancing diagnostic accuracy.
  • This approach minimizes unnecessary procedures and is particularly valuable in resource-limited settings.