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

From resistance to reliance: A human-centered analysis of the spectrum of radiologists' trust in AI.

European journal of radiology open·2026
Same author

Quality over quantity: biopsy-anchored CT radiogenomics models outperform all-lesion training in a multi-tumour cohort despite a smaller sample size.

European radiology·2026
Same author

Radiomics-based outcome prediction for irinotecan-TACE in colorectal liver metastases: advanced analysis from the prospective CIREL trial.

European radiology·2026
Same author

Germline Pathogenic Variants in Homologous Recombination Pathway Genes Are Frequent in Pancreatobiliary Ampullary Carcinoma.

JCO precision oncology·2026
Same author

¹⁹F MRI radiomic features: in vitro and in vivo repeatability.

European radiology experimental·2026
Same author

Associations of ultra-processed food intake with bone mineral density and fractures in the UK Biobank.

The British journal of nutrition·2026

Related Experiment Video

Updated: Jan 9, 2026

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

13.3K

Anomaly-Driven Approach for Enhanced Prostate Cancer Segmentation.

Alessia Hu, Regina Beets-Tan, Lishan Cai

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Anomaly detection enhances prostate cancer identification using Magnetic Resonance Imaging (MRI). The Anomaly-Driven U-Net (adU-Net) model shows improved performance in segmenting clinically significant prostate cancer (csPCa).

    More Related Videos

    Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
    08:05

    Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

    Published on: June 10, 2025

    1.1K
    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

    1.1K

    Related Experiment Videos

    Last Updated: Jan 9, 2026

    Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
    08:40

    Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

    Published on: April 8, 2016

    13.3K
    Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
    08:05

    Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

    Published on: June 10, 2025

    1.1K
    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

    1.1K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Oncology

    Background:

    • Magnetic Resonance Imaging (MRI) is crucial for identifying clinically significant prostate cancer (csPCa).
    • Automated csPCa detection methods struggle with data imbalance, varied tumor sizes, and limited annotated data.
    • Deep learning segmentation models require robust feature representation for accurate tumor identification.

    Purpose of the Study:

    • To introduce and evaluate the Anomaly-Driven U-Net (adU-Net) for improved csPCa segmentation.
    • To investigate the integration of anomaly maps into deep learning frameworks for medical image analysis.
    • To enhance the generalization and performance of automated csPCa identification systems.

    Main Methods:

    • Developed adU-Net, a deep learning model incorporating anomaly maps from biparametric MRI sequences.
    • Generated anomaly maps using Fixed-Point Generative Adversarial Network (GAN) reconstruction to highlight deviations from normal prostate tissue.
    • Conducted comparative analysis of anomaly detection techniques and their integration into the segmentation pipeline.
    • Evaluated model performance using the average score (mean of AUROC and Average Precision).

    Main Results:

    • adU-Net achieved a superior average score of 0.618 on the external test set, outperforming the baseline nnU-Net (0.605).
    • Anomaly maps, particularly those derived from apparent diffusion coefficient (ADC)-based sequences, significantly improved segmentation performance.
    • The integration of anomaly detection enhanced model generalization and accuracy in identifying csPCa.

    Conclusions:

    • Incorporating anomaly detection into deep learning segmentation models offers a promising approach for automated csPCa identification.
    • adU-Net demonstrates the potential of anomaly maps to guide segmentation models towards accurate tumor localization.
    • Further research into anomaly detection methods can advance the clinical utility of AI in prostate cancer diagnostics.