Search research articles

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

A Federated Benchmark for Clinical Natural Language Processing (FedDRAGON).

Studies in health technology and informatics·2026

Same author

Reference tissue uptake of [18F]PSMA-1007 in positron emission tomography of recurrent prostate cancer.

European radiology·2026

Same author

Evaluating an AI-driven Triaging Workflow for MRI-based Clinically Significant Prostate Cancer Diagnosis: A Simulation Study.

Radiology. Imaging cancer·2026

Same author

Prospective validation of an AI software for detecting clinically significant prostate cancer on biparametric MRI.

Insights into imaging·2026

Same author

Scalable Clinical Annotation with Location Evidence (SCALE).

Computers in biology and medicine·2025

Same author

Development and evaluation of a lymph node invasion risk prediction model in intermediate- and high-risk prostate cancer patients.

Acta oncologica (Stockholm, Sweden)·2025

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Label-set impact on deep learning-based prostate segmentation on MRI.

Jakob Meglič^1,2, Mohammed R S Sunoqrot^3,4, Tone Frost Bathen^3,4

¹Department of Circulation and Medical Imaging, Norwegian University of Science and Technology - NTNU, 7030, Trondheim, Norway. jakobmeg@stud.ntnu.no.

Insights Into Imaging

|September 25, 2023

Summary

Manual segmentation label selection significantly impacts deep learning prostate segmentation performance. Automatic segmentation models showed higher agreement than manual methods and demonstrated true learning capabilities.

Keywords:

Deep learning Label MRI Prostate Segmentation

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Related Experiment Videos

Last Updated: Jul 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Area of Science:

Medical Imaging Analysis
Artificial Intelligence in Healthcare
Prostate Cancer Diagnostics

Background:

Prostate segmentation is crucial for computer-aided detection and diagnosis of prostate cancer.
Deep learning (DL) methods excel in prostate gland and zone segmentation.
The influence of manual segmentation (label) selection on DL model performance remains under-explored.

Purpose of the Study:

To investigate the impact of manual label-set selection on the performance of DL-based prostate segmentation.
To assess how using different expert label-sets affects segmentation accuracy and agreement.
To compare the performance of DL models against manual segmentation agreement.

Main Methods:

Utilized two distinct expert label-sets from the PROSTATEx I challenge dataset (n=198).
Incorporated an additional in-house dataset (n=233) for comprehensive evaluation.
Employed the nnU-Net framework for automatic prostate segmentation.

Main Results:

Label-set selection significantly impacted model performance (p < 0.001).
Models trained and tested with the same label-set exhibited significantly higher performance (p < 0.001).
Automatic segmentations showed significantly higher agreement (p < 0.0001) than manual segmentations, with models outperforming human labelers.

Conclusions:

Manual segmentation label-set choice measurably affects DL-based prostate segmentation performance.
DL-based segmentation demonstrated superior inter-reader agreement compared to manual segmentation.
Further consideration of label-set selection, multicenter segmentation, and procedural agreement is warranted for robust DL models.