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

Coverage-Dependent Adsorption Behavior of N‑Containing Gases on Nb<sub>2</sub>CT <sub><i>x</i></sub> MXenes: A DFT Study.

ACS omega·2026
Same author

CRAF-Net: A Fine-Grained Cross-Channel Attention Network for Preoperative Microvascular Invasion Grading in Hepatocellular Carcinoma via DCE-MRI.

Journal of imaging informatics in medicine·2026
Same author

Noninvasively Evaluating the Cerebral Blood Flow Changes After Surgery in Adult Moyamoya Patients Using 3D Pulsed Arterial Spin Labelling MRI.

Clinical and experimental pharmacology & physiology·2026
Same author

Multi-task deep learning assists detection and diagnosis of gliomas and brain metastases.

NPJ digital medicine·2026
Same author

Broadly tunable continuous-wave Tm:CALYO laser operating on the <sup>3</sup>H<sub>4</sub>→<sup>3</sup>H<sub>5</sub> transition.

Optics express·2026
Same author

Single-Molecule Dual-Channel NIR Fluorescence Probe for Simultaneous Monitoring ATP and ONOO<sup>-</sup> during Ferroptosis and Hepatic Ischemia-Reperfusion Injury.

Analytical chemistry·2026

Related Experiment Video

Updated: Jul 7, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.4K

Interobserver Agreement in Automatic Segmentation Annotation of Prostate Magnetic Resonance Imaging.

Liang Jin1,2, Zhuangxuan Ma2, Haiqing Li1

  • 1Radiology Department, Huashan Hospital, Affiliated with Fudan University, Shanghai 200040, China.

Bioengineering (Basel, Switzerland)
|December 23, 2023
PubMed
Summary

Automatic segmentation significantly improves radiomics feature consistency and reduces interobserver variability in prostate cancer imaging. This AI-assisted approach enhances performance, especially for junior radiologists, ensuring more stable and reliable results.

Keywords:
T2-weighted imagingautomatic segmentationinterobserver agreementprostateradiomics

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Related Experiment Videos

Last Updated: Jul 7, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.4K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Area of Science:

  • Medical Imaging
  • Radiomics
  • Artificial Intelligence in Healthcare

Background:

  • Radiomics analysis of prostate cancer relies on accurate image segmentation.
  • Manual segmentation by radiologists can introduce interobserver variability and inconsistency in radiomics features.
  • Variability is influenced by radiologists' experience levels.

Purpose of the Study:

  • To compare manual versus automatic image segmentation performance and interobserver agreement in prostate cancer.
  • To assess the impact of automatic segmentation on radiomics feature consistency.
  • To reduce interobserver variability and improve the stability of radiomics features.

Main Methods:

  • Retrospective study of 327 prostate cancer patients; 99 used for testing.
  • Four radiologists manually segmented T2-weighted MRI images.
  • Automatic segmentation was performed, and radiomics features were extracted using Pyradiomics software.

Main Results:

  • Automatic segmentation demonstrated higher consistency than manual segmentation (p < 0.05), with an average intraclass correlation coefficient (ICC) > 0.85.
  • Junior radiologists using automatic segmentation achieved performance comparable to senior radiologists using manual segmentation.
  • The ICC for radiomics features improved to excellent consistency (0.925 [0.888~0.950]) with automatic segmentation.

Conclusions:

  • Automatic segmentation annotation provides superior results compared to manual segmentation by radiologists.
  • AI-assisted segmentation reduces variability between radiologists of different experience levels.
  • Automatic segmentation ensures greater stability and reliability of radiomics features for prostate cancer analysis.