Search research articles

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

Related Concept Videos

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...

You might also read

Related Articles

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

Sort by

Same author

Prognostic impact of radiotherapy dose to the axilla in cN + /ypN0 breast cancer after primary systemic therapy and sentinel lymph node biopsy: toward true de-escalation of axillary management.

Breast cancer (Tokyo, Japan)·2026

Same author

Tumor Treating Fields modulate apoptotic and immune programs in T-cell acute lymphoblastic leukemia cell lines.

Experimental and therapeutic medicine·2026

Same author

Feasibility of omitting regional nodal irradiation in cT1-2N1 breast cancer with ypN1 disease after neoadjuvant chemotherapy (KROG 21-06).

Clinical and translational radiation oncology·2026

Same author

The combination of <i>EWSR1-FLI1</i> and loss of one <i>EWSR1</i> allele leads to the induction of trisomy 8.

bioRxiv : the preprint server for biology·2026

Same author

Correction: Synthesis of heteroleptic [Sr(ddemap)(tmhd)]<sub>2</sub> and its use in atomic layer deposition of low carbon SrO thin films.

RSC advances·2026

Same author

Guidance Framework for Selecting Virtual Hand Illusion Paradigms to Enhance Motor Imagery via Sense of Ownership in Stroke Rehabilitation.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Search research articles

Related Experiment Video

Updated: May 3, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

A device-dependent auto-segmentation method based on combined generalized and single-device datasets.

Hyeongjin Lim¹, Yongha Gi¹, Yousun Ko¹

¹Department of Bio-medical Engineering, Korea University, Seoul, Republic of Korea.

Medical Physics

|December 19, 2024

Summary

Combining generalized and single CT scanner datasets improved auto-segmentation model performance. The device-dependent dataset-based model (DDSM) outperformed the generalized-dataset-based model (GDSM) across key metrics for unseen scanners.

Keywords:

CT of thoracic abdomen large‐scale dataset nnU‐Net segmentation

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: May 3, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Generalized auto-segmentation models for computed tomography (CT) show promise but struggle with unseen scanners due to device-specific features.
Device-dependent image characteristics pose challenges for cross-scanner medical image analysis.

Purpose of the Study:

To evaluate a device-dependent auto-segmentation model using a combined dataset.
Investigate performance improvements by integrating generalized and single CT scanner data.

Main Methods:

Trained two models: GDSM (generalized dataset) and DDSM (generalized + single scanner dataset) for 21 organs using nnU-Net.
Evaluated models on unseen single CT scanner data using Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Average Symmetric Surface Distance (ASSD).
Utilized variant metrics (DSCdiff, HDratio, ASSDratio) for organ-specific performance comparison.

Main Results:

DDSM achieved higher average DSC (0.9323 vs. 0.9251), lower average HD (9.139 mm vs. 10.66 mm), and lower average ASSD (0.6656 mm vs. 0.8318 mm) compared to GDSM.
DDSM demonstrated performance improvements of 0.78% (DSC), 14% (HD), and 20% (ASSD) over GDSM.
DDSM showed superior performance in a majority of organs for variant metrics (DSCdiff, HDratio, ASSDratio).

Conclusions:

Combining generalized and single scanner datasets enhances auto-segmentation model performance for specific devices.
The device-dependent dataset-based model (DDSM) offers improved accuracy and robustness for medical image segmentation across different CT scanners.