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

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

Hybrid µCT-FMT imaging and image analysis

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

Refined Myocardium Segmentation from CT Using a Hybrid-Fusion Transformer.

Shihua Qin^1,2, Fangxu Xing¹, Jihoon Cho³

¹Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.

Biorxiv : the Preprint Server for Biology

|November 26, 2025

Summary

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

Current modeling approaches for drug delivery to the central nervous system.

Therapeutic delivery·2026

Same author

Changes in susceptibility to heat on suicide mortality within summer in Japan, 1973-2020: A two-stage time-series analysis.

Psychiatry research·2026

Same author

Effect of Older Donors (Age ≥40) and Normothermic Regional Perfusion on DCD Heart Transplant Outcomes.

Clinical transplantation·2026

Same author

Synthesizing vocal tract magnetic resonance imaging sequences with phoneme-aware diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026

Same author

Maternal morbidity and cumulative infant mortality among women with disabilities: a nationwide population-based study in Korea, 2013-2022.

Obstetrics & gynecology science·2026

Same author

Engineered Development: Directed Morphogenesis of an Embryonic Heart Tube.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

Layered social competition coordinates reproductive hierarchy formation in ants.

bioRxiv : the preprint server for biology·2026

Same journal

Combination epigenetic-targeted therapy increases the immunogenicity of poorly immunogenic sarcomas.

bioRxiv : the preprint server for biology·2026

Same journal

Loss of LanC-like proteins delays post-injury regeneration of aging skeletal muscles.

bioRxiv : the preprint server for biology·2026

Same journal

Integrative Transfer Network: Deep Transfer Learning Across Populations and Prediction Targets.

bioRxiv : the preprint server for biology·2026

Same journal

Confidence-supported label-free metabolic imaging with FPhaS phase autofluorescence microscopy.

bioRxiv : the preprint server for biology·2026

Same journal

Sequence-encoded autoinhibition couples mRNA decapping activity to phase separation.

bioRxiv : the preprint server for biology·2026

See all related articles

This summary is machine-generated.

This study presents a deep-learning method to accurately segment the left ventricle (LV) in cardiac CT scans, improving cardiovascular disease diagnosis by refining semi-automatic segmentation and removing unwanted structures like papillary muscles.

Area of Science:

Medical Imaging
Artificial Intelligence
Cardiovascular Imaging

Background:

Accurate left ventricle (LV) segmentation in cardiac CT is vital for diagnosing cardiovascular diseases.
Manual LV segmentation is time-consuming, while semi-automatic methods often include unwanted structures like papillary muscles due to low contrast.
Developing efficient and accurate LV segmentation methods is a significant challenge in cardiac imaging.

Purpose of the Study:

To introduce a novel deep-learning framework for refined LV segmentation in cardiac CT images.
To effectively remove papillary muscles and other unwanted structures from semi-automatic segmentations.
To leverage a combination of CT images and rough semi-automatic labels for improved segmentation accuracy.

Main Methods:

Keywords:

CT Cardiac imaging deep learning myocardium papillary muscle refinement segmentation transformer

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

3D Whole-heart Myocardial Tissue Analysis

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

Related Experiment Videos

Last Updated: Jan 10, 2026

Hybrid µCT-FMT imaging and image analysis

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

3D Whole-heart Myocardial Tissue Analysis

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

A Hybrid-Fusion Transformer deep-learning framework was utilized.

A two-input-channel approach combined cardiac CT images and semi-automatic rough labels.

The model was trained on a small dataset with refined manual and rough semi-automatic labels.

Main Results:

The proposed method successfully refined LV labels and effectively removed papillary muscles.
Quantitative cross-validation demonstrated superior performance compared to models using only CT images or rough masks.
The deep-learning approach achieved accurate automatic refined segmentation.

Conclusions:

The developed deep-learning method offers an efficient solution for accurate LV segmentation in cardiac CT.
This approach enhances the assessment of ventricular function and cardiovascular disease diagnosis.
The Hybrid-Fusion Transformer framework shows promise for improving medical image segmentation tasks.