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: Nov 20, 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

Automatic liver segmentation using 3D convolutional neural networks with a hybrid loss function.

Man Tan¹, Fa Wu¹, Dexing Kong¹

¹The School of Mathematical Sciences, Zhejiang University, Hangzhou, Zhejiang, 310058, China.

Medical Physics

|January 26, 2021

Summary

This summary is machine-generated.

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 multimodal instruction dataset and benchmark for ultrasound understanding.

NPJ digital medicine·2026

Same author

Synchronous wearable ultrasound for early detection of coronary and carotid artery comorbidity.

Science advances·2026

Same author

Information Entropy-Based Framework for Quantifying Curve Tortuosity in Meibomian Glands Uneven Atrophy.

Translational vision science & technology·2026

Same author

WCEDSAM: A Lightweight Multi-Scale Colonoscopy Polyp-Segmentation Network Combining Frequency-Domain Decomposition and Adaptive Feature Enhancement.

Biology·2026

Same author

Intelligent diagnosis of ovarian cancer in PET/CT imaging based on KiteNet-MobileNetv3 fusion and CarveMix augmentation.

Scientific reports·2026

Same author

Gliosarcoma of the right cerebellar hemisphere and parahippocampal region: A case report and literature review.

Oncology letters·2026

Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026

Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026

Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026

Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026

Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026

Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026

See all related articles

This study introduces a novel hybrid loss function for automatic liver segmentation in CT scans, improving accuracy even with limited data. The method excels in pathological liver segmentation, demonstrating robust performance on benchmark datasets.

Area of Science:

Medical Imaging
Computer-Aided Surgery
Artificial Intelligence in Medicine

Background:

Automatic liver segmentation from CT images is crucial for computer-assisted liver surgery.
Existing algorithms struggle with fuzzy boundaries and pathologies, especially with scarce data.
Need for robust segmentation methods that handle data limitations and complex anatomical variations.

Purpose of the Study:

To develop an automatic liver segmentation framework using 3D convolutional neural networks.
To address challenges of fuzzy boundaries, heterogeneous pathologies, and limited training data.
To introduce a novel hybrid loss function for enhanced segmentation accuracy.

Main Methods:

Employed a two-network architecture: a liver shape autoencoder and a segmentation network.

Keywords:

automatic liver segmentation convolutional neural networks high-level shape constraint hybrid loss

More Related Videos

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: Nov 20, 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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Utilized a hybrid loss function combining adaptively weighted cross-entropy, edge-preserving smoothness, and shape constraints.

Incorporated 3D operations and data augmentation during training and testing.

Main Results:

Achieved top scores on the Sliver07 (82.55) and CHAOS (83.02) challenges with only 20 training scans.
Demonstrated superior performance on both public datasets, validating the method's effectiveness.
Successfully segmented livers despite challenges like fuzzy boundaries and pathologies.

Conclusions:

The proposed hybrid loss function effectively overcomes difficulties in liver segmentation.
The framework shows high suitability for pathological liver segmentation, even with small datasets.
Results indicate a significant advancement in automated medical image segmentation.