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: Mar 7, 2026

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

HEp-2 Specimen Image Segmentation and Classification Using Very Deep Fully Convolutional Network.

Yuexiang Li, Linlin Shen, Shiqi Yu

IEEE Transactions on Medical Imaging

|February 27, 2017

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

SinTransNet: an EEG-based deep learning framework for infantile epileptic spasms syndrome detection.

BMC medical informatics and decision making·2026

Same author

Ultrasensitive Pressure-Responsive Upconversion Luminescence in Cs<sub>2</sub>NaBiCl<sub>6</sub>:Yb<sup>3+</sup>/Mn<sup>2+</sup> Optical Manometry.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

MFF-M3AD: A unified reconstruction method with multi-scale feature fusion for multi-category 3D anomaly detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Identification and validation of glycosylation-related biomarkers in the hippocampus for Alzheimer's disease diagnosis and drug repurposing.

European journal of pharmacology·2026

Same author

Thyro-LMD: A Benchmark Dataset and Sample-Driven Data Loading, Attention, and Regularization for Long-Tailed Multi-Label Thyroid Ultrasound Diagnosis.

IEEE transactions on medical imaging·2026

Same author

LNMSNet: a multi-task deep learning network for pulmonary nodules segmentation and malignancy classification.

Frontiers in medicine·2026

Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026

Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026

Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026

Same journal

Generalised Medical Phrase Grounding.

IEEE transactions on medical imaging·2026

Same journal

EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

IEEE transactions on medical imaging·2026

Same journal

A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter.

IEEE transactions on medical imaging·2026

See all related articles

This study introduces an automated system for identifying Human Epithelial-2 (HEp-2) cell patterns, improving diagnosis of autoimmune diseases. The novel approach significantly enhances accuracy in both cell pattern classification and segmentation.

Area of Science:

Immunology
Medical Diagnostics
Computer Vision

Background:

Accurate identification of Human Epithelial-2 (HEp-2) cell patterns is crucial for diagnosing systemic autoimmune diseases.
Manual analysis of HEp-2 cell patterns by experts is subjective and prone to inter-observer variability.
There is a need for automated, objective methods for HEp-2 cell pattern recognition.

Purpose of the Study:

To develop an automated system for simultaneous segmentation and classification of HEp-2 cell patterns.
To improve the accuracy and reliability of HEp-2 cell pattern identification compared to traditional methods.
To address the limitations of manual analysis in diagnosing autoimmune diseases.

Main Methods:

A fully convolutional network (FCN) based on residual networks (ResNet) was developed, termed fully convolutional ResNet (FCRN).

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Mar 7, 2026

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

A novel 'sand-clock' shape residual module was incorporated to enhance FCRN performance.

The model was trained and evaluated on the publicly available I3A-2014 dataset for classifying HEp-2 images into seven distinct patterns.

Main Results:

The FCRN model achieved a mean class accuracy of 94.94% in HEp-2 cell pattern classification, surpassing the ICPR 2014 winner's accuracy (89.93%).
The system demonstrated a segmentation accuracy of 89.03%, a significant improvement of 19.05% over the benchmark approach (69.98%).
The proposed method effectively handles both segmentation and classification tasks for HEp-2 specimen images.

Conclusions:

The developed FCRN system offers a highly accurate and reliable automated solution for HEp-2 cell pattern recognition.
This automated approach can significantly aid in the objective diagnosis of systemic autoimmune diseases.
The novel sand-clock residual module contributes to improved performance in semantic segmentation tasks for biomedical images.