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

You might also read

Related Articles

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

Sort by

Same author

Effect of Mo on Microstructures and Wear Properties of In Situ Synthesized Ti(C,N)/Ni-Based Composite Coatings by Laser Cladding.

Materials (Basel, Switzerland)·2017

Same author

Brain Membrane Proteome and Phosphoproteome Reveal Molecular Basis Associating with Nursing and Foraging Behaviors of Honeybee Workers.

Journal of proteome research·2017

Same author

A pairwise likelihood augmented Cox estimator for left-truncated data.

Biometrics·2017

Same author

Novel Three-Dimensional Semiconducting Materials Based on Hybrid d<sup>10</sup> Transition Metal Halogenides as Visible Light-Driven Photocatalysts.

Inorganic chemistry·2017

Same author

Association of lymphocyte-to-monocyte ratio with in-hospital and long-term major adverse cardiac and cerebrovascular events in patients with ST-elevated myocardial infarction.

Medicine·2017

Same author

Tendon injuries: Basic science and new repair proposals.

EFORT open reviews·2017

Same journal

A computational model of chemically- and mechanically-induced thrombus formation in cerebral aneurysms.

Computers in biology and medicine·2026

Same journal

An improved catch fish optimization based deep learning model for Parkinson disease classification using EEG signal.

Computers in biology and medicine·2026

Same journal

Assessing the robustness of evaluation metrics for synthetic ECG signal quality.

Computers in biology and medicine·2026

Same journal

Integrating stemness and epithelial-mesenchymal transition signatures with machine learning identifies RUNX1 as a therapeutic vulnerability in colorectal cancer.

Computers in biology and medicine·2026

Same journal

Differential regional textural attributes of tongue in normal and acidity patients in the light of traditional Chinese medicine.

Computers in biology and medicine·2026

Same journal

SC-MSDNet: Spatial-consistent multi-view self-distillation for retinal OCT classification.

Computers in biology and medicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 12, 2025

Generation of Self-assembled Vascularized Human Skin Equivalents

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

AGNet: Automatic generation network for skin imaging reports.

Fan Wu¹, Haiqiong Yang², Linlin Peng²

¹The School of Intelligent Systems Engineering, Sun Yat-Sen University, No. 135, Xingang Xi Road, Guangzhou, 510275, PR China; Guangdong Provincial Key Laboratory of Fire Science and Technology, Guangzhou, 510006, China.

Computers in Biology and Medicine

|November 23, 2021

Summary

This summary is machine-generated.

This study introduces the automatic generation network (AGNet), a deep learning model for generating skin pathology image reports. AGNet significantly improves diagnostic report accuracy and efficiency, addressing challenges in medical imaging analysis.

Keywords:

Attention mechanism Deep learning Image caption Medical imaging Skin imaging report generation

More Related Videos

Generation of a Three-dimensional Full Thickness Skin Equivalent and Automated Wounding

Generation of a Three-dimensional Full Thickness Skin Equivalent and Automated Wounding

Published on: February 26, 2015

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Related Experiment Videos

Last Updated: Oct 12, 2025

Generation of Self-assembled Vascularized Human Skin Equivalents

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

Generation of a Three-dimensional Full Thickness Skin Equivalent and Automated Wounding

Generation of a Three-dimensional Full Thickness Skin Equivalent and Automated Wounding

Published on: February 26, 2015

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Area of Science:

Medical Imaging
Artificial Intelligence
Computational Pathology

Background:

Medical imaging is crucial for diagnosing skin diseases with high accuracy.
Current diagnostic reporting for skin pathology is repetitive and prone to errors by clinicians.
Manual reporting is time-consuming and tedious for both inexperienced and experienced professionals.

Purpose of the Study:

To develop an automated system for generating diagnostic reports from skin pathology images.
To address the challenges of error rates and inefficiency in manual medical report generation.
To propose a novel deep learning framework for image-to-text generation in a medical context.

Main Methods:

A deep learning-based image caption framework named the automatic generation network (AGNet) was developed.
AGNet integrates an image model for feature extraction/classification and a language model for report generation.
An attention module connects image and language components, with an embedding and labeling module for caption data processing.

Main Results:

The AGNet was validated on a skin pathological image dataset.
Performance was compared against several state-of-the-art models in image captioning.
AGNet achieved the highest scores across key image caption evaluation metrics.

Conclusions:

The proposed AGNet demonstrates promising performance for automatic skin imaging report generation.
The novel framework effectively bridges image analysis and natural language report creation.
AGNet offers a potential solution to enhance accuracy and efficiency in dermatopathology diagnostics.