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

Comparison of vonoprazan and proton pump inhibitors for the treatment of gastric endoscopic submucosal dissection-induced ulcer: an updated systematic review and meta-analysis.

BMC gastroenterology·2024

Same author

miR-129-3p inhibits NHEJ pathway by targeting SAE1 and represses gastric cancer progression.

International journal of clinical and experimental pathology·2020

Same author

PEA‑15 contributes to the clinicopathology and AKT‑regulated cisplatin resistance in gastric cancer.

Oncology reports·2018

Same author

Clinical manifestations and endoscopic presentations of gastric lymphoma: a multicenter seven year retrospective survey.

Revista espanola de enfermedades digestivas·2017

Same author

5-Azacytidine suppresses EC9706 cell proliferation and metastasis by upregulating the expression of SOX17 and CDH1.

International journal of molecular medicine·2016

Same author

Adhesive polydopamine coated avermectin microcapsules for prolonging foliar pesticide retention.

ACS applied materials & interfaces·2014

Search research articles

Related Experiment Video

Updated: Oct 9, 2025

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

Residual refinement for interactive skin lesion segmentation.

Dalei Jiang¹, Yin Wang², Feng Zhou³

¹Echocardiography and Vascular Ultrasound Center, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, CN, China.

Journal of Biomedical Semantics

|December 19, 2021

Summary

This study introduces a novel interactive method for skin lesion segmentation using a deep convolutional neural network and user input. The approach effectively refines segmentation by separating initial segmentation and refinement tasks.

Keywords:

DCNN Interactive segmentation Residual refinement Skin lesion Two-stage pipeline

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

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Related Experiment Videos

Last Updated: Oct 9, 2025

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

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

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Area of Science:

Computer Vision
Medical Image Analysis

Background:

Image segmentation is a challenging problem with diverse applications, including skin lesion analysis.
Existing methods for skin lesion segmentation lack universal applicability.

Purpose of the Study:

To develop an effective interactive method for skin lesion segmentation.
To address limitations in current interactive segmentation algorithms.

Main Methods:

A novel approach combining a deep convolutional neural network with a grabcut-like user interaction (boxes and clicks).
Explicitly separating segmentation into initial (SBox-Net) and refinement (Click-Net) tasks using individual sub-networks.
Click-Net refines SBox-Net's output using extracted features and user clicks.

Main Results:

The proposed two-stage pipeline method demonstrated effectiveness in experiments.
The approach was validated on the PH2 and ISIC public datasets.

Conclusions:

An effective interactive two-stage pipeline method for skin lesion segmentation was presented.
The method shows promise for improving skin lesion segmentation accuracy and user interaction.