Một Phần Mềm Gán Nhãn Dữ Liệu Y Tế Mới được Mở Cho Cộng đồng

Agree & Join LinkedIn

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Sign in to view more content

Create your free account or sign in to continue your search

Sign in

Welcome back

Email or phone Password Show Forgot password? Sign in

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

New to LinkedIn? Join now

or

New to LinkedIn? Join now

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

LinkedIn

LinkedIn is better on the app

Don’t have the app? Get it in the Microsoft Store.

Open the app Skip to main content

Một trong những thách thức lớn nhất hiện nay trong việc phát triển các công cụ chẩn đoán và phát hiện bệnh từ hình ảnh y khoa là việc thiếu các công cụ gán nhãn mở, hiệu quả với khả năng quản lý và gán nhãn các bộ dữ liệu quy mô lớn. Trước thực tế này, nhóm phần mềm của Phòng Xử lý ảnh y tế - Viện Nghiên cứu Dữ liệu lớn Vingroup quyết định mở toàn bộ mã nguồn của phần mềm VinDr Lab -- một công cụ gán nhãn hình ảnh DICOM do chúng tôi phát triển và hoàn thiện. VinDr Lab tích hợp nhiều tính năng gán nhãn DICOM, cho phép nhiều users làm việc đồng thời và từ xa. VinDr Lab cũng chính là phần mềm gán nhãn được sử dụng để xây dựng bộ dữ liệu cho cuộc thi VinBigData Chest X-ray Abnormalities Detection. Như vậy, tiếp sau việc mở bộ dữ liệu y tế quy mô lớn VinDr-CXR, đây là đóng góp tiếp theo của VinBigdata trong việc chia sẻ dữ liệu và công cụ phát triển AI. Qua đây, chúng tôi khuyến khích cộng đồng tăng cường việc chia sẻ dữ liệu để thúc đẩy nghiên cứu và phát triển AI tại Việt Nam.

Mã nguồn của VinDr Lab được mở tại đây.

[A new tool for labeling medical imaging data is opened for community]

Lack of efficient labeling frameworks to manage and annotate large-scale medical datasets poses a major obstacle in the development of new Machine Learning-based CADe/CADx systems. In an effort to provide a labeling tool for the community, Department of Medical Imaging, VinBigdata has decided to make the source code of our DICOM annotation tool, namely VinDr Lab. It is a web-based tool that allows multiple annotators to work at the same time and remotely. This is the software that we've used to build the dataset for our Kaggle competition VinBigData Chest X-ray Abnormalities Detection. Following the releasing of the large-scale dataset VinDr-CXR, this is our next contribution in data sharing as well as tools for AI development. We encourage the community to promote the data sharing and tools to drive AI research and development in Vietnam.

The tool is publicly available here.

Like Like Celebrate Support Love Insightful Funny Comment

• Copy
• LinkedIn
• Facebook
• X

Share 40 4 Comments Dung Dao 4y

• Report this comment

The link attached from the English "The tool is publicly available here." is wrong.

Like Reply 1 Reaction 2 Reactions See more comments

To view or add a comment, sign in

More articles by Hieu Pham

• No Good AI Model Without Good Data Sep 28, 2025

  No Good AI Model Without Good Data

  Large-scale, diverse, and representative medical datasets not only enable the development of powerful AI models but…

  122 3 Comments
• WORKSHOP “AI FOR HEALTHCARE 2025” PROMOTES INTERDISCIPLINARY COLLABORATION IN SMART HEALTHCARE DEVELOPMENT IN VIETNAM Jul 15, 2025

  WORKSHOP “AI FOR HEALTHCARE 2025” PROMOTES INTERDISCIPLINARY COLLABORATION IN SMART HEALTHCARE DEVELOPMENT IN VIETNAM

  On July 12, the VinUni-Illinois Smart Health Center (VISHC) at VinUniversity, in collaboration with the Institute of…

  44 2 Comments
• PhD Call for Applications at VinUni and University of Technology Sydney AI-based Medical Image Analysis for Early Detection and Diagnosis Sep 11, 2022

  PhD Call for Applications at VinUni and University of Technology Sydney AI-based Medical Image Analysis for Early Detection and Diagnosis

  Description Medical image analysis is an active research field where advanced image analysis solutions are developed to…

  75 8 Comments
• VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations Jan 4, 2021

  VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations

  Large-scale, high-quality datasets with full annotations for medical imaging analysis are limited and the lack of those…

  42
• Improving information flow across layers in D-CNNs Jun 17, 2018

  Improving information flow across layers in D-CNNs

  Deep Convolutional Neural Networks (D-CNNs) can improve performance in image recognition. However, they are very…

  6
• An introduction to Deep Learning for Image and Video Interpretation at the University Carlos III of Madrid. Nov 4, 2017

  An introduction to Deep Learning for Image and Video Interpretation at the University Carlos III of Madrid.

  I am very honored to give a talk about Deep Learning for Image Recognition to the Ph.D.

  4 2 Comments

Show more See all articles

Explore content categories

• Career
• Productivity
• Finance
• Soft Skills & Emotional Intelligence
• Project Management
• Education
• Technology
• Leadership
• Ecommerce
• User Experience
• Recruitment & HR
• Customer Experience
• Real Estate
• Marketing
• Sales
• Retail & Merchandising
• Science
• Supply Chain Management
• Future Of Work
• Consulting
• Writing
• Economics
• Artificial Intelligence
• Employee Experience
• Workplace Trends
• Fundraising
• Networking
• Corporate Social Responsibility
• Negotiation
• Communication
• Engineering
• Hospitality & Tourism
• Business Strategy
• Change Management
• Organizational Culture
• Design
• Innovation
• Event Planning
• Training & Development

Show more Show less