문의하기 아이콘
문의하기 텍스트
top 아이콘
coreline logo
close icon
Cookie Settings Information

When you visit our website, we store cookies on your browser to collect information. The information collected may relate to you, your device, or your preferences, and is primarily used to ensure the website functions properly and to provide a more personalized web experience.

However, you may choose to disallow certain types of cookies, which could affect your user experience and the services we are able to offer. You can click on each category below to learn more and adjust your default settings.

Please note that Strictly Necessary Cookies are essential for the basic functioning of the website and cannot be disabled (e.g., maintaining login sessions, remembering settings). For more detailed information about cookies, please refer to our [Privacy Policy].

Manage Consent Preferences
+Strictly Necessary CookiesAlways Active
These cookies are essential for the website to function properly and cannot be switched off in our systems. They are usually set only in response to actions you take, such as setting your privacy preferences, logging in, or filling out forms. You can set your browser to block or alert you about these cookies, but some parts of the site may not function properly as a result. These cookies do not store any personally identifiable information.
+Targeting Cookies
These cookies may be set through our site by our advertising partners. They are used to build a profile of your interests and show you relevant advertisements on other sites. These cookies do not directly store personal information but operate based on unique identification of your browser and device. If you do not allow these cookies, you will experience less targeted advertising.
+Performance
These cookies allow us to aggregate the number of visitors and traffic sources in order to measure and improve the performance of our website. They help us understand which pages are the most popular and how visitors navigate through the site. All information collected is aggregated and therefore anonymous. If you do not allow these cookies, we will not be able to monitor the performance of our site or know when you have visited it.
Save My Choices

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging

Authors
Yongwon Cho, Hyungjoon Cho, Jaemin Shim, Jong-Il Choi, Young-Hoon Kim, Namkug Kim, Yu-Whan Oh, Sung Ho Hwang
Journal
Journal of Korean Medical Science
Related Product

Research

Date Published
2022.09
Summary

This study proposes an automatic segmentation method for the left atrium using deep active learning in late gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMRI). Ninety-eight atrial fibrillation patients from Korea University Anam Hospital were included. Initially, 20 cases were delineated by experts to create a draft model. This model was then refined using an additional 50 cases corrected through a human-in-the-loop process, culminating in a final training set of 98 cases. The segmentation's accuracy improved across three steps, with Dice coefficients of 0.85, 0.89, and 0.90, respectively. Biases in Bland-Altman plots decreased progressively, indicating improved consistency. Annotation times were significantly reduced from 218 seconds to approximately 36 seconds. This framework demonstrated that deep active learning significantly reduces annotation time and enables efficient training with a limited dataset in LGE-CMRI, making it a valuable approach for automating left atrium segmentation. For the ground-truth segmentation, AVIEW Research is used during the research.

Contact

Please leave your inquiry if you have any questions regarding our products, recruitment, investment, or any other matters.

Contact us