logo
ResearchBunny Logo
Deep learning from "passive feeding" to "selective eating" of real-world data

Medicine and Health

Deep learning from "passive feeding" to "selective eating" of real-world data

Z. Li, C. Guo, et al.

Discover how a groundbreaking deep learning-based image filtering system (DLIFS) enhances AI diagnostic performance for ocular fundus diseases. This innovative approach, developed by Zhongwen Li and colleagues, filters out poor-quality images, ensuring more accurate diagnostics in real-world applications. Find out how this research can transform AI in healthcare!

00:00
00:00
Playback language: English
Abstract
This paper introduces a deep learning-based image filtering system (DLIFS) designed to improve the performance of AI diagnostic systems in real-world settings by filtering out poor-quality images. The DLIFS achieved high sensitivity and specificity in three independent datasets, significantly improving the performance of established AI diagnostic systems for detecting various ocular fundus diseases. The study highlights the necessity of "selective eating" of real-world data in developing robust image-based AI systems.
Publisher
npj Digital Medicine
Published On
Oct 30, 2020
Authors
Zhongwen Li, Chong Guo, Danyao Nie, Duoru Lin, Yi Zhu, Chuan Chen, Lanqin Zhao, Xiaohang Wu, Meimei Dongye, Fabao Xu, Chenjin Jin, Ping Zhang, Yu Han, Pisong Yan, Haotian Lin
Tags
deep learning
image filtering
AI diagnostics
ocular fundus diseases
real-world data

Related Publications

Explore these studies to deepen your understanding of the subject.

UroPredict: Machine learning model on real-world data for prediction of kidney cancer recurrence (UroCCR-120)
Medicine and Health

UroPredict: Machine learning model on real-world data for prediction of kidney cancer recurrence (UroCCR-120)

G. Margue, L. Ferrer, et al.

Real-world effectiveness of a social-psychological intervention translated from controlled trials to classrooms
Education

Real-world effectiveness of a social-psychological intervention translated from controlled trials to classrooms

P. Chen, D. W. H. Teo, et al.

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing
Computer Science

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing

D. Rankin, M. Black, et al.

Analyses of canine cancer mutations and treatment outcomes using real-world clinico-genomics data of 2119 dogs
Veterinary Science

Analyses of canine cancer mutations and treatment outcomes using real-world clinico-genomics data of 2119 dogs

K. Wu, L. Rodrigues, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny