DETECTION AND LOCALIZATION OF RETINAL BREAKS IN ULTRAWIDEFIELD FUNDUS PHOTOGRAPHY USING a YOLO v3 ARCHITECTURE-BASED DEEP LEARNING MODEL

人工智能 眼底摄影 视网膜 深度学习 眼底(子宫) 试验装置 目标检测 接收机工作特性 标准测试图像 计算机科学 模式识别(心理学) 眼科 图像(数学) 医学 图像处理 机器学习 荧光血管造影
作者
Richul Oh,Baek‐Lok Oh,Eun Kyoung Lee,Un Chul Park,Hyeong Gon Yu,Chang Ki Yoon
出处
期刊:Retina-the Journal of Retinal and Vitreous Diseases [Lippincott Williams & Wilkins]
卷期号:42 (10): 1889-1896 被引量:2
标识
DOI:10.1097/iae.0000000000003550
摘要

Purpose: We aimed to develop a deep learning model for detecting and localizing retinal breaks in ultrawidefield fundus (UWF) images. Methods: We retrospectively enrolled treatment-naive patients diagnosed with retinal break or rhegmatogenous retinal detachment and who had UWF images. The YOLO v3 architecture backbone was used to develop the model, using transfer learning. The performance of the model was evaluated using per-image classification and per-object detection. Results: Overall, 4,505 UWF images from 940 patients were used in the current study. Among them, 306 UWF images from 84 patients were included in the test set. In per-object detection, the average precision for the object detection model considering every retinal break was 0.840. With the best threshold, the overall precision, recall, and F1 score were 0.6800, 0.9189, and 0.7816, respectively. In the per-image classification, the model showed an area under the receiver operating characteristic curve of 0.957 within the test set. The overall accuracy, sensitivity, and specificity in the test data set were 0.9085, 0.8966, and 0.9158, respectively. Conclusion: The UWF image-based deep learning model evaluated in the current study performed well in diagnosing and locating retinal breaks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
WANGSONGLU发布了新的文献求助10
刚刚
huoyan2006应助阿良采纳,获得10
刚刚
刚刚
zho发布了新的文献求助10
刚刚
韩较瘦完成签到,获得积分0
刚刚
白茶发布了新的文献求助10
1秒前
慕青应助斯文芷荷采纳,获得10
2秒前
chx发布了新的文献求助10
3秒前
华仔应助SUNSHINE采纳,获得10
3秒前
shinn发布了新的文献求助10
4秒前
充电宝应助春去春来采纳,获得30
4秒前
5秒前
小豆芽完成签到,获得积分10
5秒前
东日完成签到,获得积分10
7秒前
共享精神应助冷酷的猎豹采纳,获得10
7秒前
8秒前
李爱国应助muyi采纳,获得10
8秒前
IanYoung71完成签到,获得积分10
8秒前
yuu完成签到,获得积分10
9秒前
英姑应助玉洁采纳,获得10
10秒前
华仔应助WANGSONGLU采纳,获得10
10秒前
哥哥喜欢格格完成签到 ,获得积分10
10秒前
欢呼尔烟完成签到,获得积分10
10秒前
Yoh1220完成签到,获得积分10
10秒前
10秒前
angelinazh发布了新的文献求助10
10秒前
皇家火鸡完成签到,获得积分10
11秒前
13秒前
善学以致用应助o30采纳,获得10
14秒前
YamDaamCaa应助lyjj023采纳,获得30
14秒前
柴柴子完成签到,获得积分10
14秒前
天竹子发布了新的文献求助10
14秒前
李健应助啵清啵采纳,获得10
14秒前
小巧映之完成签到 ,获得积分10
15秒前
orixero应助奶油布丁采纳,获得10
15秒前
虚心蜗牛完成签到 ,获得积分10
15秒前
深情安青应助张佳明采纳,获得10
15秒前
16秒前
dypdyp应助感动的红酒采纳,获得10
16秒前
magic完成签到,获得积分10
16秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969458
求助须知:如何正确求助?哪些是违规求助? 3514286
关于积分的说明 11173363
捐赠科研通 3249652
什么是DOI,文献DOI怎么找? 1794948
邀请新用户注册赠送积分活动 875501
科研通“疑难数据库(出版商)”最低求助积分说明 804836