清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Deep Learning–Based Estimation of Implantable Collamer Lens Vault Using Optical Coherence Tomography

光学相干层析成像 皮尔逊积矩相关系数 均方误差 相关系数 平均绝对百分比误差 人工神经网络 卡钳 人工智能 核医学 医学 决定系数 数学 计算机科学 统计 眼科 几何学
作者
Jad F. Assaf,Dan Z. Reinstein,Cyril Zakka,Juan Arbelaez,Peter Boufadel,Mathieu Choufani,Timothy J. Archer,Perla Ibrahim,Shady T. Awwad
出处
期刊:American Journal of Ophthalmology [Elsevier BV]
卷期号:253: 29-36 被引量:13
标识
DOI:10.1016/j.ajo.2023.04.008
摘要

•Deep learning neural network developed to automate measurement of ICL vault using AS-OCT. •Validated using 2647 scans from 139 eyes of 82 subjects from 3 different centers. •Model achieved a MAPE of 3.42%, MAE of 15.82 µm, RMSE of 18.85 µm, Pearson correlation coefficient r of +0.98, and coefficient of determination R2 of +0.96. •The model assists postoperative assessment in ICL surgery, reducing time and potential bias of manual measurements. PURPOSE To develop and validate a deep learning neural network for automated measurement of implantable collamer lens (ICL) vault using anterior segment optical coherence tomography (AS-OCT). DESIGN Cross-sectional retrospective study. METHODS A total of 2647 AS-OCT scans were used from 139 eyes of 82 subjects who underwent ICL surgery in 3 different centers. Using transfer learning, a deep learning network was trained and validated for estimating the ICL vault on OCT. A trained operator separately reviewed all OCT scans and measured the central vault using a built-in caliper tool. The model was then separately tested on 191 scans. A Bland-Altman plot was constructed and the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), Pearson correlation coefficient (r), and determination coefficient (R2) were calculated to evaluate the strength and validity of the model. RESULTS On the test set, the model achieved a MAPE of 3.42%, an MAE of 15.82 µm, a RMSE of 18.85 µm, a Pearson correlation coefficient r of +0.98 (P < .00001), and a coefficient of determination R2 of +0.96. There was no significant difference between the vaults of the test set labeled by the technician vs those estimated by the model: 478 ± 95 µm vs 475 ± 97 µm, respectively, P = .064). CONCLUSIONS Using transfer learning, our deep learning neural network was able to accurately compute the ICL vault from AS-OCT scans, overcoming the limitations of an imbalanced data set and limited training data. Such an algorithm can assist the postoperative assessment in ICL surgery. To develop and validate a deep learning neural network for automated measurement of implantable collamer lens (ICL) vault using anterior segment optical coherence tomography (AS-OCT). Cross-sectional retrospective study. A total of 2647 AS-OCT scans were used from 139 eyes of 82 subjects who underwent ICL surgery in 3 different centers. Using transfer learning, a deep learning network was trained and validated for estimating the ICL vault on OCT. A trained operator separately reviewed all OCT scans and measured the central vault using a built-in caliper tool. The model was then separately tested on 191 scans. A Bland-Altman plot was constructed and the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), Pearson correlation coefficient (r), and determination coefficient (R2) were calculated to evaluate the strength and validity of the model. On the test set, the model achieved a MAPE of 3.42%, an MAE of 15.82 µm, a RMSE of 18.85 µm, a Pearson correlation coefficient r of +0.98 (P < .00001), and a coefficient of determination R2 of +0.96. There was no significant difference between the vaults of the test set labeled by the technician vs those estimated by the model: 478 ± 95 µm vs 475 ± 97 µm, respectively, P = .064). Using transfer learning, our deep learning neural network was able to accurately compute the ICL vault from AS-OCT scans, overcoming the limitations of an imbalanced data set and limited training data. Such an algorithm can assist the postoperative assessment in ICL surgery.
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
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
威武的碧玉完成签到,获得积分10
15秒前
alei089完成签到 ,获得积分10
16秒前
21秒前
李木禾完成签到 ,获得积分10
23秒前
李S完成签到 ,获得积分10
26秒前
Aman发布了新的文献求助10
28秒前
雪白的魔镜完成签到,获得积分10
31秒前
大意的山水完成签到,获得积分10
31秒前
开放的蚂蚁完成签到,获得积分10
39秒前
wwrjj完成签到,获得积分0
42秒前
SongXJ完成签到 ,获得积分10
45秒前
多情敏完成签到,获得积分10
45秒前
迅速的书雁完成签到,获得积分10
1分钟前
鲤鱼从安完成签到,获得积分10
1分钟前
积极的一江完成签到,获得积分10
1分钟前
无私的迎蓉完成签到,获得积分10
1分钟前
危机的曼卉完成签到,获得积分10
1分钟前
zhangguo完成签到 ,获得积分10
1分钟前
落后的山槐完成签到,获得积分10
1分钟前
Imran完成签到,获得积分10
1分钟前
虚拟的白云完成签到,获得积分10
2分钟前
甜甜的文轩完成签到,获得积分10
2分钟前
FashionBoy的应助被牛魔采纳,获得10
2分钟前
2分钟前
牛魔发布了新的文献求助10
2分钟前
动听的诗翠完成签到,获得积分10
2分钟前
细腻海瑶完成签到,获得积分10
2分钟前
vitamin完成签到 ,获得积分0
2分钟前
不安荟完成签到,获得积分10
2分钟前
fys131415完成签到 ,获得积分10
2分钟前
呆萌的孤云完成签到,获得积分10
2分钟前
2分钟前
嘻嘻发布了新的文献求助10
2分钟前
华无剑的应助被研友_闾丘枫采纳,获得10
3分钟前
Shiyuzz完成签到 ,获得积分10
3分钟前
华无剑的应助被研友_闾丘枫采纳,获得10
3分钟前
zyjsunye完成签到 ,获得积分10
3分钟前
大力的以山完成签到,获得积分10
3分钟前
欢呼亦绿完成签到,获得积分10
3分钟前
Seagull完成签到,获得积分10
3分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159011
求助须知:如何正确求助?哪些是违规求助? 9554538
关于积分的说明 21719454
捐赠科研通 7748561
什么是DOI,文献DOI怎么找? 3427123
关于科研通互助平台的介绍 2552021
邀请新用户注册赠送积分活动 2471370