亲爱的研友该休息了!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,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

AI model for automatic 3D reconstruction of ossicular chain and bony labyrinth from High-Resolution CT

高分辨率 分辨率(逻辑) 解剖 计算机断层摄影术 地质学 口腔正畸科 计算机科学 医学 人工智能 放射科 遥感
作者
Mingwei Xie,Haonan Wang,Zehong Yang,Ming Gao,Guangzi Shi,Xing-Yun Liao,Zhuojing Luo,Xiaomeng Li,Jun Shen
标识
DOI:10.1093/radadv/umaf004
摘要

Abstract Background Three-dimensional (3D) reconstruction of ossicular chain and bony labyrinth based on temporal bone high resolution computed tomography (HRCT) is useful for diagnosis and treatment guidance of middle and inner ear diseases. However, these structures are small and irregular, making manual reconstruction time-consuming. Purpose To develop and validate an artificial intelligence (AI) model based on semi-supervised learning for automated 3D reconstruction of ossicular chain and bony labyrinth on HRCT images. Methods HRCT images from 304 ears of consecutive 152 patients retrospectively collected from a single center were randomly divided into training (246 ears), validation (28 ears) and internal test (30 ears) cohorts for model development. A novel semi-supervised ear bone segmentation framework was used to train the AI model, and its performance was evaluated by Dice similarity coefficients. The trained algorithm was applied to a temporally independent test dataset of 30 ears of 15 patients from the same center for comparison with manual 3D reconstruction for processing time, target volume and visual assessment of segmentation. Results The AI model demonstrated a Dice score of 0.948 (95% CI: 0.940, 0.955) for the internal and 0.979 (95% CI: 0.973, 0.986) for the temporally independent test sets. In the latter dataset, the AI model required 2% or less processing time of manual 3D reconstruction for each ear (17.7 seconds ± 10.1 vs 1080.5 seconds ± 149.8; P < .001), and had an accuracy comparable to human experts in the volume and visual assessment of segmentation targets (P = .237-1.000). In a subgroup analysis, the model achieved accurate segmentation (Dice scores of 0.98-0.99) across various diseases (e.g. otitis media, mastoiditis, otosclerosis, middle and inner ear malformations, and Ménière’s disease). Conclusion The AI model enables robust, efficient and accurate 3D reconstruction for the small structures such as ossicular chain and bony labyrinth on HRCT images.

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
1777发布了新的文献求助10
2秒前
15秒前
早茶可口完成签到,获得积分10
16秒前
奥德彪爱拉香蕉皮完成签到,获得积分10
25秒前
阿里完成签到,获得积分10
28秒前
1分钟前
1分钟前
1分钟前
leinei发布了新的文献求助10
1分钟前
整齐的不评完成签到,获得积分10
1分钟前
香蕉觅云应助中华男子汉采纳,获得10
1分钟前
2分钟前
顾矜应助jj采纳,获得10
3分钟前
阔达的沛文完成签到,获得积分10
3分钟前
3分钟前
3分钟前
3分钟前
jj发布了新的文献求助10
3分钟前
ph发布了新的文献求助30
3分钟前
3分钟前
ph完成签到,获得积分20
3分钟前
3分钟前
爱静静完成签到,获得积分0
3分钟前
yhgz完成签到,获得积分10
4分钟前
Criminology34发布了新的文献求助300
4分钟前
大模型应助leinei采纳,获得30
5分钟前
5分钟前
CRUSADER发布了新的文献求助10
5分钟前
5分钟前
CRUSADER完成签到,获得积分10
5分钟前
商毛毛发布了新的文献求助10
5分钟前
大饼完成签到 ,获得积分10
6分钟前
cc完成签到,获得积分20
6分钟前
6分钟前
6分钟前
菠萝炒饭不要辣椒完成签到,获得积分10
6分钟前
6分钟前
朱明完成签到 ,获得积分10
6分钟前
balko完成签到,获得积分10
7分钟前
LiangRen完成签到 ,获得积分10
7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
Practical Methods for Aircraft and Rotorcraft Flight Control Design: An Optimization-Based Approach 1000
2025-2031年中国兽用抗生素行业发展深度调研与未来趋势报告 1000
List of 1,091 Public Pension Profiles by Region 831
The International Law of the Sea (fourth edition) 800
A Guide to Genetic Counseling, 3rd Edition 500
Synthesis and properties of compounds of the type A (III) B2 (VI) X4 (VI), A (III) B4 (V) X7 (VI), and A3 (III) B4 (V) X9 (VI) 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 纳米技术 计算机科学 内科学 化学工程 复合材料 物理化学 基因 遗传学 催化作用 冶金 量子力学 光电子学
热门帖子
关注 科研通微信公众号,转发送积分 5413274
求助须知:如何正确求助?哪些是违规求助? 4530416
关于积分的说明 14122912
捐赠科研通 4445436
什么是DOI,文献DOI怎么找? 2439191
邀请新用户注册赠送积分活动 1431244
关于科研通互助平台的介绍 1408746