Cascaded learning in intravascular ultrasound: coronary stent delineation in manual pullbacks

医学 支架 血管内超声 分割 经皮冠状动脉介入治疗 放射科 人工智能 背景(考古学) 计算机科学 心肌梗塞 内科学 生物 古生物学
作者
Tobias Wissel,Katharina A. Riedl,Klaus Schaefers,Hannes Nickisch,Fabian J. Brunner,Nikolas D. Schnellbaecher,Stefan Blankenberg,Moritz Seiffert,Michael Grass
出处
期刊:Journal of medical imaging [SPIE - International Society for Optical Engineering]
卷期号:9 (02)
标识
DOI:10.1117/1.jmi.9.2.025001
摘要

Purpose: Implanting stents to re-open stenotic lesions during percutaneous coronary interventions is considered a standard treatment for acute or chronic coronary syndrome. Intravascular ultrasound (IVUS) can be used to guide and assess the technical success of these interventions. Automatically segmenting stent struts in IVUS sequences improves workflow efficiency but is non-trivial due to a challenging image appearance entailing manifold ambiguities with other structures. Manual, ungated IVUS pullbacks constitute a challenge in this context. We propose a fully data-driven strategy to first longitudinally detect and subsequently segment stent struts in IVUS frames. Approach: A cascaded deep learning approach is presented. It first trains an encoder model to classify frames as "stent," "no stent," or "no use." A segmentation model then delineates stent struts on a pixel level only in frames with a stent label. The first stage of the cascade acts as a gateway to reduce the risk for false positives in the second stage, the segmentation, which is trained on a smaller and difficult-to-annotate dataset. Training of the classification and segmentation model was based on 49,888 and 1826 frames of 74 sequences from 35 patients, respectively. Results: The longitudinal classification yielded Dice scores of 92.96%, 82.35%, and 94.03% for the classes stent, no stent, and no use, respectively. The segmentation achieved a Dice score of 65.1% on the stent ground truth (intra-observer performance: 75.5%) and 43.5% on all frames (including frames without stent, with guidewires, calcium, or without clinical use). The latter improved to 49.5% when gating the frames by the classification decision and further increased to 57.4% with a heuristic on the plausible stent strut area. Conclusions: A data-driven strategy for segmenting stents in ungated, manual pullbacks was presented-the most common and practical scenario in the time-critical clinical workflow. We demonstrated a mitigated risk for ambiguities and false positive predictions.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
2秒前
gomm完成签到,获得积分10
3秒前
4秒前
明年发布了新的文献求助10
7秒前
科研通AI2S应助燕祁采纳,获得10
7秒前
qqq完成签到,获得积分10
9秒前
9秒前
二甲酚橙完成签到,获得积分10
10秒前
10秒前
10秒前
12秒前
刘佳灏完成签到,获得积分10
12秒前
CipherSage应助西北望采纳,获得10
14秒前
今后应助善良的小白菜采纳,获得10
14秒前
一一应助左白易采纳,获得20
15秒前
15秒前
孤独银耳汤关注了科研通微信公众号
15秒前
刘佳灏发布了新的文献求助10
16秒前
孙成成完成签到 ,获得积分10
19秒前
Ls完成签到 ,获得积分10
19秒前
Jenny完成签到,获得积分10
19秒前
Lucas应助爱幻想的青柠采纳,获得10
22秒前
夏沫完成签到,获得积分10
22秒前
ider给ider的求助进行了留言
23秒前
999z完成签到,获得积分10
24秒前
24秒前
左白易完成签到,获得积分10
25秒前
25秒前
25秒前
白鸽应助Last炫神丶采纳,获得10
25秒前
李爱国应助甜蜜的飞松采纳,获得30
26秒前
Lucia发布了新的文献求助30
26秒前
TORCH完成签到 ,获得积分10
27秒前
28秒前
29秒前
明年关注了科研通微信公众号
31秒前
张怡博完成签到 ,获得积分10
34秒前
35秒前
天真的tian发布了新的文献求助10
35秒前
热心的咖啡豆完成签到,获得积分10
41秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Le dégorgement réflexe des Acridiens 800
Defense against predation 800
Very-high-order BVD Schemes Using β-variable THINC Method 568
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3136067
求助须知:如何正确求助?哪些是违规求助? 2786953
关于积分的说明 7779912
捐赠科研通 2443071
什么是DOI,文献DOI怎么找? 1298892
科研通“疑难数据库(出版商)”最低求助积分说明 625244
版权声明 600870