Ensemble-based uncertainty enables large-scale 3d segmentation quality control in population imaging

作者
Tobias Norajitra,Tobias Nonnenmacher,Tobias Haueise,Fabian Isensee,Maximilian Zenk,Lea J. Michel,Jan Warszawski,Marc-Nicolas von Itter,Steffen Ringhof,Thoralf Niendorf,Jessica Krepel,Manuela Harries,Rafael Mikolajczyk,Jochen Hirsch,Daniel Christopher Hoinkiss,Thomas Kroencke,Josua Decker,FILIPPO C. MICHELOTTI,Christoph M. Friedrich,Johannes Haubold
出处
期刊:Medical Image Analysis [Elsevier BV]
卷期号:: 104351-104351
标识
DOI:10.1016/j.media.2026.104351
摘要

Modern Deep-Learning facilitates automatic segmentation in large imaging studies. To prevent segmentation errors from impacting data analysis, automated quality control (QC) for filtering segmentations and identifying errors ( segmentation selection ) is essential. QC must be fast and require minimal expert delineations for application to various ROIs in large datasets. Uncertainty quantification methods capable of estimating segmentation error without ground truth offer a promising foundation. However, their implicit error estimation may lack accuracy, making suitability for segmentation selection unclear. Unfortunately, commonly employed evaluation measures cannot capture their segmentation selection capability. Furthermore, selecting or rejecting segmentations based on uncertainty alone can be non-trivial. We propose a new method for efficient segmentation QC in large imaging cohorts. We comprehensively evaluate uncertainty-based error estimators with respect to key goals of large-scale QC, specifically assessing segmentation selection capability through the area under the risk-coverage-curve. To optimize selection and rejection, we employ a binary search for decision thresholds, balancing the risk of including errors and unnecessarily rejecting segmentations. In > 11 000 MRI liver and lung segmentations in the German National Cohort, error estimation using the pairwise Dice of ensemble outputs achieved excellent QC, including segmentation selection. Numerous manually hard-to-detect errors and abnormalities ( n > 400 ) were identified during high-quality result selection, measurably restoring integrity of volume and fat measurements. QC was fast ( 0.29 − 4.48 s/case ) and required minimal annotated image data ( n < 125 ). Our method can help tackle the challenge of reliable automated QC in large-scale segmentation studies.

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
梁凉凉完成签到 ,获得积分10
刚刚
科研小能手完成签到,获得积分10
刚刚
刚刚
nn完成签到,获得积分10
1秒前
Aiven完成签到,获得积分10
1秒前
Lenacici完成签到,获得积分10
1秒前
Cc关注了科研通微信公众号
1秒前
全麦小钢板完成签到,获得积分10
2秒前
挽梦丸子发布了新的文献求助10
2秒前
2秒前
xiaoluoluo完成签到,获得积分10
2秒前
2秒前
bei完成签到,获得积分10
2秒前
feilei完成签到,获得积分10
2秒前
戴yao完成签到,获得积分10
3秒前
那你别管完成签到,获得积分10
3秒前
3秒前
99完成签到,获得积分10
3秒前
兰彻完成签到,获得积分10
4秒前
momo完成签到 ,获得积分10
4秒前
爆米花的应助被DrWei940313采纳,获得10
5秒前
SciGPT的应助被郭氧化氢采纳,获得10
5秒前
YY的应助被Pluto采纳,获得20
5秒前
搞怪的白云完成签到 ,获得积分0
5秒前
航某人完成签到,获得积分10
5秒前
feier完成签到,获得积分10
5秒前
5秒前
luoluoan发布了新的文献求助10
6秒前
6秒前
老德完成签到,获得积分10
6秒前
Pengcheng完成签到,获得积分10
6秒前
理论发布了新的文献求助10
7秒前
大胆妙松完成签到,获得积分10
7秒前
ding的应助被ly采纳,获得10
7秒前
看帅哥黑客技术完成签到,获得积分10
8秒前
不能当饭吃完成签到,获得积分0
8秒前
小虫子完成签到,获得积分10
8秒前
gonghe发布了新的文献求助10
8秒前
zyy完成签到,获得积分10
8秒前
IDCY完成签到,获得积分10
9秒前
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 1700
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
plantTFDB 508
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 8173474
求助须知:如何正确求助?哪些是违规求助? 9565719
关于积分的说明 21781727
捐赠科研通 7767700
什么是DOI,文献DOI怎么找? 3431597
关于科研通互助平台的介绍 2555855
邀请新用户注册赠送积分活动 2476832