arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04522cs.CV
收藏

ConfIC-RCA:具有统计保证的无标注条件下分割质量高效估计

ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Quality

Institute of Computer Sciences (CONICET - Universidad de Buenos Aires)(计算机科学研究所(CONICET - 布宜诺斯艾利斯大学));APOLO Biotech(APOLO生物技术公司);Universidad Nacional de San Martin(国立圣马丁大学);Faculty of Engineering, Bar-Ilan University(巴伊兰大学工程学院);Research Institute of Signals, Systems and Computational Intelligence, sinc(i) (CONICET - Universidad Nacional del Litoral)(信号、系统与计算智能研究所,sinc(i)(CONICET - 国立滨海大学));Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière(索邦大学,大脑研究所 - 巴黎大脑研究所 - ICM,CNRS,Inria,Inserm,AP-HP,皮提耶-萨勒佩特里医院)

Matias Cosarinsky, Ramiro Billot, Lucas Mansilla, Gabriel Jimenez, Nicolas Gaggión, Guanghui Fu, Tom Tirer, Enzo Ferrante

AI总结:

本文提出ConfIC-RCA方法,通过引入In-Context RCA和Conformal RCA,在无标注数据情况下实现分割质量的统计保证估计,适用于多种医学影像任务,具有高效和可靠的特点。

摘要:

评估自动图像分割质量在临床实践中至关重要,但通常由于标注数据有限而极具挑战性。反向分类准确率(RCA)是一种通过在未见过的样本上训练分割器并评估现有标注图像来估计新预测质量的方法。本文介绍了ConfIC-RCA(Conformal In-Context RCA),一种在无标注数据情况下自动估计分割质量并提供统计保证的新方法,包含两个主要创新:首先,In-Context RCA利用最近的上下文学习模型进行图像分割,并结合检索增强技术选择最相关的参考图像,从而在少量参考数据的情况下实现高效的质量估计,而无需训练额外模型。其次,我们引入了Conformal RCA,扩展了原始RCA框架和In-Context RCA,超越了点估计,利用分割置信预测工具,为分割质量生成预测区间,提供统计保证,即真实分数在估计区间内以用户指定的概率。在10种不同的医学影像任务中验证,我们的方法表现出稳健的性能和计算效率,为临床工作流程中的自动化质量控制提供了一种有前景的解决方案,其中快速且可靠的分割评估至关重要。代码可在https://github.com/mcosarinsky/Conformal-In-Context-RCA获取。

英文摘要:

Assessing the quality of automatic image segmentation is crucial in clinical practice, but often very challenging due to the limited availability of ground truth annotations. Reverse Classification Accuracy (RCA) is an approach that estimates the quality of new predictions on unseen samples by training a segmenter on those predictions, and then evaluating it against existing annotated images. In this work we introduce ConfIC-RCA (Conformal In-Context RCA), a novel method for automatically estimating segmentation quality with statistical guarantees in the absence of ground-truth annotations, which consists of two main innovations. First, In-Context RCA, which leverages recent in-context learning models for image segmentation and incorporates retrieval-augmentation techniques to select the most relevant reference images. This approach enables efficient quality estimation with minimal reference data while avoiding the need of training additional models. Second, we introduce Conformal RCA, which extends both the original RCA framework and In-Context RCA to go beyond point estimation. Using tools from split conformal prediction, Conformal RCA produces prediction intervals for segmentation quality providing statistical guarantees that the true score lies within the estimated interval with a user-specified probability. Validated across 10 different medical imaging tasks in various organs and modalities, our methods demonstrate robust performance and computational efficiency, offering a promising solution for automated quality control in clinical workflows, where fast and reliable segmentation assessment is essential. The code is available at https://github.com/mcosarinsky/Conformal-In-Context-RCA

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑