arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.19557eess.IVcs.CVphysics.med-ph
收藏

通过测试时增强对黑盒模型进行CT退化鲁棒性测试

Robustness Testing of Black-Box Models Against CT Degradation Through Test-Time Augmentation

School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与影像科学学院);Aival Ltd.(艾瓦尔有限公司);School of Computation, Information and Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);Helmholtz Munich(慕尼黑亥姆霍兹中心)

Jack Highton, Quok Zong Chong, Samuel Finestone, Arian Beqiri, Julia A. Schnabel, Kanwal K. Bhatia

AI总结:

本文提出一种基于测试时增强的黑盒鲁棒性测试框架,仅用少量本地病例即可评估CT分割与检测模型对图像质量退化的鲁棒性,并揭示模型架构和预处理对鲁棒性的显著影响。

摘要:

用于医学图像分割和目标检测的深度学习模型正越来越多地作为临床产品提供。然而,由于训练数据的细节很少被披露,当病例与训练分布中的情况不同时,模型可能会意外失效。一种允许潜在用户独立测试模型鲁棒性的方法,将模型视为黑盒,并仅使用来自其自身机构的少量病例,对于模型的采用至关重要。为了解决这一问题,本文提出了一种测试这些模型对CT图像质量变化的鲁棒性的方法。在这项工作中,我们通过证明在给定相同训练数据的情况下,模型架构和数据预处理会极大地影响几种常用分割和目标检测方法对模拟CT成像伪影和退化的鲁棒性,来展示这一框架。我们的框架还通过考虑由于扫描仪老化或成像协议变化引起的未来图像质量偏移(而这些偏移在有限的本地测试数据集中并未体现),回应了深度学习模型在临床使用中可持续性的担忧。

英文摘要:

Deep learning models for medical image segmentation and object detection are becoming increasingly available as clinical products. However, as details are rarely provided about the training data, models may unexpectedly fail when cases differ from those in the training distribution. An approach allowing potential users to independently test the robustness of a model, treating it as a black box and using only a few cases from their own site, is key for adoption. To address this, a method to test the robustness of these models against CT image quality variation is presented. In this work we present this framework by demonstrating that given the same training data, the model architecture and data pre processing greatly affect the robustness of several frequently used segmentation and object detection methods to simulated CT imaging artifacts and degradation. Our framework also addresses the concern about the sustainability of deep learning models in clinical use, by considering future shifts in image quality due to scanner deterioration or imaging protocol changes which are not reflected in a limited local test dataset.

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。

↑