arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.07618cs.CVcs.LGeess.IV
收藏

基于局部Lipschitz的深度学习图像重建不确定性估计与分布外检测

Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz

Harvard University(哈佛大学);Google Research(谷歌研究院);Harvard Medical School(哈佛医学院);Massachusetts General Hospital(麻省总医院);Boston University(波士顿大学)

Danyal F. Bhutto, Bo Zhu, Jeremiah Z. Liu, Neha Koonjoo, Hongwei B. Li, Bruce R. Rosen, Matthew S. Rosen

AI总结:

本文提出基于局部Lipschitz度量的方法,用于深度学习医学图像重建中的分布外检测与不确定性估计,AUC达99.94%,并通过其与MAE的强相关性指导数据增强以降低模型不确定性。

摘要:

准确的图像重建是医学影像诊断的核心。已有研究探索了基于监督深度学习的方法来求解包括图像重建在内的逆问题。然而,这些训练好的模型在部署过程中会遇到与训练数据分布存在显著偏移的未见数据分布。因此,为了诊断目的,评估给定输入是否落在训练数据分布范围内至关重要。现有的不确定性估计方法主要侧重于向放射科医生提供不确定性图,而不是评估训练分布的拟合程度。在本工作中,我们提出了一种基于局部Lipschitz度量的方法,用于区分分布外图像与分布内图像,曲线下面积达到99.94%。通过实验,我们证明了局部Lipschitz值与平均绝对误差(MAE)之间存在非常强的关系,其Spearman秩相关系数高达0.8475,这一关系可用于确定实现最优模型性能的不确定性估计阈值。通过识别假阳性,局部Lipschitz与MAE之间的关系被用于指导数据增强并降低模型不确定性。我们的研究使用AUTOMAP架构进行传感器到图像的磁共振成像(MRI)重建来验证。我们将所提出的方法与基线方法进行了比较:Monte-Carlo dropout和深度集成,进一步的分析还包括使用UNET架构的MRI去噪和计算机断层扫描(CT)稀疏到全视角重建。我们表明,我们的方法适用于各种架构和学习函数,尤其是在医学图像重建领域,在该领域中保持重建图像的诊断准确性仍然至关重要。

英文摘要:

Accurate image reconstruction is at the heart of diagnostics in medical imaging. Supervised deep learning-based approaches have been investigated for solving inverse problems including image reconstruction. However, these trained models encounter unseen data distributions that are widely shifted from training data during deployment. Therefore, it is essential to assess whether a given input falls within the training data distribution for diagnostic purposes. Uncertainty estimation approaches exist but focus on providing an uncertainty map to radiologists, rather than assessing the training distribution fit. In this work, we propose a method based on the local Lipschitz-based metric to distinguish out-of-distribution images from in-distribution with an area under the curve of 99.94%. Empirically, we demonstrate a very strong relationship between the local Lipschitz value and mean absolute error (MAE), supported by a high Spearman's rank correlation coefficient of 0.8475, which determines the uncertainty estimation threshold for optimal model performance. Through the identification of false positives, the local Lipschitz and MAE relationship was used to guide data augmentation and reduce model uncertainty. Our study was validated using the AUTOMAP architecture for sensor-to-image Magnetic Resonance Imaging (MRI) reconstruction. We compare our proposed approach with baseline methods: Monte-Carlo dropout and deep ensembles, and further analysis included MRI denoising and Computed Tomography (CT) sparse-to-full view reconstruction using UNET architectures. We show that our approach is applicable to various architectures and learned functions, especially in the realm of medical image reconstruction, where preserving the diagnostic accuracy of reconstructed images remains paramount.

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。

↑