arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.17792eess.IVcs.CVq-bio.NC
收藏

可解释深度学习在神经影像学中的应用:全面综述

Applications of interpretable deep learning in neuroimaging: a comprehensive review

University of Eastern Finland(东芬兰大学)

Lindsay Munroe, Mariana da Silva, Faezeh Heidari, Irina Grigorescu, Simon Dahan, Emma C. Robinson, Maria Deprez, Po-Wah So

AI总结:

本文综述了75项关于可解释深度学习在神经影像学应用的研究,分析了10类iDL方法及5个解释属性,发现现有流行方法对神经影像数据可能次优并指明未来方向。

摘要:

深度学习模型的临床应用在一定程度上受到了阻碍,因为神经网络的黑盒特性引发了人们对其可信度和可靠性的担忧。由于神经影像学中常遇到复杂的大脑表型和受试者间的异质性,这些担忧在该领域尤为突出。可解释深度学习(iDL)方法能够实现深度学习模型内部工作机制的可视化与解释,从而应对这一挑战。本研究系统回顾了iDL方法在神经影像学应用方面的文献,并批判性地分析了如何评估iDL的解释属性。共纳入了75项研究,并识别出10类iDL方法。我们还回顾了纳入研究中分析的iDL解释的5个属性:生物学有效性、鲁棒性、连续性、选择性和下游任务性能。我们发现文献中最常用的iDL方法对于神经影像数据可能是次优的,并探讨了该领域未来可能的发展方向。

英文摘要:

Clinical adoption of deep learning models has been hindered, in part, because the black-box nature of neural networks leads to concerns regarding their trustworthiness and reliability. These concerns are particularly relevant in the field of neuroimaging due to the complex brain phenotypes and inter-subject heterogeneity often encountered. The challenge can be addressed by interpretable deep learning (iDL) methods that enable the visualisation and interpretation of the inner workings of deep learning models. This study systematically reviewed the literature on neuroimaging applications of iDL methods and critically analysed how iDL explanation properties were evaluated. Seventy-five studies were included, and ten categories of iDL methods were identified. We also reviewed five properties of iDL explanations that were analysed in the included studies: biological validity, robustness, continuity, selectivity, and downstream task performance. We found that the most popular iDL approaches used in the literature may be sub-optimal for neuroimaging data, and we discussed possible future directions for the field.

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。

↑