Munroe Lindsay, da Silva Mariana, Heidari Faezeh, Grigorescu Irina, Dahan Simon, Robinson Emma C, Deprez Maria, So Po-Wah
Department of Neuroimaging, King's College London, London, United Kingdom.
School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.
Imaging Neurosci (Camb). 2024 Jul 12;2. doi: 10.1162/imag_a_00214. eCollection 2024.
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.
深度学习模型在临床应用中受到了阻碍，部分原因是神经网络的“黑箱”性质引发了人们对其可信度和可靠性的担忧。由于经常遇到复杂的脑表型和个体间异质性，这些担忧在神经影像学领域尤为突出。可解释深度学习（iDL）方法能够可视化和解释深度学习模型的内部工作原理，从而应对这一挑战。本研究系统回顾了关于iDL方法在神经影像学应用的文献，并批判性地分析了iDL解释特性是如何评估的。纳入了75项研究，确定了10类iDL方法。我们还回顾了纳入研究中分析的iDL解释的五个特性：生物学有效性、稳健性、连续性、选择性和下游任务性能。我们发现，文献中使用的最流行的iDL方法可能对神经影像学数据并非最优，并且我们讨论了该领域未来可能的发展方向。
