Ellis Charles A, Miller Robyn L, Calhoun Vince D
Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 313 Ferst Dr NW, Atlanta, 30332, GA, United States.
Tri-institutional Center for Translational Research in Neuroimaging and Data Science: Georgia State University, Georgia Institute of Technology, Emory University, 55 Park Pl NE, Atlanta, GA, 30303, United States.
Inform Med Unlocked. 2023;37. doi: 10.1016/j.imu.2023.101176. Epub 2023 Jan 18.
The field of neuroimaging has increasingly sought to develop artificial intelligence-based models for neurological and neuropsychiatric disorder automated diagnosis and clinical decision support. However, if these models are to be implemented in a clinical setting, transparency will be vital. Two aspects of transparency are (1) confidence estimation and (2) explainability. Confidence estimation approaches indicate confidence in individual predictions. Explainability methods give insight into the importance of features to model predictions. In this study, we integrate confidence estimation and explainability approaches for the first time. We demonstrate their viability for schizophrenia diagnosis using resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) data. We compare two confidence estimation approaches: Monte Carlo dropout (MCD) and MC batch normalization (MCBN). We combine them with two gradient-based explainability approaches, saliency and layer-wise relevance propagation (LRP), and examine their effects upon explanations. We find that MCD often adversely affects model gradients, making it ill-suited for integration with gradient-based explainability methods. In contrast, MCBN does not affect model gradients. Additionally, we find many participant-level differences between regular explanations and the distributions of explanations for combined explainability and confidence estimation approaches. This suggests that a similar confidence estimation approach used in a clinical context with explanations only output for the regular model would likely not yield adequate explanations. We hope that our findings will provide a starting point for the integration of the two fields, provide useful guidance for future studies, and accelerate the development of transparent neuroimaging clinical decision support systems.
神经影像学领域越来越多地寻求开发基于人工智能的模型，用于神经和神经精神疾病的自动诊断及临床决策支持。然而，如果要在临床环境中应用这些模型，透明度将至关重要。透明度的两个方面是：（1）置信度估计和（2）可解释性。置信度估计方法表明对个体预测的置信度。可解释性方法能深入了解特征对模型预测的重要性。在本研究中，我们首次将置信度估计和可解释性方法进行整合。我们使用静息态功能磁共振成像（rs-fMRI）动态功能网络连接性（dFNC）数据，证明了它们在精神分裂症诊断中的可行性。我们比较了两种置信度估计方法：蒙特卡洛随机失活（MCD）和蒙特卡洛批归一化（MCBN）。我们将它们与两种基于梯度的可解释性方法——显著性和逐层相关性传播（LRP）相结合，并研究它们对解释的影响。我们发现，MCD常常会对模型梯度产生不利影响，使其不适于与基于梯度的可解释性方法相结合。相比之下，MCBN不会影响模型梯度。此外，我们发现常规解释与结合了可解释性和置信度估计方法后的解释分布之间存在许多参与者层面的差异。这表明，在临床环境中使用仅为常规模型输出解释的类似置信度估计方法，可能无法产生足够的解释。我们希望我们的研究结果将为这两个领域的整合提供一个起点，为未来的研究提供有用的指导，并加速透明神经影像学临床决策支持系统的开发。
