Anatomic Interpretability in Neuroimage Deep Learning: Saliency Approaches for Typical Aging and Traumatic Brain Injury

The black box nature of deep neural networks (DNNs) makes researchers and clinicians hesitant to rely on their findings. Saliency maps can enhance DNN explainability by suggesting the anatomic localization of relevant brain features. This study compares seven popular attribution-based saliency approaches to assign neuroanatomic interpretability to DNNs that estimate biological brain age (BA) from magnetic resonance imaging (MRI). Cognitively normal (CN) adults (N = 13,394, 5,900 males; mean age: 65.82 ± 8.89 years) are included for DNN training, testing, validation, and saliency map generation to estimate BA. To study saliency robustness to the presence of anatomic deviations from normality, saliency maps are also generated for adults with mild traumatic brain injury (mTBI, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>N</mml:mi></mml:math> = 214, 135 males; mean age: 55.3 ± 9.9 years). We assess saliency methods' capacities to capture known anatomic features of brain aging and compare them to a surrogate ground truth whose anatomic saliency is known a priori. Anatomic aging features are identified most reliably by the integrated gradients method, which outperforms all others through its ability to localize relevant anatomic features. Gradient Shapley additive explanations, input × gradient, and masked gradient perform less consistently but still highlight ubiquitous neuroanatomic features of aging (ventricle dilation, hippocampal atrophy, sulcal widening). Saliency methods involving gradient saliency, guided backpropagation, and guided gradient-weight class attribution mapping localize saliency outside the brain, which is undesirable. Our research suggests the relative tradeoffs of saliency methods to interpret DNN findings during BA estimation in typical aging and after mTBI.